Token | social |
Token ID | 14557 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
nesday | +3.314 |
mble | +3.307 |
pher | +3.008 |
cream | +2.774 |
displayText | +2.607 |
Neg logit contributions | |
Tik | -2.774 |
viral | -2.772 |
stride | -2.719 |
Kik | -2.584 |
characteristic | -2.546 |
Token | justice |
Token ID | 5316 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
nesday | +1.040 |
mble | +1.031 |
pher | +0.933 |
cream | +0.851 |
displayText | +0.815 |
Neg logit contributions | |
viral | -0.799 |
Tik | -0.798 |
stride | -0.775 |
Kik | -0.748 |
uni | -0.733 |
Token | math |
Token ID | 10688 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
viral | +1.265 |
Tik | +1.259 |
stride | +1.216 |
Kik | +1.154 |
characteristic | +1.141 |
Neg logit contributions | |
nesday | -2.141 |
mble | -2.129 |
pher | -1.929 |
cream | -1.785 |
displayText | -1.731 |
Token | ." |
Token ID | 526 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
mble | +5.696 |
nesday | +5.656 |
pher | +5.175 |
cream | +4.818 |
displayText | +4.522 |
Neg logit contributions | |
Tik | -3.433 |
viral | -3.403 |
stride | -3.341 |
Kik | -3.206 |
uni | -3.129 |
Token | ( |
Token ID | 357 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
nesday | +2.164 |
mble | +2.149 |
pher | +1.979 |
cream | +1.819 |
displayText | +1.745 |
Neg logit contributions | |
viral | -1.420 |
Tik | -1.386 |
stride | -1.384 |
characteristic | -1.298 |
Kik | -1.281 |
Token | Fre |
Token ID | 20366 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
mble | +4.336 |
nesday | +4.290 |
pher | +3.921 |
cream | +3.560 |
displayText | +3.351 |
Neg logit contributions | |
viral | -4.761 |
Tik | -4.714 |
stride | -4.651 |
Kik | -4.414 |
characteristic | -4.403 |
Token | ire |
Token ID | 557 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
nesday | +11.052 |
mble | +11.021 |
pher | +9.906 |
cream | +8.536 |
pel | +8.250 |
Neg logit contributions | |
Tik | -11.262 |
viral | -10.946 |
Kik | -10.640 |
stride | -10.566 |
squid | -10.350 |
Token | was |
Token ID | 373 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
nesday | +1.799 |
mble | +1.788 |
pher | +1.636 |
cream | +1.509 |
displayText | +1.453 |
Neg logit contributions | |
viral | -1.019 |
Tik | -1.016 |
stride | -0.987 |
Kik | -0.931 |
characteristic | -0.917 |
Token | a |
Token ID | 257 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
nesday | +3.800 |
mble | +3.763 |
pher | +3.460 |
cream | +3.163 |
displayText | +3.061 |
Neg logit contributions | |
Tik | -2.445 |
viral | -2.431 |
stride | -2.370 |
Kik | -2.246 |
uni | -2.227 |
Token | Brazilian |
Token ID | 17036 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
nesday | +1.394 |
mble | +1.388 |
pher | +1.275 |
cream | +1.185 |
displayText | +1.139 |
Neg logit contributions | |
Tik | -0.696 |
viral | -0.683 |
stride | -0.673 |
Kik | -0.631 |
uni | -0.624 |
Token | leftist |
Token ID | 28318 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
nesday | +2.495 |
mble | +2.479 |
pher | +2.292 |
cream | +2.127 |
displayText | +2.026 |
Neg logit contributions | |
Tik | -1.338 |
viral | -1.323 |
stride | -1.296 |
Kik | -1.219 |
uni | -1.209 |
Token | a |
Token ID | 257 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
viral | +1.325 |
Tik | +1.319 |
stride | +1.276 |
Kik | +1.209 |
characteristic | +1.188 |
Neg logit contributions | |
nesday | -2.373 |
mble | -2.363 |
pher | -2.150 |
cream | -1.992 |
displayText | -1.924 |
Token | referendum |
Token ID | 11467 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Tik | +0.192 |
viral | +0.191 |
stride | +0.184 |
Kik | +0.174 |
uni | +0.172 |
Neg logit contributions | |
nesday | -0.372 |
mble | -0.371 |
pher | -0.337 |
cream | -0.314 |
displayText | -0.303 |
Token | supported |
Token ID | 4855 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
viral | +3.106 |
Tik | +3.064 |
stride | +2.980 |
characteristic | +2.828 |
Kik | +2.824 |
Neg logit contributions | |
mble | -5.948 |
nesday | -5.933 |
pher | -5.323 |
cream | -5.022 |
displayText | -4.854 |
Token | by |
Token ID | 416 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
viral | +0.444 |
Tik | +0.441 |
stride | +0.429 |
Kik | +0.407 |
characteristic | +0.401 |
Neg logit contributions | |
nesday | -0.702 |
mble | -0.698 |
pher | -0.632 |
cream | -0.583 |
displayText | -0.563 |
Token | all |
Token ID | 477 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
mble | +1.727 |
nesday | +1.721 |
pher | +1.568 |
cream | +1.460 |
displayText | +1.380 |
Neg logit contributions | |
viral | -0.963 |
Tik | -0.955 |
stride | -0.931 |
uni | -0.875 |
Kik | -0.874 |
Token | Sloven |
Token ID | 30694 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Tik | +0.004 |
viral | +0.004 |
stride | +0.004 |
Kik | +0.004 |
uni | +0.004 |
Neg logit contributions | |
mble | -0.007 |
nesday | -0.007 |
pher | -0.007 |
cream | -0.006 |
displayText | -0.006 |
Token | ian |
Token ID | 666 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
nesday | +8.486 |
mble | +8.202 |
pher | +7.689 |
cream | +6.491 |
bourg | +5.925 |
Neg logit contributions | |
viral | -11.963 |
Tik | -11.803 |
stride | -11.566 |
Kik | -11.313 |
squid | -11.119 |
Token | political |
Token ID | 1964 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
mble | +4.278 |
nesday | +4.249 |
pher | +3.942 |
cream | +3.629 |
displayText | +3.459 |
Neg logit contributions | |
Tik | -2.560 |
viral | -2.560 |
stride | -2.493 |
Kik | -2.359 |
uni | -2.346 |
Token | parties |
Token ID | 4671 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
mble | +3.445 |
nesday | +3.407 |
pher | +3.095 |
cream | +2.824 |
displayText | +2.624 |
Neg logit contributions | |
Tik | -3.241 |
viral | -3.214 |
stride | -3.136 |
Kik | -3.004 |
uni | -2.981 |
Token | was |
Token ID | 373 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
nesday | +0.025 |
mble | +0.025 |
pher | +0.023 |
cream | +0.021 |
displayText | +0.020 |
Neg logit contributions | |
viral | -0.015 |
Tik | -0.015 |
stride | -0.014 |
Kik | -0.013 |
characteristic | -0.013 |
Token | held |
Token ID | 2714 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
nesday | +3.197 |
mble | +3.162 |
pher | +2.922 |
cream | +2.695 |
displayText | +2.619 |
Neg logit contributions | |
Tik | -1.609 |
viral | -1.603 |
stride | -1.547 |
Kik | -1.470 |
uni | -1.442 |
Token | injured |
Token ID | 6686 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
nesday | +1.769 |
mble | +1.751 |
pher | +1.603 |
cream | +1.475 |
displayText | +1.408 |
Neg logit contributions | |
Tik | -1.110 |
viral | -1.098 |
stride | -1.071 |
Kik | -1.016 |
uni | -1.012 |
Token | Robert |
Token ID | 5199 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
viral | +0.611 |
Tik | +0.609 |
stride | +0.591 |
Kik | +0.565 |
characteristic | +0.559 |
Neg logit contributions | |
nesday | -0.817 |
mble | -0.812 |
pher | -0.731 |
cream | -0.670 |
displayText | -0.641 |
Token | Kub |
Token ID | 24921 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
nesday | +7.151 |
mble | +6.915 |
pher | +6.447 |
cream | +5.997 |
bourg | +5.615 |
Neg logit contributions | |
viral | -4.794 |
stride | -4.674 |
Tik | -4.508 |
characteristic | -4.398 |
sighting | -4.235 |
Token | ica |
Token ID | 3970 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
nesday | +3.407 |
mble | +3.402 |
pher | +3.017 |
cream | +2.669 |
displayText | +2.489 |
Neg logit contributions | |
viral | -3.645 |
Tik | -3.634 |
stride | -3.525 |
Kik | -3.458 |
Gujar | -3.386 |
Token | at |
Token ID | 379 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
nesday | +2.310 |
mble | +2.281 |
pher | +2.117 |
cream | +1.951 |
displayText | +1.874 |
Neg logit contributions | |
viral | -1.236 |
Tik | -1.235 |
stride | -1.184 |
Kik | -1.133 |
uni | -1.122 |
Token | Renault |
Token ID | 44083 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
nesday | +0.737 |
mble | +0.732 |
pher | +0.670 |
cream | +0.615 |
displayText | +0.595 |
Neg logit contributions | |
viral | -0.413 |
Tik | -0.411 |
stride | -0.396 |
Kik | -0.376 |
uni | -0.375 |
Token | after |
Token ID | 706 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
nesday | +12.286 |
mble | +12.014 |
pher | +11.381 |
cream | +10.405 |
onica | +9.858 |
Neg logit contributions | |
Tik | -8.383 |
viral | -8.183 |
stride | -8.052 |
uni | -7.607 |
Gujar | -7.443 |
Token | setting |
Token ID | 4634 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
nesday | +3.256 |
mble | +3.196 |
pher | +2.934 |
cream | +2.669 |
displayText | +2.552 |
Neg logit contributions | |
Tik | -2.044 |
viral | -2.032 |
stride | -1.975 |
uni | -1.908 |
Kik | -1.872 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
nesday | +3.165 |
mble | +3.141 |
pher | +2.843 |
cream | +2.587 |
displayText | +2.443 |
Neg logit contributions | |
Tik | -2.214 |
viral | -2.183 |
stride | -2.092 |
Kik | -2.043 |
uni | -2.036 |
Token | fastest |
Token ID | 14162 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
mble | +4.796 |
nesday | +4.782 |
pher | +4.359 |
cream | +3.990 |
displayText | +3.798 |
Neg logit contributions | |
Tik | -2.739 |
viral | -2.671 |
stride | -2.567 |
uni | -2.475 |
Kik | -2.474 |
Token | time |
Token ID | 640 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
nesday | +2.623 |
mble | +2.612 |
pher | +2.407 |
cream | +2.224 |
displayText | +2.121 |
Neg logit contributions | |
Tik | -1.230 |
viral | -1.204 |
stride | -1.133 |
Kik | -1.110 |
uni | -1.105 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
viral | +0.307 |
Tik | +0.306 |
stride | +0.296 |
Kik | +0.282 |
characteristic | +0.275 |
Neg logit contributions | |
nesday | -0.531 |
mble | -0.528 |
pher | -0.483 |
cream | -0.446 |
displayText | -0.430 |
Token | its |
Token ID | 663 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
nesday | +0.803 |
mble | +0.800 |
pher | +0.731 |
cream | +0.670 |
displayText | +0.643 |
Neg logit contributions | |
viral | -0.505 |
Tik | -0.505 |
stride | -0.485 |
Kik | -0.465 |
characteristic | -0.455 |
Token | power |
Token ID | 1176 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
viral | +2.539 |
Tik | +2.527 |
stride | +2.461 |
characteristic | +2.321 |
Kik | +2.303 |
Neg logit contributions | |
nesday | -4.717 |
mble | -4.653 |
pher | -4.205 |
cream | -3.933 |
displayText | -3.831 |
Token | train |
Token ID | 27432 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
viral | +3.750 |
Tik | +3.733 |
stride | +3.668 |
characteristic | +3.491 |
Kik | +3.414 |
Neg logit contributions | |
nesday | -6.244 |
mble | -6.115 |
pher | -5.509 |
cream | -5.108 |
displayText | -4.984 |
Token | , |
Token ID | 11 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
viral | +2.397 |
Tik | +2.383 |
stride | +2.308 |
characteristic | +2.192 |
Kik | +2.176 |
Neg logit contributions | |
nesday | -4.578 |
mble | -4.520 |
pher | -4.077 |
cream | -3.814 |
displayText | -3.730 |
Token | dri |
Token ID | 1454 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
viral | +1.037 |
Tik | +1.033 |
stride | +0.999 |
Kik | +0.949 |
characteristic | +0.935 |
Neg logit contributions | |
nesday | -1.778 |
mble | -1.768 |
pher | -1.605 |
cream | -1.486 |
displayText | -1.438 |
Token | vel |
Token ID | 626 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
mble | +10.213 |
nesday | +9.840 |
pher | +9.284 |
cream | +8.045 |
ationally | +7.502 |
Neg logit contributions | |
Tik | -10.713 |
viral | -10.575 |
stride | -10.226 |
Kik | -10.128 |
Hawai | -9.959 |
Token | ine |
Token ID | 500 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
nesday | +2.454 |
mble | +2.440 |
pher | +2.202 |
cream | +2.012 |
displayText | +1.918 |
Neg logit contributions | |
viral | -1.889 |
Tik | -1.882 |
stride | -1.790 |
Kik | -1.749 |
characteristic | -1.719 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
viral | +0.864 |
Tik | +0.860 |
stride | +0.829 |
Kik | +0.782 |
characteristic | +0.769 |
Neg logit contributions | |
nesday | -1.777 |
mble | -1.766 |
pher | -1.614 |
cream | -1.502 |
displayText | -1.458 |
Token | traction |
Token ID | 23692 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Tik | +0.347 |
viral | +0.346 |
stride | +0.333 |
Kik | +0.319 |
uni | +0.313 |
Neg logit contributions | |
mble | -0.602 |
nesday | -0.601 |
pher | -0.550 |
cream | -0.505 |
displayText | -0.488 |
Token | control |
Token ID | 1630 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
mble | +2.181 |
nesday | +2.164 |
pher | +2.001 |
cream | +1.833 |
displayText | +1.769 |
Neg logit contributions | |
Tik | -1.278 |
viral | -1.274 |
stride | -1.216 |
Kik | -1.168 |
uni | -1.155 |
Token | probe |
Token ID | 12774 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
mble | +3.034 |
nesday | +3.001 |
pher | +2.770 |
cream | +2.537 |
displayText | +2.477 |
Neg logit contributions | |
Tik | -1.610 |
viral | -1.581 |
stride | -1.521 |
Kik | -1.458 |
uni | -1.443 |
Token | test |
Token ID | 1332 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
mble | +1.442 |
nesday | +1.436 |
pher | +1.313 |
cream | +1.209 |
displayText | +1.170 |
Neg logit contributions | |
Tik | -0.818 |
viral | -0.808 |
stride | -0.774 |
Kik | -0.747 |
uni | -0.737 |
Token | ( |
Token ID | 357 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
mble | +0.267 |
nesday | +0.267 |
pher | +0.242 |
cream | +0.224 |
displayText | +0.217 |
Neg logit contributions | |
Tik | -0.145 |
viral | -0.145 |
stride | -0.139 |
Kik | -0.133 |
uni | -0.130 |
Token | tri |
Token ID | 28461 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
nesday | +4.835 |
mble | +4.831 |
pher | +4.387 |
cream | +4.060 |
displayText | +3.869 |
Neg logit contributions | |
Tik | -3.750 |
viral | -3.708 |
stride | -3.604 |
Kik | -3.421 |
squid | -3.366 |
Token | ple |
Token ID | 1154 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
viral | +2.763 |
Tik | +2.755 |
stride | +2.706 |
Kik | +2.610 |
uni | +2.598 |
Neg logit contributions | |
nesday | -1.915 |
mble | -1.898 |
pher | -1.625 |
cream | -1.439 |
displayText | -1.375 |
Token | diss |
Token ID | 6249 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
viral | +1.675 |
Tik | +1.657 |
stride | +1.614 |
Kik | +1.518 |
characteristic | +1.497 |
Neg logit contributions | |
nesday | -3.202 |
mble | -3.178 |
pher | -2.904 |
cream | -2.693 |
displayText | -2.623 |
Token | ociation |
Token ID | 41003 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
nesday | +10.613 |
mble | +10.340 |
pher | +9.502 |
cream | +8.430 |
pel | +7.921 |
Neg logit contributions | |
Tik | -10.092 |
viral | -9.639 |
stride | -9.346 |
squid | -9.114 |
uni | -9.100 |
Token | | |
Token ID | 91 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
mble | +1.560 |
nesday | +1.559 |
pher | +1.422 |
cream | +1.306 |
displayText | +1.259 |
Neg logit contributions | |
Tik | -0.922 |
viral | -0.908 |
stride | -0.873 |
Kik | -0.840 |
uni | -0.837 |
Token | , |
Token ID | 11 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
nesday | +1.613 |
mble | +1.611 |
pher | +1.458 |
cream | +1.345 |
displayText | +1.280 |
Neg logit contributions | |
Tik | -1.234 |
viral | -1.223 |
stride | -1.186 |
Kik | -1.140 |
characteristic | -1.116 |
Token | ( |
Token ID | 357 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
viral | +0.475 |
Tik | +0.474 |
stride | +0.457 |
Kik | +0.434 |
characteristic | +0.426 |
Neg logit contributions | |
nesday | -0.847 |
mble | -0.843 |
pher | -0.768 |
cream | -0.711 |
displayText | -0.688 |
Token | D |
Token ID | 35 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
nesday | +2.964 |
mble | +2.963 |
pher | +2.668 |
cream | +2.475 |
displayText | +2.346 |
Neg logit contributions | |
Tik | -2.377 |
viral | -2.353 |
stride | -2.289 |
Kik | -2.195 |
characteristic | -2.156 |
Token | services |
Token ID | 2594 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
nesday | +2.251 |
mble | +2.219 |
pher | +2.062 |
cream | +1.904 |
displayText | +1.800 |
Neg logit contributions | |
Tik | -1.234 |
viral | -1.191 |
stride | -1.181 |
uni | -1.120 |
Kik | -1.103 |
Token | that |
Token ID | 326 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
nesday | +0.112 |
mble | +0.111 |
pher | +0.102 |
cream | +0.094 |
displayText | +0.090 |
Neg logit contributions | |
Tik | -0.068 |
viral | -0.067 |
stride | -0.066 |
Kik | -0.062 |
uni | -0.061 |
Token | have |
Token ID | 423 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
viral | +1.414 |
Tik | +1.405 |
stride | +1.361 |
Kik | +1.294 |
characteristic | +1.275 |
Neg logit contributions | |
nesday | -2.380 |
mble | -2.371 |
pher | -2.141 |
cream | -1.987 |
displayText | -1.924 |
Token | traditionally |
Token ID | 16083 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
viral | +0.073 |
Tik | +0.073 |
stride | +0.071 |
Kik | +0.068 |
characteristic | +0.067 |
Neg logit contributions | |
nesday | -0.108 |
mble | -0.107 |
pher | -0.097 |
cream | -0.089 |
displayText | -0.086 |
Token | been |
Token ID | 587 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
viral | +2.648 |
Tik | +2.600 |
stride | +2.547 |
characteristic | +2.418 |
Kik | +2.399 |
Neg logit contributions | |
nesday | -3.892 |
mble | -3.888 |
pher | -3.388 |
cream | -3.195 |
displayText | -3.104 |
Token | fre |
Token ID | 2030 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
viral | +0.084 |
Tik | +0.084 |
stride | +0.081 |
Kik | +0.076 |
characteristic | +0.075 |
Neg logit contributions | |
nesday | -0.162 |
mble | -0.161 |
pher | -0.147 |
cream | -0.137 |
displayText | -0.132 |
Token | ew |
Token ID | 413 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
nesday | +9.380 |
mble | +8.955 |
pher | +8.858 |
cream | +7.547 |
ationally | +7.237 |
Neg logit contributions | |
viral | -11.006 |
stride | -10.828 |
Tik | -10.792 |
sighting | -10.718 |
characteristic | -10.510 |
Token | he |
Token ID | 258 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
nesday | +2.129 |
mble | +2.115 |
pher | +1.869 |
cream | +1.684 |
displayText | +1.607 |
Neg logit contributions | |
viral | -2.187 |
Tik | -2.180 |
stride | -2.129 |
Kik | -2.053 |
characteristic | -2.030 |
Token | eling |
Token ID | 10809 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
viral | +1.513 |
Tik | +1.506 |
stride | +1.477 |
Kik | +1.431 |
characteristic | +1.414 |
Neg logit contributions | |
nesday | -1.182 |
mble | -1.177 |
pher | -1.011 |
cream | -0.905 |
displayText | -0.873 |
Token | forums |
Token ID | 14216 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
mble | +2.913 |
nesday | +2.901 |
pher | +2.676 |
cream | +2.446 |
displayText | +2.324 |
Neg logit contributions | |
Tik | -1.790 |
viral | -1.736 |
stride | -1.702 |
uni | -1.662 |
Kik | -1.628 |
Token | where |
Token ID | 810 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
viral | +1.679 |
Tik | +1.660 |
stride | +1.605 |
Kik | +1.522 |
characteristic | +1.506 |
Neg logit contributions | |
nesday | -3.050 |
mble | -3.035 |
pher | -2.743 |
cream | -2.553 |
displayText | -2.486 |
Token | back |
Token ID | 736 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
nesday | +3.146 |
mble | +3.144 |
pher | +2.871 |
cream | +2.654 |
displayText | +2.526 |
Neg logit contributions | |
viral | -1.857 |
Tik | -1.856 |
stride | -1.802 |
Kik | -1.705 |
uni | -1.693 |
Token | , |
Token ID | 11 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
nesday | +0.391 |
mble | +0.389 |
pher | +0.354 |
cream | +0.327 |
displayText | +0.315 |
Neg logit contributions | |
viral | -0.241 |
Tik | -0.241 |
stride | -0.233 |
Kik | -0.222 |
characteristic | -0.219 |
Token | winger |
Token ID | 31389 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
viral | +0.181 |
Tik | +0.180 |
stride | +0.174 |
Kik | +0.166 |
characteristic | +0.163 |
Neg logit contributions | |
nesday | -0.312 |
mble | -0.311 |
pher | -0.283 |
cream | -0.262 |
displayText | -0.253 |
Token | and |
Token ID | 290 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
nesday | +1.975 |
mble | +1.968 |
pher | +1.800 |
cream | +1.670 |
displayText | +1.597 |
Neg logit contributions | |
viral | -1.123 |
Tik | -1.122 |
stride | -1.072 |
Kik | -1.035 |
uni | -1.009 |
Token | first |
Token ID | 717 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
nesday | +2.514 |
mble | +2.508 |
pher | +2.299 |
cream | +2.128 |
displayText | +2.039 |
Neg logit contributions | |
Tik | -1.317 |
viral | -1.309 |
stride | -1.246 |
Kik | -1.195 |
uni | -1.176 |
Token | couple |
Token ID | 3155 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
mble | +3.338 |
nesday | +3.334 |
pher | +3.083 |
cream | +2.873 |
displayText | +2.735 |
Neg logit contributions | |
Tik | -1.580 |
viral | -1.570 |
stride | -1.489 |
Kik | -1.439 |
uni | -1.426 |
Token | of |
Token ID | 286 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
mble | +12.849 |
nesday | +12.771 |
pher | +11.937 |
cream | +10.913 |
umbledore | +9.994 |
Neg logit contributions | |
Tik | -7.007 |
viral | -6.876 |
stride | -6.523 |
Kik | -6.428 |
uni | -6.237 |
Token | attackers |
Token ID | 16391 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
nesday | +6.191 |
mble | +6.190 |
pher | +5.677 |
cream | +5.189 |
displayText | +4.955 |
Neg logit contributions | |
Tik | -3.526 |
viral | -3.501 |
stride | -3.349 |
uni | -3.239 |
Kik | -3.213 |
Token | to |
Token ID | 284 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
mble | +3.429 |
nesday | +3.425 |
pher | +3.134 |
cream | +2.921 |
displayText | +2.763 |
Neg logit contributions | |
Tik | -1.975 |
viral | -1.962 |
stride | -1.869 |
Kik | -1.820 |
uni | -1.780 |
Token | hold |
Token ID | 1745 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
mble | +2.515 |
nesday | +2.512 |
pher | +2.295 |
cream | +2.119 |
displayText | +2.033 |
Neg logit contributions | |
viral | -1.351 |
Tik | -1.346 |
stride | -1.287 |
Kik | -1.235 |
characteristic | -1.211 |
Token | defensive |
Token ID | 6110 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
viral | +0.856 |
Tik | +0.852 |
stride | +0.821 |
Kik | +0.779 |
characteristic | +0.765 |
Neg logit contributions | |
nesday | -1.618 |
mble | -1.611 |
pher | -1.468 |
cream | -1.363 |
displayText | -1.319 |
Token | Par |
Token ID | 2547 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
nesday | +0.882 |
mble | +0.876 |
pher | +0.801 |
cream | +0.738 |
displayText | +0.713 |
Neg logit contributions | |
viral | -0.490 |
Tik | -0.488 |
stride | -0.475 |
Kik | -0.449 |
characteristic | -0.443 |
Token | th |
Token ID | 400 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
viral | +0.209 |
Tik | +0.208 |
stride | +0.203 |
Kik | +0.192 |
uni | +0.191 |
Neg logit contributions | |
nesday | -0.294 |
mble | -0.293 |
pher | -0.261 |
cream | -0.241 |
displayText | -0.234 |
Token | iv |
Token ID | 452 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
viral | +2.873 |
Tik | +2.860 |
stride | +2.775 |
uni | +2.641 |
Kik | +2.621 |
Neg logit contributions | |
nesday | -4.045 |
mble | -3.996 |
pher | -3.493 |
displayText | -3.203 |
cream | -3.191 |
Token | I |
Token ID | 314 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
viral | +2.031 |
Tik | +2.005 |
stride | +1.922 |
Kik | +1.833 |
characteristic | +1.799 |
Neg logit contributions | |
mble | -3.455 |
nesday | -3.439 |
pher | -3.096 |
cream | -2.868 |
displayText | -2.789 |
Token | have |
Token ID | 423 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
nesday | +1.002 |
mble | +1.002 |
pher | +0.916 |
cream | +0.837 |
displayText | +0.808 |
Neg logit contributions | |
Tik | -0.685 |
viral | -0.684 |
stride | -0.660 |
Kik | -0.641 |
characteristic | -0.624 |
Token | fre |
Token ID | 2030 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
nesday | +0.237 |
mble | +0.236 |
pher | +0.213 |
cream | +0.193 |
displayText | +0.186 |
Neg logit contributions | |
viral | -0.191 |
Tik | -0.191 |
stride | -0.185 |
Kik | -0.179 |
characteristic | -0.175 |
Token | tted |
Token ID | 28734 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
nesday | +8.908 |
mble | +8.441 |
pher | +8.029 |
cream | +6.676 |
ationally | +6.566 |
Neg logit contributions | |
viral | -11.635 |
Tik | -11.333 |
stride | -11.307 |
Kik | -11.189 |
characteristic | -11.035 |
Token | over |
Token ID | 625 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
nesday | +3.349 |
mble | +3.345 |
pher | +3.071 |
cream | +2.792 |
displayText | +2.694 |
Neg logit contributions | |
Tik | -2.096 |
viral | -2.085 |
stride | -2.047 |
Kik | -1.959 |
uni | -1.939 |
Token | whether |
Token ID | 1771 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
nesday | +1.480 |
mble | +1.478 |
pher | +1.346 |
cream | +1.227 |
displayText | +1.185 |
Neg logit contributions | |
Tik | -0.937 |
viral | -0.936 |
stride | -0.915 |
Kik | -0.876 |
uni | -0.864 |
Token | it |
Token ID | 340 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
viral | +0.952 |
Tik | +0.947 |
stride | +0.911 |
Kik | +0.861 |
characteristic | +0.845 |
Neg logit contributions | |
nesday | -1.895 |
mble | -1.886 |
pher | -1.719 |
cream | -1.601 |
displayText | -1.555 |
Token | could |
Token ID | 714 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
viral | +0.794 |
Tik | +0.791 |
stride | +0.764 |
Kik | +0.725 |
characteristic | +0.714 |
Neg logit contributions | |
nesday | -1.400 |
mble | -1.393 |
pher | -1.266 |
cream | -1.173 |
displayText | -1.135 |
Token | this |
Token ID | 5661 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
nesday | +1.292 |
mble | +1.291 |
pher | +1.158 |
cream | +1.059 |
displayText | +1.007 |
Neg logit contributions | |
viral | -1.105 |
Tik | -1.100 |
stride | -1.068 |
Kik | -1.028 |
characteristic | -1.013 |
Token | maj |
Token ID | 16486 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
mble | +4.135 |
nesday | +4.072 |
pher | +3.785 |
cream | +3.484 |
displayText | +3.301 |
Neg logit contributions | |
Tik | -2.313 |
viral | -2.274 |
stride | -2.160 |
Kik | -2.110 |
uni | -2.088 |
Token | est |
Token ID | 395 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
Tik | +1.854 |
viral | +1.851 |
stride | +1.800 |
Kik | +1.709 |
uni | +1.689 |
Neg logit contributions | |
nesday | -2.960 |
mble | -2.935 |
pher | -2.652 |
cream | -2.453 |
displayText | -2.399 |
Token | ical |
Token ID | 605 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
mble | +1.947 |
nesday | +1.942 |
pher | +1.740 |
cream | +1.595 |
displayText | +1.493 |
Neg logit contributions | |
viral | -1.668 |
Tik | -1.667 |
stride | -1.613 |
Kik | -1.550 |
characteristic | -1.529 |
Token | roof |
Token ID | 9753 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
mble | +3.742 |
nesday | +3.668 |
pher | +3.429 |
cream | +3.168 |
displayText | +3.014 |
Neg logit contributions | |
Tik | -1.821 |
viral | -1.818 |
stride | -1.693 |
Kik | -1.661 |
uni | -1.655 |
Token | fre |
Token ID | 2030 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
mble | +1.725 |
nesday | +1.711 |
pher | +1.571 |
cream | +1.452 |
displayText | +1.380 |
Neg logit contributions | |
viral | -1.055 |
Tik | -1.049 |
stride | -1.001 |
Kik | -0.973 |
characteristic | -0.945 |
Token | tted |
Token ID | 28734 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
mble | +10.893 |
nesday | +10.721 |
pher | +10.254 |
cream | +8.882 |
maid | +8.230 |
Neg logit contributions | |
viral | -9.371 |
Tik | -9.108 |
stride | -8.728 |
Kik | -8.634 |
characteristic | -8.537 |
Token | with |
Token ID | 351 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
mble | +6.594 |
nesday | +6.470 |
pher | +5.990 |
cream | +5.535 |
displayText | +5.182 |
Neg logit contributions | |
Tik | -3.993 |
viral | -3.943 |
stride | -3.748 |
Kik | -3.704 |
uni | -3.668 |
Token | golden |
Token ID | 10861 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
mble | +2.629 |
nesday | +2.605 |
pher | +2.403 |
cream | +2.222 |
displayText | +2.116 |
Neg logit contributions | |
Tik | -1.470 |
viral | -1.454 |
stride | -1.400 |
Kik | -1.343 |
uni | -1.323 |
Token | fire |
Token ID | 2046 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
viral | +5.116 |
Tik | +5.084 |
stride | +4.968 |
characteristic | +4.684 |
Kik | +4.632 |
Neg logit contributions | |
nesday | -8.504 |
mble | -8.330 |
pher | -7.421 |
displayText | -6.886 |
cream | -6.800 |
Token | , |
Token ID | 11 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
mble | +1.388 |
nesday | +1.382 |
pher | +1.268 |
cream | +1.182 |
displayText | +1.123 |
Neg logit contributions | |
Tik | -0.776 |
viral | -0.775 |
stride | -0.744 |
Kik | -0.715 |
characteristic | -0.695 |
Token | low |
Token ID | 1877 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
viral | +1.548 |
Tik | +1.539 |
stride | +1.492 |
Kik | +1.398 |
characteristic | +1.383 |
Neg logit contributions | |
nesday | -3.031 |
mble | -3.015 |
pher | -2.752 |
cream | -2.556 |
displayText | -2.485 |
Token | point |
Token ID | 966 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
viral | +1.028 |
Tik | +1.023 |
stride | +0.993 |
Kik | +0.942 |
characteristic | +0.929 |
Neg logit contributions | |
nesday | -1.733 |
mble | -1.723 |
pher | -1.564 |
cream | -1.447 |
displayText | -1.401 |
Token | he |
Token ID | 339 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
viral | +0.412 |
Tik | +0.410 |
stride | +0.397 |
Kik | +0.378 |
characteristic | +0.371 |
Neg logit contributions | |
nesday | -0.692 |
mble | -0.688 |
pher | -0.625 |
cream | -0.577 |
displayText | -0.559 |
Token | drilled |
Token ID | 34936 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
viral | +0.895 |
Tik | +0.892 |
stride | +0.865 |
Kik | +0.820 |
characteristic | +0.814 |
Neg logit contributions | |
nesday | -1.414 |
mble | -1.410 |
pher | -1.255 |
cream | -1.170 |
displayText | -1.132 |
Token | 17 |
Token ID | 1596 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
nesday | +0.935 |
mble | +0.929 |
pher | +0.851 |
cream | +0.786 |
displayText | +0.755 |
Neg logit contributions | |
viral | -0.522 |
Tik | -0.518 |
stride | -0.501 |
Kik | -0.476 |
uni | -0.468 |
Token | dry |
Token ID | 5894 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
nesday | +1.095 |
mble | +1.088 |
pher | +0.983 |
cream | +0.895 |
displayText | +0.862 |
Neg logit contributions | |
viral | -0.833 |
Tik | -0.829 |
stride | -0.807 |
Kik | -0.774 |
characteristic | -0.761 |
Token | holes |
Token ID | 10421 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
nesday | +11.009 |
mble | +10.910 |
pher | +10.342 |
cream | +9.149 |
pel | +8.663 |
Neg logit contributions | |
Tik | -8.441 |
viral | -8.421 |
stride | -8.026 |
uni | -7.999 |
Kik | -7.839 |
Token | in |
Token ID | 287 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
nesday | +1.736 |
mble | +1.713 |
pher | +1.583 |
cream | +1.458 |
displayText | +1.399 |
Neg logit contributions | |
viral | -0.984 |
Tik | -0.979 |
stride | -0.950 |
Kik | -0.903 |
uni | -0.890 |
Token | a |
Token ID | 257 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
viral | +1.951 |
Tik | +1.950 |
stride | +1.881 |
Kik | +1.785 |
characteristic | +1.759 |
Neg logit contributions | |
nesday | -3.465 |
mble | -3.446 |
pher | -3.118 |
cream | -2.903 |
displayText | -2.828 |
Token | row |
Token ID | 5752 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
viral | +1.032 |
Tik | +1.028 |
stride | +0.992 |
Kik | +0.940 |
characteristic | +0.924 |
Neg logit contributions | |
nesday | -1.931 |
mble | -1.922 |
pher | -1.753 |
cream | -1.625 |
displayText | -1.573 |
Token | . |
Token ID | 13 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
nesday | +0.073 |
mble | +0.072 |
pher | +0.066 |
cream | +0.061 |
displayText | +0.059 |
Neg logit contributions | |
viral | -0.040 |
Tik | -0.040 |
stride | -0.039 |
Kik | -0.037 |
characteristic | -0.036 |
Token | Let |
Token ID | 3914 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
nesday | +0.001 |
mble | +0.001 |
pher | +0.001 |
cream | +0.001 |
displayText | +0.001 |
Neg logit contributions | |
viral | -0.000 |
Tik | -0.000 |
stride | -0.000 |
Kik | -0.000 |
characteristic | -0.000 |
Token | us |
Token ID | 514 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
viral | +2.034 |
Tik | +2.032 |
stride | +1.960 |
Kik | +1.871 |
characteristic | +1.853 |
Neg logit contributions | |
nesday | -3.108 |
mble | -3.095 |
pher | -2.797 |
cream | -2.582 |
displayText | -2.496 |
Token | remember |
Token ID | 3505 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
viral | +0.900 |
Tik | +0.898 |
stride | +0.865 |
Kik | +0.833 |
characteristic | +0.817 |
Neg logit contributions | |
nesday | -1.360 |
mble | -1.353 |
pher | -1.227 |
cream | -1.125 |
displayText | -1.086 |
Token | that |
Token ID | 326 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
viral | +0.155 |
Tik | +0.154 |
stride | +0.149 |
Kik | +0.142 |
characteristic | +0.139 |
Neg logit contributions | |
nesday | -0.254 |
mble | -0.253 |
pher | -0.229 |
cream | -0.211 |
displayText | -0.204 |
Token | the |
Token ID | 262 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
viral | +1.699 |
Tik | +1.692 |
stride | +1.634 |
Kik | +1.551 |
characteristic | +1.529 |
Neg logit contributions | |
nesday | -3.022 |
mble | -3.005 |
pher | -2.734 |
cream | -2.534 |
displayText | -2.457 |
Token | Sloven |
Token ID | 30694 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
viral | +0.222 |
Tik | +0.221 |
stride | +0.213 |
Kik | +0.203 |
characteristic | +0.199 |
Neg logit contributions | |
nesday | -0.395 |
mble | -0.393 |
pher | -0.357 |
cream | -0.331 |
displayText | -0.320 |
Token | ian |
Token ID | 666 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
nesday | +8.973 |
mble | +8.719 |
pher | +7.992 |
cream | +6.983 |
displayText | +6.555 |
Neg logit contributions | |
Tik | -10.713 |
viral | -10.645 |
stride | -10.331 |
Kik | -10.136 |
Hawai | -10.036 |
Token | government |
Token ID | 1230 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
nesday | +4.628 |
mble | +4.594 |
pher | +4.201 |
cream | +3.884 |
displayText | +3.760 |
Neg logit contributions | |
Tik | -2.758 |
viral | -2.756 |
stride | -2.651 |
Kik | -2.527 |
uni | -2.518 |
Token | declared |
Token ID | 6875 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
nesday | +0.724 |
mble | +0.718 |
pher | +0.658 |
cream | +0.606 |
displayText | +0.587 |
Neg logit contributions | |
viral | -0.424 |
Tik | -0.423 |
stride | -0.408 |
Kik | -0.390 |
characteristic | -0.381 |
Token | independence |
Token ID | 10404 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
viral | +2.597 |
Tik | +2.585 |
stride | +2.512 |
Kik | +2.393 |
characteristic | +2.382 |
Neg logit contributions | |
nesday | -3.525 |
mble | -3.508 |
pher | -3.162 |
cream | -2.911 |
displayText | -2.815 |
Token | in |
Token ID | 287 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
viral | +1.797 |
Tik | +1.781 |
stride | +1.724 |
Kik | +1.618 |
characteristic | +1.612 |
Neg logit contributions | |
mble | -3.502 |
nesday | -3.498 |
pher | -3.172 |
cream | -2.949 |
displayText | -2.867 |
Token | spect |
Token ID | 4443 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
mble | +1.812 |
nesday | +1.794 |
pher | +1.668 |
cream | +1.528 |
displayText | +1.431 |
Neg logit contributions | |
Tik | -1.331 |
viral | -1.327 |
stride | -1.281 |
Kik | -1.242 |
squid | -1.205 |
Token | ral |
Token ID | 1373 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
mble | +3.210 |
nesday | +3.110 |
pher | +2.870 |
cream | +2.568 |
displayText | +2.370 |
Neg logit contributions | |
viral | -3.393 |
Tik | -3.366 |
stride | -3.319 |
Kik | -3.220 |
squid | -3.130 |
Token | response |
Token ID | 2882 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
mble | +1.244 |
nesday | +1.231 |
pher | +1.148 |
cream | +1.058 |
displayText | +1.003 |
Neg logit contributions | |
viral | -0.665 |
Tik | -0.660 |
stride | -0.631 |
Kik | -0.609 |
uni | -0.597 |
Token | at |
Token ID | 379 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
viral | +1.561 |
Tik | +1.549 |
stride | +1.503 |
Kik | +1.407 |
characteristic | +1.405 |
Neg logit contributions | |
nesday | -3.135 |
mble | -3.109 |
pher | -2.825 |
cream | -2.631 |
displayText | -2.570 |
Token | higher |
Token ID | 2440 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
viral | +1.577 |
Tik | +1.570 |
stride | +1.513 |
Kik | +1.434 |
characteristic | +1.403 |
Neg logit contributions | |
nesday | -3.145 |
mble | -3.131 |
pher | -2.868 |
cream | -2.662 |
displayText | -2.572 |
Token | sensit |
Token ID | 44752 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
viral | +2.035 |
Tik | +2.022 |
stride | +1.948 |
Kik | +1.835 |
characteristic | +1.811 |
Neg logit contributions | |
nesday | -4.172 |
mble | -4.137 |
pher | -3.765 |
cream | -3.513 |
displayText | -3.430 |
Token | ivities |
Token ID | 28720 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
mble | +7.271 |
nesday | +7.239 |
pher | +6.920 |
cream | +5.741 |
ison | +5.285 |
Neg logit contributions | |
Tik | -12.204 |
viral | -11.950 |
stride | -11.908 |
uni | -11.421 |
Kik | -11.379 |
Token | though |
Token ID | 996 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
mble | +3.119 |
nesday | +3.103 |
pher | +2.867 |
cream | +2.658 |
displayText | +2.515 |
Neg logit contributions | |
Tik | -1.817 |
viral | -1.792 |
stride | -1.732 |
Kik | -1.671 |
uni | -1.637 |
Token | , |
Token ID | 11 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
viral | +0.342 |
Tik | +0.342 |
stride | +0.330 |
Kik | +0.315 |
characteristic | +0.307 |
Neg logit contributions | |
mble | -0.614 |
nesday | -0.612 |
pher | -0.560 |
cream | -0.518 |
displayText | -0.498 |
Token | which |
Token ID | 543 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
viral | +0.227 |
Tik | +0.227 |
stride | +0.218 |
Kik | +0.207 |
characteristic | +0.202 |
Neg logit contributions | |
nesday | -0.425 |
mble | -0.423 |
pher | -0.388 |
cream | -0.359 |
displayText | -0.346 |
Token | is |
Token ID | 318 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
nesday | +2.394 |
mble | +2.384 |
pher | +2.189 |
cream | +2.015 |
displayText | +1.923 |
Neg logit contributions | |
viral | -1.426 |
Tik | -1.423 |
stride | -1.369 |
Kik | -1.308 |
uni | -1.276 |
Token | a |
Token ID | 257 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
viral | +0.252 |
Tik | +0.250 |
stride | +0.241 |
Kik | +0.229 |
uni | +0.223 |
Neg logit contributions | |
nesday | -0.492 |
mble | -0.490 |
pher | -0.448 |
cream | -0.415 |
displayText | -0.401 |
Token | building |
Token ID | 2615 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
viral | +0.744 |
Tik | +0.743 |
stride | +0.715 |
Kik | +0.678 |
characteristic | +0.657 |
Neg logit contributions | |
nesday | -1.483 |
mble | -1.479 |
pher | -1.352 |
cream | -1.254 |
displayText | -1.214 |
Token | is |
Token ID | 318 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
viral | +1.788 |
Tik | +1.781 |
stride | +1.716 |
Kik | +1.621 |
characteristic | +1.593 |
Neg logit contributions | |
nesday | -3.582 |
mble | -3.564 |
pher | -3.256 |
cream | -3.026 |
displayText | -2.934 |
Token | constructed |
Token ID | 12006 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
viral | +0.490 |
Tik | +0.489 |
stride | +0.472 |
Kik | +0.446 |
characteristic | +0.436 |
Neg logit contributions | |
nesday | -0.947 |
mble | -0.942 |
pher | -0.862 |
cream | -0.799 |
displayText | -0.774 |
Token | . |
Token ID | 13 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
nesday | +1.658 |
mble | +1.654 |
pher | +1.518 |
cream | +1.411 |
displayText | +1.356 |
Neg logit contributions | |
Tik | -0.858 |
viral | -0.853 |
stride | -0.821 |
Kik | -0.789 |
squid | -0.756 |
Token | Dri |
Token ID | 5809 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
viral | +1.013 |
Tik | +1.011 |
stride | +0.975 |
Kik | +0.928 |
characteristic | +0.913 |
Neg logit contributions | |
nesday | -1.752 |
mble | -1.743 |
pher | -1.582 |
cream | -1.464 |
displayText | -1.418 |
Token | ven |
Token ID | 574 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
nesday | +8.866 |
mble | +8.726 |
pher | +7.820 |
cream | +6.890 |
pel | +6.480 |
Neg logit contributions | |
Tik | -10.634 |
viral | -10.460 |
stride | -10.373 |
Kik | -10.218 |
Gujar | -9.937 |
Token | by |
Token ID | 416 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
nesday | +6.018 |
mble | +5.931 |
pher | +5.411 |
cream | +4.927 |
displayText | +4.682 |
Neg logit contributions | |
Tik | -4.447 |
viral | -4.357 |
stride | -4.336 |
Kik | -4.253 |
Hawai | -4.009 |
Token | utility |
Token ID | 10361 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
nesday | +0.392 |
mble | +0.390 |
pher | +0.357 |
cream | +0.330 |
displayText | +0.317 |
Neg logit contributions | |
Tik | -0.219 |
viral | -0.219 |
stride | -0.212 |
Kik | -0.201 |
uni | -0.197 |
Token | , |
Token ID | 11 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
viral | +0.758 |
Tik | +0.755 |
stride | +0.728 |
Kik | +0.689 |
characteristic | +0.677 |
Neg logit contributions | |
nesday | -1.453 |
mble | -1.446 |
pher | -1.320 |
cream | -1.225 |
displayText | -1.187 |
Token | aesthetic |
Token ID | 19713 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
viral | +1.452 |
Tik | +1.447 |
stride | +1.397 |
Kik | +1.325 |
characteristic | +1.301 |
Neg logit contributions | |
nesday | -2.665 |
mble | -2.652 |
pher | -2.416 |
cream | -2.240 |
displayText | -2.168 |
Token | maybe |
Token ID | 3863 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
viral | +0.082 |
Tik | +0.082 |
stride | +0.079 |
Kik | +0.076 |
characteristic | +0.074 |
Neg logit contributions | |
nesday | -0.130 |
mble | -0.130 |
pher | -0.117 |
cream | -0.108 |
displayText | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
nesday | +2.322 |
mble | +2.312 |
pher | +2.110 |
cream | +1.954 |
displayText | +1.881 |
Neg logit contributions | |
Tik | -1.292 |
viral | -1.282 |
stride | -1.243 |
Kik | -1.186 |
uni | -1.159 |
Token | we |
Token ID | 356 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
nesday | +0.863 |
mble | +0.857 |
pher | +0.781 |
cream | +0.722 |
displayText | +0.696 |
Neg logit contributions | |
Tik | -0.496 |
viral | -0.495 |
stride | -0.479 |
Kik | -0.456 |
characteristic | -0.447 |
Token | should |
Token ID | 815 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
mble | +3.611 |
nesday | +3.595 |
pher | +3.323 |
cream | +3.034 |
displayText | +2.883 |
Neg logit contributions | |
Tik | -2.262 |
viral | -2.252 |
stride | -2.164 |
Kik | -2.115 |
characteristic | -2.061 |
Token | be |
Token ID | 307 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
viral | +0.231 |
Tik | +0.231 |
stride | +0.223 |
Kik | +0.213 |
characteristic | +0.209 |
Neg logit contributions | |
nesday | -0.377 |
mble | -0.375 |
pher | -0.340 |
cream | -0.314 |
displayText | -0.304 |
Token | incentiv |
Token ID | 39678 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
nesday | +0.230 |
mble | +0.228 |
pher | +0.207 |
cream | +0.191 |
displayText | +0.185 |
Neg logit contributions | |
viral | -0.143 |
Tik | -0.142 |
stride | -0.138 |
Kik | -0.131 |
characteristic | -0.129 |
Token | izing |
Token ID | 2890 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
nesday | +7.586 |
mble | +7.159 |
pher | +6.559 |
cream | +5.617 |
ationally | +5.082 |
Neg logit contributions | |
viral | -12.355 |
Tik | -12.192 |
stride | -12.020 |
Gujar | -11.541 |
Kik | -11.486 |
Token | them |
Token ID | 606 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
nesday | +1.473 |
mble | +1.469 |
pher | +1.326 |
cream | +1.222 |
displayText | +1.176 |
Neg logit contributions | |
Tik | -0.974 |
viral | -0.969 |
stride | -0.940 |
Kik | -0.900 |
characteristic | -0.883 |
Token | to |
Token ID | 284 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
nesday | +0.926 |
mble | +0.919 |
pher | +0.833 |
cream | +0.764 |
displayText | +0.736 |
Neg logit contributions | |
viral | -0.642 |
Tik | -0.642 |
stride | -0.621 |
Kik | -0.595 |
characteristic | -0.585 |
Token | solve |
Token ID | 8494 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
viral | +1.489 |
Tik | +1.461 |
stride | +1.443 |
Kik | +1.351 |
characteristic | +1.331 |
Neg logit contributions | |
nesday | -2.598 |
mble | -2.589 |
pher | -2.337 |
cream | -2.176 |
displayText | -2.117 |
Token | them |
Token ID | 606 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
nesday | +2.673 |
mble | +2.666 |
pher | +2.428 |
cream | +2.233 |
displayText | +2.131 |
Neg logit contributions | |
Tik | -1.716 |
viral | -1.675 |
stride | -1.647 |
Kik | -1.574 |
uni | -1.552 |
Token | ,' |
Token ID | 4032 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
nesday | +2.569 |
mble | +2.563 |
pher | +2.328 |
cream | +2.136 |
displayText | +2.065 |
Neg logit contributions | |
Tik | -1.676 |
viral | -1.675 |
stride | -1.605 |
Kik | -1.542 |
characteristic | -1.513 |
Token | said |
Token ID | 531 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
viral | +0.138 |
Tik | +0.137 |
stride | +0.133 |
Kik | +0.127 |
uni | +0.125 |
Neg logit contributions | |
nesday | -0.237 |
mble | -0.236 |
pher | -0.217 |
cream | -0.200 |
displayText | -0.192 |
Token | Jack |
Token ID | 3619 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
mble | +2.154 |
nesday | +2.147 |
pher | +1.969 |
cream | +1.804 |
displayText | +1.723 |
Neg logit contributions | |
viral | -1.304 |
Tik | -1.284 |
stride | -1.253 |
Kik | -1.200 |
uni | -1.186 |
Token | . |
Token ID | 13 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
viral | +2.066 |
Tik | +2.061 |
stride | +2.007 |
Kik | +1.887 |
characteristic | +1.869 |
Neg logit contributions | |
nesday | -3.807 |
mble | -3.773 |
pher | -3.418 |
cream | -3.174 |
displayText | -3.066 |
Token | ' |
Token ID | 705 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
nesday | +1.727 |
mble | +1.721 |
pher | +1.593 |
cream | +1.479 |
displayText | +1.421 |
Neg logit contributions | |
viral | -0.884 |
Tik | -0.857 |
stride | -0.842 |
Kik | -0.788 |
characteristic | -0.786 |
Token | Sex |
Token ID | 23398 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
mble | +3.969 |
nesday | +3.935 |
pher | +3.606 |
cream | +3.246 |
displayText | +3.051 |
Neg logit contributions | |
viral | -4.690 |
Tik | -4.602 |
stride | -4.548 |
characteristic | -4.357 |
Kik | -4.315 |
Token | has |
Token ID | 468 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
nesday | +11.702 |
mble | +11.627 |
pher | +10.969 |
cream | +9.940 |
displayText | +9.243 |
Neg logit contributions | |
Tik | -7.874 |
viral | -7.776 |
stride | -7.410 |
Kik | -7.106 |
Gujar | -7.000 |
Token | never |
Token ID | 1239 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
nesday | +2.022 |
mble | +2.015 |
pher | +1.838 |
cream | +1.691 |
displayText | +1.618 |
Neg logit contributions | |
Tik | -1.271 |
viral | -1.268 |
stride | -1.223 |
Kik | -1.169 |
uni | -1.148 |
Token | entered |
Token ID | 5982 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
nesday | +0.364 |
mble | +0.362 |
pher | +0.326 |
cream | +0.299 |
displayText | +0.289 |
Neg logit contributions | |
viral | -0.265 |
Tik | -0.264 |
stride | -0.256 |
Kik | -0.245 |
characteristic | -0.242 |
Token | my |
Token ID | 616 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
viral | +0.394 |
Tik | +0.393 |
stride | +0.379 |
Kik | +0.363 |
characteristic | +0.357 |
Neg logit contributions | |
nesday | -0.607 |
mble | -0.605 |
pher | -0.548 |
cream | -0.504 |
displayText | -0.486 |
Token | mind |
Token ID | 2000 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
Tik | +0.394 |
viral | +0.393 |
stride | +0.375 |
Kik | +0.360 |
uni | +0.350 |
Neg logit contributions | |
nesday | -0.752 |
mble | -0.751 |
pher | -0.684 |
cream | -0.634 |
displayText | -0.612 |
Token | what |
Token ID | 644 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
nesday | +5.449 |
mble | +5.413 |
pher | +4.957 |
cream | +4.488 |
displayText | +4.220 |
Neg logit contributions | |
Tik | -4.382 |
stride | -4.286 |
viral | -4.274 |
Kik | -4.145 |
uni | -4.080 |
Token | we |
Token ID | 356 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
nesday | +6.063 |
mble | +5.990 |
pher | +5.607 |
cream | +5.091 |
displayText | +4.912 |
Neg logit contributions | |
Tik | -3.194 |
stride | -3.158 |
viral | -3.134 |
Kik | -3.062 |
uni | -2.950 |
Token | can |
Token ID | 460 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
nesday | +5.127 |
mble | +5.083 |
pher | +4.762 |
cream | +4.385 |
displayText | +4.145 |
Neg logit contributions | |
Tik | -2.687 |
viral | -2.675 |
stride | -2.587 |
Kik | -2.547 |
uni | -2.444 |
Token | say |
Token ID | 910 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
nesday | +3.652 |
mble | +3.593 |
pher | +3.310 |
cream | +2.955 |
displayText | +2.766 |
Neg logit contributions | |
Tik | -3.025 |
viral | -2.975 |
stride | -2.904 |
Kik | -2.870 |
uni | -2.805 |
Token | , |
Token ID | 11 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
nesday | +2.864 |
mble | +2.843 |
pher | +2.583 |
cream | +2.377 |
displayText | +2.295 |
Neg logit contributions | |
Tik | -1.813 |
viral | -1.781 |
stride | -1.747 |
Kik | -1.690 |
characteristic | -1.630 |
Token | see |
Token ID | 766 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
nesday | +3.216 |
mble | +3.197 |
pher | +2.943 |
cream | +2.681 |
displayText | +2.566 |
Neg logit contributions | |
Tik | -2.069 |
viral | -2.045 |
stride | -2.010 |
Kik | -1.933 |
uni | -1.927 |
Token | or |
Token ID | 393 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
nesday | +11.014 |
mble | +10.989 |
pher | +9.971 |
cream | +8.984 |
displayText | +8.780 |
Neg logit contributions | |
Tik | -8.189 |
viral | -8.092 |
stride | -7.998 |
Kik | -7.894 |
squid | -7.644 |
Token | hear |
Token ID | 3285 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
nesday | +5.845 |
mble | +5.793 |
pher | +5.371 |
cream | +4.722 |
displayText | +4.423 |
Neg logit contributions | |
Tik | -5.233 |
viral | -5.013 |
stride | -4.942 |
Kik | -4.899 |
uni | -4.805 |
Token | ? |
Token ID | 30 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
nesday | +5.767 |
mble | +5.710 |
pher | +5.157 |
cream | +4.694 |
displayText | +4.501 |
Neg logit contributions | |
Tik | -4.481 |
stride | -4.385 |
viral | -4.368 |
Kik | -4.241 |
squid | -4.094 |
Token | Who |
Token ID | 5338 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
nesday | +1.728 |
mble | +1.719 |
pher | +1.580 |
cream | +1.459 |
displayText | +1.408 |
Neg logit contributions | |
viral | -1.043 |
Tik | -1.033 |
stride | -1.012 |
characteristic | -0.952 |
Kik | -0.951 |
Token | decides |
Token ID | 13267 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
nesday | +2.772 |
mble | +2.756 |
pher | +2.526 |
cream | +2.323 |
displayText | +2.245 |
Neg logit contributions | |
viral | -1.650 |
Tik | -1.647 |
stride | -1.594 |
Kik | -1.521 |
characteristic | -1.498 |
Token | starch |
Token ID | 39515 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
viral | +2.544 |
Tik | +2.525 |
stride | +2.446 |
Kik | +2.287 |
characteristic | +2.277 |
Neg logit contributions | |
nesday | -4.984 |
mble | -4.973 |
pher | -4.517 |
cream | -4.180 |
displayText | -4.084 |
Token | ( |
Token ID | 357 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
nesday | +3.764 |
mble | +3.738 |
pher | +3.418 |
cream | +3.237 |
displayText | +3.007 |
Neg logit contributions | |
Tik | -2.100 |
viral | -2.081 |
stride | -2.009 |
Kik | -1.943 |
uni | -1.897 |
Token | which |
Token ID | 4758 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
nesday | +4.387 |
mble | +4.365 |
pher | +4.023 |
cream | +3.785 |
displayText | +3.492 |
Neg logit contributions | |
viral | -3.474 |
stride | -3.421 |
Tik | -3.419 |
Kik | -3.164 |
sighting | -3.153 |
Token | is |
Token ID | 318 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
nesday | +2.067 |
mble | +2.057 |
pher | +1.892 |
cream | +1.759 |
displayText | +1.680 |
Neg logit contributions | |
viral | -1.135 |
Tik | -1.128 |
stride | -1.113 |
Kik | -1.038 |
characteristic | -1.018 |
Token | ground |
Token ID | 2323 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
nesday | +0.080 |
mble | +0.079 |
pher | +0.072 |
cream | +0.066 |
displayText | +0.064 |
Neg logit contributions | |
viral | -0.053 |
Tik | -0.053 |
stride | -0.052 |
Kik | -0.049 |
uni | -0.048 |
Token | dehyd |
Token ID | 28151 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
nesday | +2.323 |
mble | +2.308 |
pher | +2.120 |
cream | +1.982 |
displayText | +1.863 |
Neg logit contributions | |
Tik | -1.363 |
viral | -1.358 |
stride | -1.339 |
Kik | -1.266 |
uni | -1.246 |
Token | rated |
Token ID | 4111 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
mble | +8.217 |
nesday | +8.182 |
pher | +7.794 |
cream | +6.649 |
ationally | +5.942 |
Neg logit contributions | |
Tik | -11.612 |
stride | -11.337 |
viral | -11.181 |
sighting | -10.971 |
Kik | -10.898 |
Token | k |
Token ID | 479 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
mble | +2.782 |
nesday | +2.762 |
pher | +2.559 |
cream | +2.384 |
displayText | +2.259 |
Neg logit contributions | |
viral | -1.491 |
Tik | -1.491 |
stride | -1.487 |
uni | -1.362 |
Kik | -1.360 |
Token | uz |
Token ID | 10277 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
viral | +2.656 |
Tik | +2.642 |
stride | +2.543 |
Kik | +2.436 |
uni | +2.427 |
Neg logit contributions | |
nesday | -4.254 |
mble | -4.242 |
pher | -3.829 |
cream | -3.529 |
displayText | -3.440 |
Token | u |
Token ID | 84 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
nesday | +0.108 |
mble | +0.108 |
pher | +0.099 |
cream | +0.092 |
displayText | +0.087 |
Neg logit contributions | |
viral | -0.060 |
Tik | -0.060 |
stride | -0.058 |
Kik | -0.055 |
characteristic | -0.054 |
Token | root |
Token ID | 6808 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
viral | +3.024 |
Tik | +3.004 |
stride | +2.897 |
characteristic | +2.732 |
Kik | +2.730 |
Neg logit contributions | |
nesday | -5.280 |
mble | -5.261 |
pher | -4.753 |
cream | -4.376 |
displayText | -4.298 |
Token | Baldwin |
Token ID | 26402 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
nesday | +3.990 |
mble | +3.979 |
pher | +3.664 |
cream | +3.402 |
displayText | +3.276 |
Neg logit contributions | |
viral | -2.022 |
Tik | -1.995 |
stride | -1.938 |
Kik | -1.824 |
characteristic | -1.802 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
nesday | +3.762 |
mble | +3.736 |
pher | +3.489 |
cream | +3.244 |
displayText | +3.120 |
Neg logit contributions | |
viral | -1.818 |
Tik | -1.815 |
stride | -1.752 |
Kik | -1.650 |
characteristic | -1.635 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
nesday | +0.747 |
mble | +0.745 |
pher | +0.676 |
cream | +0.633 |
displayText | +0.616 |
Neg logit contributions | |
viral | -0.305 |
Tik | -0.304 |
stride | -0.291 |
Kik | -0.273 |
characteristic | -0.266 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
nesday | +4.191 |
mble | +4.149 |
pher | +3.779 |
cream | +3.463 |
displayText | +3.347 |
Neg logit contributions | |
Tik | -3.420 |
viral | -3.386 |
stride | -3.316 |
Kik | -3.162 |
characteristic | -3.137 |
Token | Steve |
Token ID | 6542 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
nesday | +1.709 |
mble | +1.699 |
pher | +1.537 |
cream | +1.392 |
displayText | +1.312 |
Neg logit contributions | |
viral | -1.489 |
stride | -1.481 |
Tik | -1.476 |
uni | -1.398 |
characteristic | -1.388 |
Token | Care |
Token ID | 7276 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Tik | +3.223 |
viral | +3.188 |
stride | +3.038 |
Kik | +3.038 |
characteristic | +2.874 |
Neg logit contributions | |
mble | -5.036 |
nesday | -5.033 |
pher | -4.381 |
cream | -3.966 |
displayText | -3.947 |
Token | ll |
Token ID | 297 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
mble | +6.918 |
nesday | +6.825 |
pher | +6.466 |
cream | +5.804 |
bourg | +5.071 |
Neg logit contributions | |
Tik | -12.989 |
viral | -12.819 |
stride | -12.642 |
Kik | -12.407 |
squid | -12.385 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
nesday | +5.887 |
mble | +5.838 |
pher | +5.554 |
cream | +5.149 |
displayText | +4.911 |
Neg logit contributions | |
Tik | -3.238 |
viral | -3.192 |
stride | -3.165 |
characteristic | -2.992 |
Kik | -2.960 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
nesday | +0.736 |
mble | +0.734 |
pher | +0.666 |
cream | +0.623 |
displayText | +0.606 |
Neg logit contributions | |
viral | -0.299 |
Tik | -0.298 |
stride | -0.284 |
Kik | -0.267 |
characteristic | -0.261 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
nesday | +4.503 |
mble | +4.456 |
pher | +4.054 |
cream | +3.720 |
displayText | +3.595 |
Neg logit contributions | |
Tik | -3.589 |
viral | -3.565 |
stride | -3.486 |
Kik | -3.328 |
characteristic | -3.295 |
Token | Lee |
Token ID | 5741 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
nesday | +2.663 |
mble | +2.645 |
pher | +2.399 |
cream | +2.176 |
displayText | +2.047 |
Neg logit contributions | |
stride | -2.307 |
viral | -2.299 |
Tik | -2.270 |
uni | -2.166 |
characteristic | -2.153 |
Token | back |
Token ID | 736 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
nesday | +0.322 |
mble | +0.321 |
pher | +0.294 |
cream | +0.273 |
displayText | +0.264 |
Neg logit contributions | |
Tik | -0.159 |
viral | -0.158 |
stride | -0.154 |
Kik | -0.145 |
uni | -0.142 |
Token | burner |
Token ID | 46027 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
Tik | +0.450 |
viral | +0.449 |
stride | +0.437 |
Kik | +0.420 |
characteristic | +0.414 |
Neg logit contributions | |
nesday | -0.565 |
mble | -0.563 |
pher | -0.506 |
cream | -0.466 |
displayText | -0.444 |
Token | , |
Token ID | 11 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
nesday | +3.113 |
mble | +3.080 |
pher | +2.822 |
cream | +2.609 |
displayText | +2.507 |
Neg logit contributions | |
Tik | -1.886 |
viral | -1.868 |
stride | -1.814 |
Kik | -1.740 |
uni | -1.703 |
Token | I |
Token ID | 314 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
Tik | +0.218 |
viral | +0.217 |
stride | +0.210 |
Kik | +0.199 |
characteristic | +0.195 |
Neg logit contributions | |
nesday | -0.407 |
mble | -0.405 |
pher | -0.371 |
cream | -0.343 |
displayText | -0.332 |
Token | was |
Token ID | 373 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
nesday | +0.235 |
mble | +0.234 |
pher | +0.212 |
cream | +0.195 |
displayText | +0.188 |
Neg logit contributions | |
viral | -0.156 |
Tik | -0.155 |
stride | -0.150 |
Kik | -0.144 |
characteristic | -0.141 |
Token | freed |
Token ID | 13459 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
nesday | +3.074 |
mble | +3.061 |
pher | +2.818 |
cream | +2.573 |
displayText | +2.492 |
Neg logit contributions | |
Tik | -1.966 |
viral | -1.943 |
stride | -1.872 |
Kik | -1.802 |
characteristic | -1.764 |
Token | up |
Token ID | 510 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
nesday | +10.884 |
mble | +10.759 |
pher | +9.819 |
cream | +9.103 |
displayText | +8.379 |
Neg logit contributions | |
Tik | -8.490 |
viral | -8.018 |
Kik | -7.845 |
Gujar | -7.786 |
stride | -7.743 |
Token | to |
Token ID | 284 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
nesday | +3.351 |
mble | +3.341 |
pher | +3.017 |
cream | +2.753 |
displayText | +2.647 |
Neg logit contributions | |
Tik | -2.607 |
viral | -2.579 |
stride | -2.492 |
Kik | -2.414 |
uni | -2.385 |
Token | focus |
Token ID | 2962 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
nesday | +3.493 |
mble | +3.455 |
pher | +3.220 |
cream | +2.911 |
displayText | +2.835 |
Neg logit contributions | |
Tik | -2.055 |
viral | -2.028 |
stride | -1.920 |
Kik | -1.896 |
uni | -1.846 |
Token | on |
Token ID | 319 |
Feature activation | +5.78e-03 |
Pos logit contributions | |
nesday | +0.949 |
mble | +0.944 |
pher | +0.864 |
cream | +0.800 |
displayText | +0.773 |
Neg logit contributions | |
Tik | -0.519 |
viral | -0.513 |
stride | -0.499 |
Kik | -0.475 |
characteristic | -0.463 |
Token | authentic |
Token ID | 16425 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
nesday | +0.027 |
mble | +0.027 |
pher | +0.024 |
cream | +0.022 |
displayText | +0.022 |
Neg logit contributions | |
viral | -0.016 |
Tik | -0.016 |
stride | -0.016 |
Kik | -0.015 |
characteristic | -0.015 |
Token | Ob |
Token ID | 1835 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
mble | +0.401 |
nesday | +0.401 |
pher | +0.364 |
cream | +0.336 |
displayText | +0.324 |
Neg logit contributions | |
Tik | -0.238 |
viral | -0.237 |
stride | -0.230 |
Kik | -0.219 |
uni | -0.215 |
Token | amas |
Token ID | 17485 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
viral | +0.268 |
Tik | +0.266 |
stride | +0.258 |
Kik | +0.243 |
uni | +0.240 |
Neg logit contributions | |
nesday | -0.541 |
mble | -0.537 |
pher | -0.486 |
cream | -0.454 |
displayText | -0.443 |
Token | announced |
Token ID | 3414 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
viral | +0.308 |
Tik | +0.307 |
stride | +0.298 |
Kik | +0.284 |
characteristic | +0.280 |
Neg logit contributions | |
nesday | -0.455 |
mble | -0.452 |
pher | -0.407 |
cream | -0.375 |
displayText | -0.362 |
Token | they |
Token ID | 484 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
nesday | +0.881 |
mble | +0.876 |
pher | +0.799 |
cream | +0.739 |
displayText | +0.713 |
Neg logit contributions | |
viral | -0.485 |
Tik | -0.485 |
stride | -0.468 |
Kik | -0.447 |
uni | -0.436 |
Token | were |
Token ID | 547 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
viral | +0.258 |
Tik | +0.257 |
stride | +0.250 |
Kik | +0.239 |
characteristic | +0.235 |
Neg logit contributions | |
nesday | -0.383 |
mble | -0.381 |
pher | -0.344 |
cream | -0.317 |
displayText | -0.306 |
Token | cur |
Token ID | 1090 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
nesday | +2.010 |
mble | +2.005 |
pher | +1.832 |
cream | +1.675 |
displayText | +1.617 |
Neg logit contributions | |
Tik | -1.287 |
viral | -1.281 |
stride | -1.236 |
Kik | -1.188 |
uni | -1.166 |
Token | t |
Token ID | 83 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
nesday | +9.052 |
mble | +8.565 |
pher | +8.165 |
cream | +7.042 |
ationally | +6.527 |
Neg logit contributions | |
viral | -10.812 |
Tik | -10.609 |
stride | -10.587 |
Kik | -10.383 |
characteristic | -10.037 |
Token | ailing |
Token ID | 11608 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
nesday | +3.935 |
mble | +3.903 |
pher | +3.608 |
cream | +3.333 |
displayText | +3.251 |
Neg logit contributions | |
viral | -1.822 |
Tik | -1.819 |
stride | -1.742 |
Kik | -1.654 |
characteristic | -1.607 |
Token | ( |
Token ID | 357 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
nesday | +1.702 |
mble | +1.702 |
pher | +1.541 |
cream | +1.422 |
displayText | +1.357 |
Neg logit contributions | |
Tik | -1.045 |
viral | -1.038 |
stride | -1.010 |
Kik | -0.977 |
uni | -0.955 |
Token | ban |
Token ID | 3820 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
mble | +7.432 |
nesday | +7.393 |
pher | +6.866 |
cream | +6.421 |
displayText | +5.890 |
Neg logit contributions | |
Tik | -6.504 |
viral | -6.346 |
stride | -6.294 |
Kik | -6.042 |
characteristic | -5.905 |
Token | ning |
Token ID | 768 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
nesday | +1.104 |
mble | +1.099 |
pher | +0.963 |
cream | +0.855 |
displayText | +0.805 |
Neg logit contributions | |
viral | -1.304 |
Tik | -1.303 |
stride | -1.274 |
Kik | -1.235 |
characteristic | -1.216 |
Token | Manga |
Token ID | 27024 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
viral | +2.547 |
Tik | +2.541 |
stride | +2.443 |
Kik | +2.348 |
characteristic | +2.298 |
Neg logit contributions | |
nesday | -4.296 |
mble | -4.275 |
pher | -3.874 |
cream | -3.579 |
displayText | -3.490 |
Token | Award |
Token ID | 11289 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
Tik | +2.957 |
viral | +2.953 |
stride | +2.847 |
Kik | +2.748 |
characteristic | +2.699 |
Neg logit contributions | |
nesday | -4.172 |
mble | -4.159 |
pher | -3.730 |
cream | -3.427 |
displayText | -3.326 |
Token | in |
Token ID | 287 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
viral | +2.179 |
Tik | +2.173 |
stride | +2.084 |
Kik | +1.984 |
characteristic | +1.952 |
Neg logit contributions | |
nesday | -4.371 |
mble | -4.347 |
pher | -3.972 |
cream | -3.682 |
displayText | -3.589 |
Token | the |
Token ID | 262 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
viral | +1.338 |
Tik | +1.332 |
stride | +1.289 |
Kik | +1.220 |
characteristic | +1.200 |
Neg logit contributions | |
nesday | -2.378 |
mble | -2.368 |
pher | -2.156 |
cream | -1.996 |
displayText | -1.926 |
Token | Sh |
Token ID | 911 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
viral | +0.642 |
Tik | +0.639 |
stride | +0.619 |
Kik | +0.581 |
characteristic | +0.573 |
Neg logit contributions | |
nesday | -1.189 |
mble | -1.186 |
pher | -1.081 |
cream | -1.003 |
displayText | -0.964 |
Token | ō |
Token ID | 13090 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
viral | +2.236 |
Tik | +2.232 |
stride | +2.154 |
Kik | +2.047 |
characteristic | +2.008 |
Neg logit contributions | |
nesday | -4.116 |
mble | -4.085 |
pher | -3.716 |
cream | -3.449 |
displayText | -3.345 |
Token | jo |
Token ID | 7639 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Tik | +7.309 |
viral | +7.299 |
Kik | +7.006 |
uni | +6.877 |
stride | +6.635 |
Neg logit contributions | |
nesday | -15.347 |
mble | -14.682 |
pher | -13.426 |
displayText | -12.706 |
cream | -12.443 |
Token | category |
Token ID | 6536 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Tik | +5.194 |
viral | +5.121 |
Kik | +4.959 |
stride | +4.898 |
uni | +4.627 |
Neg logit contributions | |
nesday | -8.756 |
mble | -8.706 |
pher | -7.824 |
cream | -7.274 |
displayText | -7.113 |
Token | .[ |
Token ID | 3693 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
viral | +0.708 |
Tik | +0.706 |
stride | +0.679 |
Kik | +0.635 |
characteristic | +0.620 |
Neg logit contributions | |
nesday | -1.575 |
mble | -1.568 |
pher | -1.442 |
cream | -1.346 |
displayText | -1.299 |
Token | 16 |
Token ID | 1433 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
viral | +1.957 |
Tik | +1.944 |
stride | +1.884 |
Kik | +1.777 |
uni | +1.755 |
Neg logit contributions | |
nesday | -3.801 |
mble | -3.762 |
pher | -3.408 |
cream | -3.141 |
displayText | -3.063 |
Token | ] |
Token ID | 60 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
nesday | +0.194 |
mble | +0.193 |
pher | +0.174 |
cream | +0.158 |
displayText | +0.153 |
Neg logit contributions | |
viral | -0.160 |
Tik | -0.160 |
stride | -0.156 |
Kik | -0.149 |
characteristic | -0.147 |
Token | i |
Token ID | 1312 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
viral | +0.606 |
Tik | +0.603 |
stride | +0.586 |
Kik | +0.555 |
characteristic | +0.548 |
Neg logit contributions | |
nesday | -0.964 |
mble | -0.964 |
pher | -0.873 |
cream | -0.806 |
displayText | -0.776 |
Token | |
Token ID | 220 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
viral | +0.304 |
Tik | +0.300 |
stride | +0.287 |
Kik | +0.259 |
characteristic | +0.257 |
Neg logit contributions | |
nesday | -0.987 |
mble | -0.986 |
pher | -0.912 |
cream | -0.857 |
displayText | -0.833 |
Token | � |
Token ID | 134 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
Tik | +1.385 |
viral | +1.355 |
stride | +1.219 |
Kik | +1.135 |
uni | +1.045 |
Neg logit contributions | |
nesday | -7.317 |
mble | -7.247 |
pher | -6.774 |
cream | -6.392 |
displayText | -6.244 |
Token | � |
Token ID | 119 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
viral | +2.786 |
Tik | +2.758 |
stride | +2.661 |
Kik | +2.569 |
characteristic | +2.530 |
Neg logit contributions | |
nesday | -3.712 |
mble | -3.571 |
pher | -3.236 |
cream | -2.971 |
displayText | -2.849 |
Token | emo |
Token ID | 41903 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
viral | +0.575 |
Tik | +0.572 |
stride | +0.557 |
Kik | +0.532 |
characteristic | +0.526 |
Neg logit contributions | |
nesday | -0.754 |
mble | -0.751 |
pher | -0.676 |
cream | -0.619 |
displayText | -0.594 |
Token | ko |
Token ID | 41727 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
viral | +2.932 |
Tik | +2.924 |
stride | +2.802 |
Kik | +2.685 |
uni | +2.606 |
Neg logit contributions | |
nesday | -5.605 |
mble | -5.558 |
pher | -5.064 |
cream | -4.708 |
displayText | -4.576 |
Token | Kal |
Token ID | 12612 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Tik | +7.503 |
viral | +7.461 |
stride | +7.008 |
Kik | +6.980 |
uni | +6.821 |
Neg logit contributions | |
nesday | -13.638 |
mble | -13.381 |
pher | -12.142 |
cream | -11.285 |
displayText | -11.061 |
Token | an |
Token ID | 272 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
Tik | +4.631 |
viral | +4.600 |
stride | +4.415 |
Kik | +4.328 |
uni | +4.312 |
Neg logit contributions | |
nesday | -5.623 |
mble | -5.603 |
pher | -4.966 |
cream | -4.561 |
displayText | -4.473 |
Token | ial |
Token ID | 498 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
viral | +1.240 |
Tik | +1.234 |
stride | +1.206 |
Kik | +1.150 |
characteristic | +1.140 |
Neg logit contributions | |
nesday | -1.554 |
mble | -1.545 |
pher | -1.384 |
cream | -1.265 |
displayText | -1.212 |
Token | i |
Token ID | 72 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
mble | +1.454 |
nesday | +1.453 |
pher | +1.259 |
cream | +1.135 |
displayText | +1.051 |
Neg logit contributions | |
viral | -1.741 |
Tik | -1.718 |
stride | -1.708 |
characteristic | -1.630 |
Kik | -1.617 |
Token | � |
Token ID | 134 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
viral | +0.251 |
Tik | +0.248 |
stride | +0.234 |
Kik | +0.197 |
characteristic | +0.196 |
Neg logit contributions | |
nesday | -1.288 |
mble | -1.287 |
pher | -1.196 |
cream | -1.133 |
displayText | -1.107 |
Token | You |
Token ID | 921 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
nesday | +0.955 |
mble | +0.948 |
pher | +0.864 |
cream | +0.793 |
displayText | +0.765 |
Neg logit contributions | |
viral | -0.641 |
Tik | -0.635 |
stride | -0.620 |
Kik | -0.589 |
characteristic | -0.584 |
Token | know |
Token ID | 760 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
nesday | +2.162 |
mble | +2.160 |
pher | +1.969 |
cream | +1.812 |
displayText | +1.734 |
Neg logit contributions | |
viral | -1.343 |
Tik | -1.341 |
stride | -1.292 |
Kik | -1.248 |
characteristic | -1.224 |
Token | how |
Token ID | 703 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
nesday | +4.154 |
mble | +4.129 |
pher | +3.753 |
cream | +3.417 |
displayText | +3.284 |
Neg logit contributions | |
viral | -3.061 |
Tik | -3.030 |
stride | -2.976 |
Kik | -2.881 |
uni | -2.827 |
Token | Batman |
Token ID | 9827 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
nesday | +3.460 |
mble | +3.437 |
pher | +3.191 |
cream | +2.900 |
displayText | +2.778 |
Neg logit contributions | |
Tik | -1.874 |
viral | -1.865 |
stride | -1.820 |
Kik | -1.755 |
uni | -1.705 |
Token | is |
Token ID | 318 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
viral | +3.096 |
Tik | +3.073 |
stride | +2.979 |
Kik | +2.771 |
characteristic | +2.771 |
Neg logit contributions | |
mble | -5.351 |
nesday | -5.345 |
pher | -4.784 |
cream | -4.414 |
displayText | -4.384 |
Token | Bruce |
Token ID | 11088 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
viral | +1.104 |
Tik | +1.095 |
stride | +1.062 |
Kik | +1.009 |
characteristic | +1.005 |
Neg logit contributions | |
nesday | -1.667 |
mble | -1.653 |
pher | -1.483 |
cream | -1.367 |
displayText | -1.331 |
Token | Wayne |
Token ID | 13329 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
Tik | +6.130 |
viral | +6.028 |
stride | +5.932 |
characteristic | +5.468 |
Kik | +5.345 |
Neg logit contributions | |
mble | -15.319 |
nesday | -14.925 |
pher | -13.458 |
cream | -12.751 |
displayText | -12.545 |
Token | ? |
Token ID | 30 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
viral | +2.864 |
Tik | +2.834 |
stride | +2.767 |
characteristic | +2.608 |
Kik | +2.604 |
Neg logit contributions | |
nesday | -4.316 |
mble | -4.293 |
pher | -3.853 |
cream | -3.545 |
displayText | -3.479 |
Token | And |
Token ID | 843 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
Tik | +1.896 |
viral | +1.873 |
stride | +1.805 |
Kik | +1.751 |
characteristic | +1.695 |
Neg logit contributions | |
nesday | -2.776 |
mble | -2.764 |
pher | -2.453 |
cream | -2.264 |
displayText | -2.202 |
Token | that |
Token ID | 326 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
nesday | +0.382 |
mble | +0.380 |
pher | +0.346 |
cream | +0.320 |
displayText | +0.309 |
Neg logit contributions | |
viral | -0.216 |
Tik | -0.215 |
stride | -0.208 |
Kik | -0.198 |
characteristic | -0.194 |
Token | he |
Token ID | 339 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
viral | +0.983 |
Tik | +0.977 |
stride | +0.944 |
Kik | +0.890 |
characteristic | +0.880 |
Neg logit contributions | |
nesday | -1.872 |
mble | -1.863 |
pher | -1.694 |
cream | -1.577 |
displayText | -1.530 |
Token | he |
Token ID | 339 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
viral | +0.574 |
Tik | +0.567 |
stride | +0.556 |
uni | +0.515 |
Kik | +0.514 |
Neg logit contributions | |
nesday | -1.213 |
mble | -1.208 |
pher | -1.112 |
cream | -1.033 |
displayText | -0.997 |
Token | summed |
Token ID | 32794 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
viral | +0.538 |
Tik | +0.536 |
stride | +0.520 |
Kik | +0.496 |
characteristic | +0.489 |
Neg logit contributions | |
nesday | -0.815 |
mble | -0.810 |
pher | -0.732 |
cream | -0.675 |
displayText | -0.652 |
Token | up |
Token ID | 510 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
viral | +0.659 |
Tik | +0.657 |
stride | +0.638 |
Kik | +0.607 |
characteristic | +0.598 |
Neg logit contributions | |
nesday | -1.040 |
mble | -1.036 |
pher | -0.938 |
cream | -0.866 |
displayText | -0.834 |
Token | Z |
Token ID | 1168 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
mble | +1.311 |
nesday | +1.305 |
pher | +1.189 |
cream | +1.098 |
displayText | +1.052 |
Neg logit contributions | |
viral | -0.783 |
Tik | -0.779 |
stride | -0.759 |
uni | -0.722 |
Kik | -0.717 |
Token | t |
Token ID | 83 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
viral | +1.052 |
Tik | +1.047 |
stride | +1.017 |
Kik | +0.976 |
characteristic | +0.961 |
Neg logit contributions | |
nesday | -1.412 |
mble | -1.410 |
pher | -1.273 |
cream | -1.163 |
displayText | -1.112 |
Token | oh |
Token ID | 1219 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
viral | +3.195 |
Tik | +3.187 |
stride | +3.090 |
Kik | +2.958 |
characteristic | +2.913 |
Neg logit contributions | |
nesday | -4.453 |
mble | -4.417 |
pher | -3.982 |
cream | -3.661 |
displayText | -3.537 |
Token | oven |
Token ID | 16206 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Tik | +9.544 |
viral | +9.402 |
stride | +9.024 |
Kik | +8.668 |
uni | +8.648 |
Neg logit contributions | |
nesday | -11.532 |
mble | -11.391 |
pher | -9.836 |
cream | -9.183 |
displayText | -9.109 |
Token | � |
Token ID | 447 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
viral | +0.777 |
Tik | +0.772 |
stride | +0.743 |
Kik | +0.697 |
characteristic | +0.685 |
Neg logit contributions | |
nesday | -1.700 |
mble | -1.692 |
pher | -1.548 |
cream | -1.442 |
displayText | -1.403 |
Token | � |
Token ID | 247 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
nesday | +0.269 |
mble | +0.269 |
pher | +0.243 |
cream | +0.223 |
displayText | +0.216 |
Neg logit contributions | |
Tik | -0.181 |
viral | -0.180 |
stride | -0.173 |
Kik | -0.167 |
characteristic | -0.164 |
Token | s |
Token ID | 82 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
nesday | +0.207 |
mble | +0.206 |
pher | +0.188 |
cream | +0.175 |
displayText | +0.168 |
Neg logit contributions | |
viral | -0.110 |
Tik | -0.110 |
stride | -0.106 |
Kik | -0.101 |
characteristic | -0.098 |
Token | larger |
Token ID | 4025 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
viral | +2.407 |
Tik | +2.382 |
stride | +2.318 |
Kik | +2.174 |
characteristic | +2.161 |
Neg logit contributions | |
nesday | -4.718 |
mble | -4.686 |
pher | -4.271 |
cream | -3.970 |
displayText | -3.881 |
Token | � |
Token ID | 120 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
viral | +6.454 |
Tik | +6.279 |
stride | +6.032 |
characteristic | +5.706 |
Kik | +5.590 |
Neg logit contributions | |
nesday | -12.007 |
mble | -11.286 |
pher | -10.288 |
displayText | -9.477 |
cream | -9.431 |
Token | � |
Token ID | 223 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
viral | +3.525 |
Tik | +3.493 |
stride | +3.366 |
Kik | +3.267 |
characteristic | +3.233 |
Neg logit contributions | |
nesday | -3.911 |
mble | -3.886 |
pher | -3.429 |
cream | -3.136 |
displayText | -3.026 |
Token | ρ |
Token ID | 33643 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
viral | +5.153 |
Tik | +5.131 |
stride | +4.869 |
Kik | +4.748 |
characteristic | +4.661 |
Neg logit contributions | |
mble | -7.533 |
nesday | -7.447 |
pher | -6.569 |
cream | -6.112 |
displayText | -6.031 |
Token | π |
Token ID | 46582 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Tik | +4.761 |
viral | +4.757 |
stride | +4.470 |
Kik | +4.388 |
characteristic | +4.268 |
Neg logit contributions | |
mble | -8.221 |
nesday | -8.162 |
pher | -7.227 |
cream | -6.783 |
displayText | -6.605 |
Token | α |
Token ID | 17394 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
viral | +4.612 |
Tik | +4.599 |
stride | +4.264 |
Kik | +4.233 |
characteristic | +4.118 |
Neg logit contributions | |
nesday | -8.334 |
mble | -8.288 |
pher | -7.361 |
cream | -6.864 |
displayText | -6.694 |
Token | γ |
Token ID | 42063 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
viral | +5.338 |
Tik | +5.261 |
stride | +5.045 |
Kik | +4.925 |
characteristic | +4.833 |
Neg logit contributions | |
mble | -7.552 |
nesday | -7.520 |
pher | -6.623 |
cream | -6.126 |
displayText | -5.983 |
Token | � |
Token ID | 157 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
viral | +7.529 |
Tik | +7.420 |
stride | +6.970 |
Kik | +6.881 |
Gujar | +6.786 |
Neg logit contributions | |
nesday | -13.437 |
mble | -13.331 |
pher | -11.556 |
cream | -10.965 |
displayText | -10.808 |
Token | � |
Token ID | 123 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
viral | +7.246 |
Tik | +7.076 |
stride | +6.682 |
Gujar | +6.446 |
uni | +6.400 |
Neg logit contributions | |
nesday | -10.997 |
mble | -10.392 |
pher | -9.384 |
displayText | -8.757 |
cream | -8.598 |
Token | � |
Token ID | 228 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
viral | +2.540 |
Tik | +2.518 |
stride | +2.446 |
Kik | +2.363 |
characteristic | +2.326 |
Neg logit contributions | |
nesday | -3.059 |
mble | -3.026 |
pher | -2.700 |
cream | -2.474 |
displayText | -2.389 |
Token | ς |
Token ID | 35558 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
viral | +4.305 |
Tik | +4.295 |
stride | +4.125 |
Kik | +4.030 |
characteristic | +3.976 |
Neg logit contributions | |
mble | -4.511 |
nesday | -4.504 |
pher | -3.906 |
cream | -3.584 |
displayText | -3.469 |
Token | ( |
Token ID | 357 |
Feature activation | -4.75e-03 |
Pos logit contributions | |
viral | +5.076 |
Tik | +5.028 |
stride | +4.661 |
Kik | +4.585 |
characteristic | +4.500 |
Neg logit contributions | |
mble | -10.544 |
nesday | -10.495 |
pher | -9.395 |
cream | -8.812 |
displayText | -8.610 |
Token | me |
Token ID | 502 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
viral | +0.243 |
Tik | +0.241 |
stride | +0.235 |
Kik | +0.219 |
characteristic | +0.217 |
Neg logit contributions | |
nesday | -0.475 |
mble | -0.474 |
pher | -0.434 |
cream | -0.402 |
displayText | -0.388 |
Token | ke |
Token ID | 885 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
mble | +1.723 |
nesday | +1.702 |
pher | +1.513 |
cream | +1.338 |
displayText | +1.245 |
Neg logit contributions | |
viral | -2.010 |
Tik | -1.997 |
stride | -1.967 |
Kik | -1.879 |
characteristic | -1.878 |
Token | k |
Token ID | 479 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
mble | +1.891 |
nesday | +1.889 |
pher | +1.743 |
cream | +1.614 |
displayText | +1.549 |
Neg logit contributions | |
viral | -0.834 |
Tik | -0.821 |
stride | -0.811 |
characteristic | -0.739 |
Kik | -0.735 |
Token | ah |
Token ID | 993 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Tik | +3.752 |
viral | +3.719 |
stride | +3.567 |
Kik | +3.473 |
uni | +3.471 |
Neg logit contributions | |
nesday | -5.977 |
mble | -5.925 |
pher | -5.347 |
cream | -4.946 |
displayText | -4.834 |
Token | uk |
Token ID | 2724 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Tik | +5.181 |
viral | +5.118 |
stride | +4.905 |
Kik | +4.781 |
uni | +4.776 |
Neg logit contributions | |
nesday | -7.450 |
mble | -7.331 |
pher | -6.585 |
cream | -6.085 |
displayText | -5.973 |
Token | ahu |
Token ID | 12196 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
Tik | +3.715 |
viral | +3.702 |
stride | +3.557 |
Kik | +3.446 |
uni | +3.445 |
Neg logit contributions | |
nesday | -5.335 |
mble | -5.285 |
pher | -4.758 |
cream | -4.390 |
displayText | -4.280 |
Token | i |
Token ID | 1312 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Tik | +8.103 |
viral | +7.958 |
Kik | +7.591 |
Hawai | +7.457 |
stride | +7.443 |
Neg logit contributions | |
nesday | -12.945 |
mble | -12.762 |
pher | -11.472 |
cream | -10.721 |
displayText | -10.574 |
Token | ka |
Token ID | 38387 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
viral | +0.907 |
Tik | +0.901 |
stride | +0.863 |
Kik | +0.798 |
characteristic | +0.784 |
Neg logit contributions | |
nesday | -2.492 |
mble | -2.483 |
pher | -2.289 |
cream | -2.143 |
displayText | -2.082 |
Token | pil |
Token ID | 5560 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Tik | +3.773 |
viral | +3.755 |
stride | +3.551 |
Kik | +3.438 |
uni | +3.305 |
Neg logit contributions | |
nesday | -7.953 |
mble | -7.898 |
pher | -7.196 |
cream | -6.724 |
displayText | -6.572 |
Token | ina |
Token ID | 1437 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
mble | +0.542 |
nesday | +0.541 |
pher | +0.494 |
cream | +0.454 |
displayText | +0.435 |
Neg logit contributions | |
viral | -0.327 |
Tik | -0.323 |
stride | -0.317 |
Kik | -0.298 |
characteristic | -0.295 |
Token | |
Token ID | 220 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
viral | +1.131 |
Tik | +1.124 |
stride | +1.088 |
Kik | +1.025 |
characteristic | +1.010 |
Neg logit contributions | |
nesday | -2.182 |
mble | -2.173 |
pher | -1.984 |
cream | -1.841 |
displayText | -1.782 |
Token |
|
Token ID | 198 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
viral | +0.779 |
Tik | +0.774 |
stride | +0.734 |
Kik | +0.687 |
characteristic | +0.661 |
Neg logit contributions | |
nesday | -2.237 |
mble | -2.236 |
pher | -1.983 |
cream | -1.868 |
displayText | -1.826 |
Token | Split |
Token ID | 41205 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
nesday | +0.828 |
mble | +0.826 |
pher | +0.744 |
cream | +0.684 |
displayText | +0.657 |
Neg logit contributions | |
viral | -0.637 |
Tik | -0.636 |
stride | -0.619 |
Kik | -0.590 |
characteristic | -0.583 |
Token | release |
Token ID | 2650 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
nesday | +6.625 |
mble | +6.576 |
pher | +5.990 |
cream | +5.540 |
displayText | +5.309 |
Neg logit contributions | |
viral | -3.705 |
Tik | -3.693 |
stride | -3.597 |
uni | -3.407 |
Kik | -3.376 |
Token | with |
Token ID | 351 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
nesday | +0.732 |
mble | +0.731 |
pher | +0.664 |
cream | +0.618 |
displayText | +0.597 |
Neg logit contributions | |
Tik | -0.384 |
viral | -0.383 |
stride | -0.372 |
Kik | -0.349 |
uni | -0.345 |
Token | Yam |
Token ID | 14063 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
nesday | +0.912 |
mble | +0.908 |
pher | +0.826 |
cream | +0.767 |
displayText | +0.739 |
Neg logit contributions | |
viral | -0.504 |
Tik | -0.502 |
stride | -0.489 |
Kik | -0.460 |
uni | -0.456 |
Token | Yam |
Token ID | 14063 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Tik | +6.236 |
viral | +6.205 |
stride | +5.898 |
Kik | +5.777 |
uni | +5.764 |
Neg logit contributions | |
nesday | -8.990 |
mble | -8.883 |
pher | -7.904 |
cream | -7.356 |
displayText | -7.239 |
Token | Records |
Token ID | 13407 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Tik | +8.694 |
viral | +8.472 |
Kik | +8.146 |
stride | +8.016 |
Yam | +7.815 |
Neg logit contributions | |
nesday | -11.938 |
mble | -11.736 |
pher | -10.480 |
cream | -9.594 |
displayText | -9.561 |
Token |
|
Token ID | 198 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
viral | +0.365 |
Tik | +0.363 |
stride | +0.352 |
Kik | +0.330 |
characteristic | +0.325 |
Neg logit contributions | |
nesday | -0.702 |
mble | -0.700 |
pher | -0.637 |
cream | -0.594 |
displayText | -0.572 |
Token |
|
Token ID | 198 |
Feature activation | +4.50e-03 |
Pos logit contributions | |
viral | +0.968 |
Tik | +0.963 |
stride | +0.909 |
Kik | +0.852 |
doi | +0.822 |
Neg logit contributions | |
nesday | -2.825 |
mble | -2.822 |
pher | -2.498 |
cream | -2.356 |
displayText | -2.301 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
nesday | +0.018 |
mble | +0.018 |
pher | +0.016 |
cream | +0.015 |
displayText | +0.014 |
Neg logit contributions | |
viral | -0.016 |
Tik | -0.016 |
stride | -0.015 |
Kik | -0.015 |
characteristic | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
mble | +0.664 |
nesday | +0.663 |
pher | +0.602 |
cream | +0.557 |
displayText | +0.539 |
Neg logit contributions | |
viral | -0.387 |
Tik | -0.385 |
stride | -0.375 |
Kik | -0.354 |
characteristic | -0.349 |
Token | costs |
Token ID | 3484 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
mble | +2.499 |
nesday | +2.498 |
pher | +2.289 |
cream | +2.114 |
displayText | +2.017 |
Neg logit contributions | |
Tik | -1.604 |
viral | -1.571 |
stride | -1.548 |
Kik | -1.488 |
uni | -1.458 |
Token | is |
Token ID | 318 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
nesday | +1.935 |
mble | +1.926 |
pher | +1.770 |
cream | +1.633 |
displayText | +1.573 |
Neg logit contributions | |
Tik | -1.092 |
viral | -1.091 |
stride | -1.051 |
Kik | -1.008 |
uni | -0.981 |
Token | built |
Token ID | 3170 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
nesday | +1.851 |
mble | +1.841 |
pher | +1.682 |
cream | +1.556 |
displayText | +1.493 |
Neg logit contributions | |
Tik | -1.105 |
viral | -1.104 |
stride | -1.073 |
Kik | -1.019 |
uni | -1.000 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
nesday | +2.102 |
mble | +2.097 |
pher | +1.918 |
cream | +1.770 |
displayText | +1.712 |
Neg logit contributions | |
Tik | -1.171 |
viral | -1.154 |
stride | -1.121 |
Kik | -1.079 |
uni | -1.037 |
Token | a |
Token ID | 257 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
viral | +0.348 |
Tik | +0.347 |
stride | +0.336 |
Kik | +0.319 |
characteristic | +0.313 |
Neg logit contributions | |
nesday | -0.585 |
mble | -0.583 |
pher | -0.530 |
cream | -0.490 |
displayText | -0.473 |
Token | widely |
Token ID | 6768 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
viral | +1.097 |
Tik | +1.091 |
stride | +1.050 |
Kik | +0.992 |
characteristic | +0.975 |
Neg logit contributions | |
nesday | -2.242 |
mble | -2.230 |
pher | -2.039 |
cream | -1.897 |
displayText | -1.841 |
Token | used |
Token ID | 973 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
viral | +6.708 |
Tik | +6.030 |
characteristic | +6.016 |
stride | +5.806 |
search | +5.706 |
Neg logit contributions | |
nesday | -14.479 |
mble | -14.470 |
pher | -12.376 |
cream | -12.083 |
displayText | -12.078 |
Token | methodology |
Token ID | 20411 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
viral | +1.572 |
Tik | +1.555 |
stride | +1.502 |
Kik | +1.419 |
characteristic | +1.406 |
Neg logit contributions | |
nesday | -3.077 |
mble | -3.050 |
pher | -2.786 |
cream | -2.588 |
displayText | -2.511 |
Token | introduced |
Token ID | 5495 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
viral | +0.501 |
Tik | +0.499 |
stride | +0.482 |
Kik | +0.458 |
characteristic | +0.452 |
Neg logit contributions | |
nesday | -0.869 |
mble | -0.864 |
pher | -0.785 |
cream | -0.726 |
displayText | -0.703 |
Token | in |
Token ID | 287 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
nesday | +1.325 |
mble | +1.316 |
pher | +1.198 |
cream | +1.104 |
displayText | +1.066 |
Neg logit contributions | |
viral | -0.800 |
Tik | -0.799 |
stride | -0.775 |
Kik | -0.738 |
characteristic | -0.723 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
viral | +0.806 |
Tik | +0.803 |
stride | +0.774 |
Kik | +0.734 |
characteristic | +0.720 |
Neg logit contributions | |
nesday | -1.524 |
mble | -1.517 |
pher | -1.384 |
cream | -1.284 |
displayText | -1.243 |
Token | not |
Token ID | 407 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
viral | +1.753 |
Tik | +1.736 |
stride | +1.675 |
Kik | +1.584 |
characteristic | +1.561 |
Neg logit contributions | |
nesday | -3.416 |
mble | -3.398 |
pher | -3.091 |
cream | -2.874 |
displayText | -2.794 |
Token | signing |
Token ID | 8415 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
viral | +0.083 |
Tik | +0.083 |
stride | +0.080 |
Kik | +0.076 |
characteristic | +0.075 |
Neg logit contributions | |
nesday | -0.136 |
mble | -0.136 |
pher | -0.123 |
cream | -0.114 |
displayText | -0.110 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
viral | +1.099 |
Tik | +1.095 |
stride | +1.060 |
Kik | +1.008 |
characteristic | +0.992 |
Neg logit contributions | |
nesday | -1.857 |
mble | -1.847 |
pher | -1.678 |
cream | -1.551 |
displayText | -1.500 |
Token | mailed |
Token ID | 37789 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
Tik | +0.033 |
viral | +0.033 |
stride | +0.032 |
Kik | +0.031 |
characteristic | +0.030 |
Neg logit contributions | |
nesday | -0.057 |
mble | -0.056 |
pher | -0.051 |
cream | -0.047 |
displayText | -0.046 |
Token | out |
Token ID | 503 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
nesday | +0.305 |
mble | +0.304 |
pher | +0.278 |
cream | +0.257 |
displayText | +0.247 |
Neg logit contributions | |
Tik | -0.172 |
viral | -0.171 |
stride | -0.167 |
Kik | -0.158 |
uni | -0.156 |
Token | ballot |
Token ID | 11100 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
mble | +1.586 |
nesday | +1.586 |
pher | +1.454 |
cream | +1.346 |
displayText | +1.294 |
Neg logit contributions | |
Tik | -0.856 |
viral | -0.850 |
stride | -0.833 |
Kik | -0.784 |
uni | -0.777 |
Token | questionnaire |
Token ID | 28301 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
viral | +7.004 |
Tik | +6.755 |
stride | +6.476 |
characteristic | +6.245 |
Kik | +6.200 |
Neg logit contributions | |
mble | -13.530 |
nesday | -13.339 |
pher | -12.017 |
cream | -11.080 |
displayText | -11.070 |
Token | at |
Token ID | 379 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
viral | +1.773 |
Tik | +1.757 |
stride | +1.697 |
Kik | +1.610 |
characteristic | +1.590 |
Neg logit contributions | |
nesday | -3.173 |
mble | -3.162 |
pher | -2.871 |
cream | -2.665 |
displayText | -2.587 |
Token | the |
Token ID | 262 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
nesday | +0.351 |
mble | +0.349 |
pher | +0.316 |
cream | +0.291 |
displayText | +0.280 |
Neg logit contributions | |
viral | -0.219 |
Tik | -0.219 |
stride | -0.211 |
Kik | -0.202 |
uni | -0.198 |
Token | bottom |
Token ID | 4220 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
viral | +0.473 |
Tik | +0.472 |
stride | +0.456 |
Kik | +0.434 |
characteristic | +0.425 |
Neg logit contributions | |
nesday | -0.824 |
mble | -0.820 |
pher | -0.745 |
cream | -0.688 |
displayText | -0.668 |
Token | in |
Token ID | 287 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
nesday | +0.050 |
mble | +0.050 |
pher | +0.046 |
cream | +0.042 |
displayText | +0.041 |
Neg logit contributions | |
Tik | -0.028 |
viral | -0.027 |
stride | -0.027 |
Kik | -0.025 |
uni | -0.025 |
Token | Score |
Token ID | 26595 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
nesday | +0.043 |
mble | +0.043 |
pher | +0.039 |
cream | +0.036 |
displayText | +0.035 |
Neg logit contributions | |
viral | -0.022 |
Tik | -0.022 |
stride | -0.021 |
Kik | -0.020 |
characteristic | -0.020 |
Token | esports |
Token ID | 37407 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
viral | +1.400 |
Tik | +1.382 |
stride | +1.312 |
Kik | +1.254 |
characteristic | +1.222 |
Neg logit contributions | |
nesday | -3.347 |
mble | -3.317 |
pher | -3.046 |
cream | -2.840 |
displayText | -2.771 |
Token | . |
Token ID | 13 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
viral | +1.748 |
Tik | +1.738 |
stride | +1.669 |
Kik | +1.577 |
characteristic | +1.544 |
Neg logit contributions | |
nesday | -3.867 |
mble | -3.848 |
pher | -3.533 |
cream | -3.288 |
displayText | -3.203 |
Token | You |
Token ID | 921 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
Tik | +1.928 |
viral | +1.912 |
stride | +1.823 |
Kik | +1.772 |
characteristic | +1.706 |
Neg logit contributions | |
nesday | -3.810 |
mble | -3.780 |
pher | -3.430 |
cream | -3.204 |
displayText | -3.114 |
Token | can |
Token ID | 460 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
viral | +1.451 |
Tik | +1.441 |
stride | +1.379 |
Kik | +1.296 |
characteristic | +1.267 |
Neg logit contributions | |
nesday | -3.606 |
mble | -3.589 |
pher | -3.297 |
cream | -3.081 |
displayText | -3.002 |
Token | follow |
Token ID | 1061 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
viral | +3.083 |
Tik | +2.932 |
stride | +2.894 |
characteristic | +2.644 |
Kik | +2.637 |
Neg logit contributions | |
mble | -9.194 |
nesday | -9.158 |
pher | -8.468 |
cream | -7.932 |
displayText | -7.787 |
Token | him |
Token ID | 683 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Tik | +9.883 |
viral | +9.806 |
stride | +9.423 |
Kik | +9.108 |
characteristic | +9.102 |
Neg logit contributions | |
mble | -9.982 |
nesday | -9.957 |
pher | -8.956 |
cream | -8.144 |
displayText | -7.608 |
Token | on |
Token ID | 319 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
viral | +3.293 |
Tik | +3.242 |
stride | +3.107 |
Kik | +2.911 |
characteristic | +2.892 |
Neg logit contributions | |
mble | -7.876 |
nesday | -7.866 |
pher | -7.136 |
cream | -6.689 |
displayText | -6.523 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
viral | +4.571 |
Tik | +4.416 |
stride | +4.232 |
Kik | +4.230 |
". | +3.822 |
Neg logit contributions | |
mble | -12.809 |
nesday | -12.710 |
pher | -11.703 |
cream | -11.139 |
displayText | -10.826 |
Token | . |
Token ID | 13 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
viral | +3.920 |
Tik | +3.895 |
stride | +3.625 |
Kik | +3.620 |
characteristic | +3.409 |
Neg logit contributions | |
mble | -9.837 |
nesday | -9.836 |
pher | -9.060 |
cream | -8.414 |
displayText | -8.157 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
viral | +1.730 |
Tik | +1.729 |
stride | +1.640 |
Kik | +1.562 |
characteristic | +1.519 |
Neg logit contributions | |
nesday | -4.006 |
mble | -3.979 |
pher | -3.644 |
cream | -3.402 |
displayText | -3.300 |
Token | � |
Token ID | 25001 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
viral | +7.354 |
Tik | +7.192 |
stride | +6.949 |
Kik | +6.887 |
characteristic | +6.802 |
Neg logit contributions | |
nesday | -11.876 |
mble | -11.636 |
pher | -10.536 |
cream | -9.606 |
displayText | -9.562 |
Token | � |
Token ID | 245 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
viral | +5.139 |
Tik | +5.064 |
stride | +4.884 |
Kik | +4.736 |
characteristic | +4.701 |
Neg logit contributions | |
nesday | -7.769 |
mble | -7.669 |
pher | -6.939 |
cream | -6.412 |
displayText | -6.271 |
Token | � |
Token ID | 165 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
viral | +5.036 |
Tik | +4.945 |
stride | +4.811 |
Kik | +4.694 |
characteristic | +4.612 |
Neg logit contributions | |
nesday | -7.916 |
mble | -7.860 |
pher | -7.095 |
cream | -6.510 |
displayText | -6.322 |
Token | � |
Token ID | 246 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
viral | +4.592 |
Tik | +4.556 |
stride | +4.425 |
Kik | +4.264 |
characteristic | +4.223 |
Neg logit contributions | |
nesday | -5.404 |
mble | -5.279 |
pher | -4.770 |
cream | -4.350 |
displayText | -4.226 |
Token | � |
Token ID | 253 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
viral | +2.025 |
Tik | +2.017 |
stride | +1.959 |
Kik | +1.886 |
characteristic | +1.857 |
Neg logit contributions | |
nesday | -2.541 |
mble | -2.517 |
pher | -2.257 |
cream | -2.061 |
displayText | -1.992 |
Token | � |
Token ID | 17312 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
viral | +5.050 |
Tik | +4.942 |
stride | +4.826 |
Kik | +4.699 |
characteristic | +4.601 |
Neg logit contributions | |
nesday | -8.127 |
mble | -8.122 |
pher | -7.336 |
cream | -6.669 |
displayText | -6.576 |
Token | � |
Token ID | 235 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Tik | +8.685 |
viral | +8.583 |
stride | +8.527 |
Kik | +8.084 |
characteristic | +8.026 |
Neg logit contributions | |
nesday | -11.050 |
mble | -10.959 |
pher | -9.791 |
cream | -8.842 |
displayText | -8.611 |
Token | , |
Token ID | 11 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
viral | +5.455 |
Tik | +5.348 |
stride | +5.229 |
Kik | +5.110 |
characteristic | +4.991 |
Neg logit contributions | |
nesday | -8.706 |
mble | -8.618 |
pher | -7.790 |
cream | -7.114 |
displayText | -6.946 |
Token | which |
Token ID | 543 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
viral | +2.327 |
Tik | +2.306 |
stride | +2.223 |
Kik | +2.134 |
characteristic | +2.096 |
Neg logit contributions | |
nesday | -4.317 |
mble | -4.302 |
pher | -3.906 |
cream | -3.624 |
displayText | -3.540 |
Token | means |
Token ID | 1724 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
nesday | +0.630 |
mble | +0.626 |
pher | +0.569 |
cream | +0.523 |
displayText | +0.502 |
Neg logit contributions | |
Tik | -0.400 |
viral | -0.399 |
stride | -0.388 |
Kik | -0.367 |
characteristic | -0.362 |
Token | � |
Token ID | 564 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
viral | +2.461 |
Tik | +2.425 |
stride | +2.350 |
Kik | +2.227 |
characteristic | +2.188 |
Neg logit contributions | |
nesday | -5.104 |
mble | -5.063 |
pher | -4.647 |
cream | -4.305 |
displayText | -4.230 |
Token | due |
Token ID | 2233 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
viral | +0.299 |
Tik | +0.297 |
stride | +0.286 |
Kik | +0.270 |
characteristic | +0.266 |
Neg logit contributions | |
nesday | -0.610 |
mble | -0.608 |
pher | -0.554 |
cream | -0.516 |
displayText | -0.501 |
Token | to |
Token ID | 284 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
nesday | +2.988 |
mble | +2.968 |
pher | +2.677 |
cream | +2.445 |
displayText | +2.354 |
Neg logit contributions | |
Tik | -2.303 |
viral | -2.302 |
stride | -2.237 |
Kik | -2.145 |
characteristic | -2.113 |
Token | the |
Token ID | 262 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
mble | +1.382 |
nesday | +1.382 |
pher | +1.252 |
cream | +1.158 |
displayText | +1.109 |
Neg logit contributions | |
Tik | -0.845 |
viral | -0.833 |
stride | -0.821 |
Kik | -0.775 |
uni | -0.774 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
nesday | +0.125 |
mble | +0.125 |
pher | +0.114 |
cream | +0.106 |
displayText | +0.102 |
Neg logit contributions | |
Tik | -0.067 |
viral | -0.067 |
stride | -0.065 |
Kik | -0.061 |
uni | -0.061 |
Token | T |
Token ID | 309 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
viral | +2.796 |
Tik | +2.758 |
stride | +2.650 |
Kik | +2.547 |
characteristic | +2.492 |
Neg logit contributions | |
nesday | -4.857 |
mble | -4.802 |
pher | -4.373 |
cream | -4.061 |
displayText | -3.934 |
Token | oh |
Token ID | 1219 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
viral | +1.670 |
Tik | +1.666 |
stride | +1.614 |
Kik | +1.541 |
characteristic | +1.520 |
Neg logit contributions | |
nesday | -2.447 |
mble | -2.436 |
pher | -2.199 |
cream | -2.023 |
displayText | -1.952 |
Token | oku |
Token ID | 11601 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Tik | +4.107 |
viral | +3.711 |
Kik | +3.372 |
stride | +3.355 |
uni | +3.183 |
Neg logit contributions | |
nesday | -16.170 |
mble | -15.946 |
pher | -14.382 |
displayText | -13.809 |
cream | -13.609 |
Token | Earthquake |
Token ID | 45591 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
viral | +5.654 |
Tik | +5.645 |
Kik | +5.426 |
stride | +5.280 |
squid | +5.074 |
Neg logit contributions | |
mble | -9.256 |
nesday | -9.099 |
pher | -8.272 |
cream | -7.699 |
displayText | -7.544 |
Token | , |
Token ID | 11 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
nesday | +2.109 |
mble | +2.090 |
pher | +1.920 |
cream | +1.778 |
displayText | +1.708 |
Neg logit contributions | |
Tik | -1.200 |
viral | -1.191 |
stride | -1.166 |
uni | -1.101 |
Kik | -1.090 |
Token | and |
Token ID | 290 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
viral | +0.951 |
Tik | +0.947 |
stride | +0.910 |
Kik | +0.855 |
characteristic | +0.838 |
Neg logit contributions | |
nesday | -2.152 |
mble | -2.141 |
pher | -1.964 |
cream | -1.831 |
displayText | -1.778 |
Token | went |
Token ID | 1816 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
viral | +1.199 |
Tik | +1.194 |
stride | +1.153 |
Kik | +1.099 |
characteristic | +1.080 |
Neg logit contributions | |
nesday | -2.033 |
mble | -2.023 |
pher | -1.837 |
cream | -1.700 |
displayText | -1.644 |
Token | last |
Token ID | 938 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
viral | +1.385 |
Tik | +1.377 |
stride | +1.330 |
Kik | +1.267 |
characteristic | +1.249 |
Neg logit contributions | |
nesday | -2.271 |
mble | -2.260 |
pher | -2.042 |
cream | -1.892 |
displayText | -1.826 |
Token | year |
Token ID | 614 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
viral | +1.390 |
Tik | +1.383 |
stride | +1.328 |
Kik | +1.245 |
characteristic | +1.222 |
Neg logit contributions | |
nesday | -3.181 |
mble | -3.168 |
pher | -2.904 |
cream | -2.709 |
displayText | -2.629 |
Token | � |
Token ID | 447 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
viral | +1.937 |
Tik | +1.911 |
stride | +1.821 |
Kik | +1.695 |
characteristic | +1.661 |
Neg logit contributions | |
mble | -4.896 |
nesday | -4.889 |
pher | -4.449 |
cream | -4.200 |
displayText | -4.056 |
Token | � |
Token ID | 247 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
nesday | +1.186 |
mble | +1.174 |
pher | +1.067 |
cream | +0.989 |
displayText | +0.956 |
Neg logit contributions | |
viral | -0.646 |
Tik | -0.636 |
stride | -0.620 |
Kik | -0.584 |
characteristic | -0.575 |
Token | s |
Token ID | 82 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
nesday | +2.312 |
mble | +2.284 |
pher | +2.102 |
cream | +1.927 |
displayText | +1.865 |
Neg logit contributions | |
Tik | -1.452 |
viral | -1.450 |
stride | -1.412 |
Kik | -1.351 |
characteristic | -1.322 |
Token | ballot |
Token ID | 11100 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
viral | +1.374 |
Tik | +1.368 |
stride | +1.322 |
Kik | +1.255 |
characteristic | +1.236 |
Neg logit contributions | |
nesday | -2.369 |
mble | -2.357 |
pher | -2.140 |
cream | -1.982 |
displayText | -1.916 |
Token | initiative |
Token ID | 10219 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
viral | +7.340 |
stride | +7.099 |
Tik | +7.062 |
characteristic | +6.634 |
Kik | +6.595 |
Neg logit contributions | |
mble | -12.846 |
nesday | -12.651 |
pher | -11.252 |
cream | -10.561 |
displayText | -9.953 |
Token | that |
Token ID | 326 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
viral | +2.899 |
Tik | +2.868 |
stride | +2.758 |
Kik | +2.655 |
characteristic | +2.615 |
Neg logit contributions | |
mble | -4.564 |
nesday | -4.551 |
pher | -4.043 |
cream | -3.794 |
displayText | -3.633 |
Token | would |
Token ID | 561 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
viral | +0.471 |
Tik | +0.469 |
stride | +0.455 |
Kik | +0.434 |
characteristic | +0.428 |
Neg logit contributions | |
nesday | -0.705 |
mble | -0.701 |
pher | -0.632 |
cream | -0.583 |
displayText | -0.562 |
Token | have |
Token ID | 423 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
mble | +0.706 |
nesday | +0.706 |
pher | +0.642 |
cream | +0.584 |
displayText | +0.567 |
Neg logit contributions | |
Tik | -0.486 |
viral | -0.485 |
stride | -0.467 |
Kik | -0.451 |
characteristic | -0.442 |
Token | made |
Token ID | 925 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
mble | +3.329 |
nesday | +3.318 |
pher | +3.070 |
cream | +2.714 |
displayText | +2.656 |
Neg logit contributions | |
Tik | -2.603 |
viral | -2.602 |
stride | -2.543 |
Kik | -2.429 |
uni | -2.404 |
Token | biological |
Token ID | 10685 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
mble | +1.890 |
nesday | +1.880 |
pher | +1.743 |
cream | +1.612 |
displayText | +1.543 |
Neg logit contributions | |
Tik | -0.884 |
viral | -0.869 |
stride | -0.860 |
Kik | -0.806 |
uni | -0.802 |
Token | or |
Token ID | 393 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
viral | +1.697 |
Tik | +1.689 |
stride | +1.639 |
Kik | +1.565 |
characteristic | +1.544 |
Neg logit contributions | |
nesday | -2.506 |
mble | -2.491 |
pher | -2.247 |
cream | -2.070 |
displayText | -2.001 |
Token | chemical |
Token ID | 5931 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Tik | +0.200 |
viral | +0.196 |
stride | +0.192 |
Kik | +0.180 |
uni | +0.173 |
Neg logit contributions | |
mble | -0.489 |
nesday | -0.488 |
pher | -0.451 |
cream | -0.420 |
displayText | -0.407 |
Token | weapons |
Token ID | 3777 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
mble | +5.378 |
nesday | +5.336 |
pher | +4.975 |
cream | +4.411 |
ationally | +4.107 |
Neg logit contributions | |
Tik | -4.633 |
stride | -4.498 |
viral | -4.487 |
uni | -4.386 |
Kik | -4.317 |
Token | by |
Token ID | 416 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
viral | +0.886 |
Tik | +0.882 |
stride | +0.853 |
Kik | +0.810 |
characteristic | +0.796 |
Neg logit contributions | |
nesday | -1.569 |
mble | -1.561 |
pher | -1.421 |
cream | -1.316 |
displayText | -1.273 |
Token | Osama |
Token ID | 29236 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
mble | +0.531 |
nesday | +0.530 |
pher | +0.487 |
cream | +0.448 |
displayText | +0.428 |
Neg logit contributions | |
viral | -0.293 |
Tik | -0.293 |
stride | -0.290 |
uni | -0.269 |
Kik | -0.268 |
Token | bin |
Token ID | 9874 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Tik | +4.385 |
viral | +4.154 |
stride | +4.019 |
Kik | +3.808 |
mu | +3.596 |
Neg logit contributions | |
mble | -16.188 |
nesday | -15.788 |
pher | -14.240 |
cream | -13.725 |
displayText | -13.545 |
Token | Laden |
Token ID | 19402 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
Tik | +3.683 |
viral | +3.592 |
stride | +3.465 |
Kik | +3.289 |
characteristic | +3.208 |
Neg logit contributions | |
mble | -7.935 |
nesday | -7.862 |
pher | -7.051 |
cream | -6.630 |
displayText | -6.459 |
Token | and |
Token ID | 290 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
nesday | +0.221 |
mble | +0.219 |
pher | +0.203 |
cream | +0.188 |
displayText | +0.181 |
Neg logit contributions | |
viral | -0.113 |
Tik | -0.113 |
stride | -0.109 |
Kik | -0.104 |
characteristic | -0.101 |
Token | Saddam |
Token ID | 24277 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
viral | +0.538 |
Tik | +0.535 |
stride | +0.521 |
Kik | +0.494 |
characteristic | +0.487 |
Neg logit contributions | |
nesday | -0.844 |
mble | -0.837 |
pher | -0.761 |
cream | -0.702 |
displayText | -0.675 |
Token | Hussein |
Token ID | 22983 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
viral | +1.034 |
Tik | +1.025 |
stride | +0.987 |
Kik | +0.917 |
characteristic | +0.897 |
Neg logit contributions | |
nesday | -2.683 |
mble | -2.665 |
pher | -2.460 |
cream | -2.298 |
displayText | -2.233 |
Token | ET |
Token ID | 2767 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Tik | +0.873 |
viral | +0.866 |
stride | +0.831 |
Kik | +0.813 |
uni | +0.784 |
Neg logit contributions | |
nesday | -1.318 |
mble | -1.304 |
pher | -1.157 |
cream | -1.069 |
displayText | -1.025 |
Token | who |
Token ID | 508 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
nesday | +1.123 |
mble | +1.118 |
pher | +1.019 |
cream | +0.949 |
displayText | +0.911 |
Neg logit contributions | |
Tik | -0.565 |
viral | -0.564 |
stride | -0.538 |
Kik | -0.513 |
uni | -0.506 |
Token | have |
Token ID | 423 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
viral | +0.675 |
Tik | +0.673 |
stride | +0.649 |
Kik | +0.618 |
characteristic | +0.607 |
Neg logit contributions | |
nesday | -1.177 |
mble | -1.172 |
pher | -1.067 |
cream | -0.986 |
displayText | -0.954 |
Token | a |
Token ID | 257 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
viral | +0.316 |
Tik | +0.315 |
stride | +0.306 |
Kik | +0.292 |
characteristic | +0.288 |
Neg logit contributions | |
nesday | -0.471 |
mble | -0.468 |
pher | -0.422 |
cream | -0.390 |
displayText | -0.377 |
Token | long |
Token ID | 890 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
viral | +1.377 |
Tik | +1.364 |
stride | +1.322 |
Kik | +1.244 |
characteristic | +1.232 |
Neg logit contributions | |
nesday | -2.659 |
mble | -2.642 |
pher | -2.410 |
cream | -2.240 |
displayText | -2.180 |
Token | standing |
Token ID | 5055 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
viral | +3.948 |
stride | +3.912 |
Tik | +3.775 |
characteristic | +3.467 |
Kik | +3.409 |
Neg logit contributions | |
nesday | -10.533 |
mble | -10.352 |
pher | -9.578 |
cream | -8.998 |
displayText | -8.978 |
Token | heritage |
Token ID | 15012 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
viral | +6.057 |
stride | +5.958 |
Tik | +5.722 |
characteristic | +5.614 |
search | +5.388 |
Neg logit contributions | |
nesday | -13.644 |
mble | -13.375 |
pher | -12.294 |
displayText | -11.655 |
cream | -11.551 |
Token | as |
Token ID | 355 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
viral | +3.386 |
Tik | +3.318 |
stride | +3.251 |
characteristic | +3.046 |
Kik | +3.020 |
Neg logit contributions | |
nesday | -7.118 |
mble | -7.056 |
pher | -6.411 |
cream | -5.992 |
displayText | -5.911 |
Token | a |
Token ID | 257 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
viral | +0.317 |
Tik | +0.316 |
stride | +0.306 |
Kik | +0.292 |
characteristic | +0.286 |
Neg logit contributions | |
nesday | -0.515 |
mble | -0.512 |
pher | -0.465 |
cream | -0.429 |
displayText | -0.414 |
Token | recogn |
Token ID | 3018 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
viral | +0.706 |
Tik | +0.704 |
stride | +0.680 |
Kik | +0.646 |
characteristic | +0.633 |
Neg logit contributions | |
nesday | -1.273 |
mble | -1.268 |
pher | -1.155 |
cream | -1.069 |
displayText | -1.034 |
Token | isable |
Token ID | 43942 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
nesday | +1.975 |
mble | +1.963 |
pher | +1.783 |
cream | +1.622 |
displayText | +1.547 |
Neg logit contributions | |
viral | -1.618 |
Tik | -1.615 |
stride | -1.568 |
Kik | -1.502 |
characteristic | -1.480 |
Token | band |
Token ID | 4097 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
mble | +4.254 |
nesday | +4.253 |
pher | +3.861 |
cream | +3.550 |
displayText | +3.458 |
Neg logit contributions | |
Tik | -2.289 |
viral | -2.232 |
stride | -2.186 |
uni | -2.111 |
Kik | -2.110 |
Token | is |
Token ID | 318 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
viral | +2.324 |
Tik | +2.307 |
stride | +2.239 |
Kik | +2.104 |
characteristic | +2.101 |
Neg logit contributions | |
nesday | -4.270 |
mble | -4.249 |
pher | -3.856 |
cream | -3.582 |
displayText | -3.488 |
Token | led |
Token ID | 2957 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
viral | +1.781 |
Tik | +1.761 |
stride | +1.704 |
Kik | +1.619 |
characteristic | +1.608 |
Neg logit contributions | |
nesday | -3.092 |
mble | -3.061 |
pher | -2.778 |
cream | -2.579 |
displayText | -2.508 |
Token | by |
Token ID | 416 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
nesday | +3.640 |
mble | +3.616 |
pher | +3.285 |
cream | +2.985 |
displayText | +2.875 |
Neg logit contributions | |
Tik | -2.580 |
viral | -2.544 |
stride | -2.510 |
Kik | -2.420 |
squid | -2.339 |
Token | P |
Token ID | 350 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
viral | +0.630 |
Tik | +0.629 |
stride | +0.610 |
Kik | +0.580 |
characteristic | +0.572 |
Neg logit contributions | |
nesday | -1.001 |
mble | -0.998 |
pher | -0.903 |
cream | -0.832 |
displayText | -0.803 |
Token | oh |
Token ID | 1219 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
viral | +4.683 |
Tik | +4.646 |
stride | +4.505 |
Kik | +4.348 |
uni | +4.295 |
Neg logit contributions | |
nesday | -6.269 |
mble | -6.198 |
pher | -5.564 |
cream | -5.123 |
displayText | -5.008 |
Token | j |
Token ID | 73 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Tik | +9.385 |
viral | +9.273 |
Kik | +8.750 |
stride | +8.735 |
uni | +8.586 |
Neg logit contributions | |
nesday | -10.171 |
mble | -10.001 |
pher | -8.717 |
displayText | -8.153 |
cream | -7.922 |
Token | ola |
Token ID | 5708 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
Tik | +4.199 |
viral | +4.185 |
stride | +4.002 |
Kik | +3.919 |
uni | +3.867 |
Neg logit contributions | |
nesday | -5.532 |
mble | -5.492 |
pher | -4.892 |
cream | -4.527 |
displayText | -4.401 |
Token | on |
Token ID | 319 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
viral | +2.307 |
Tik | +2.306 |
stride | +2.217 |
Kik | +2.122 |
characteristic | +2.068 |
Neg logit contributions | |
nesday | -4.201 |
mble | -4.174 |
pher | -3.796 |
cream | -3.526 |
displayText | -3.423 |
Token | piano |
Token ID | 19132 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
viral | +2.901 |
Tik | +2.879 |
stride | +2.789 |
Kik | +2.654 |
characteristic | +2.612 |
Neg logit contributions | |
nesday | -5.220 |
mble | -5.185 |
pher | -4.724 |
cream | -4.388 |
displayText | -4.280 |
Token | , |
Token ID | 11 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
mble | +2.647 |
nesday | +2.626 |
pher | +2.425 |
cream | +2.246 |
displayText | +2.133 |
Neg logit contributions | |
viral | -1.368 |
Tik | -1.356 |
stride | -1.296 |
uni | -1.238 |
Kik | -1.228 |
Token | � |
Token ID | 239 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
viral | +3.634 |
Tik | +3.616 |
stride | +3.491 |
Kik | +3.360 |
uni | +3.330 |
Neg logit contributions | |
nesday | -4.916 |
mble | -4.788 |
pher | -4.360 |
cream | -3.967 |
displayText | -3.842 |
Token | � |
Token ID | 46349 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
viral | +1.114 |
Tik | +1.109 |
stride | +1.072 |
Kik | +1.022 |
characteristic | +1.004 |
Neg logit contributions | |
nesday | -1.912 |
mble | -1.902 |
pher | -1.728 |
cream | -1.598 |
displayText | -1.547 |
Token | � |
Token ID | 111 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
viral | +6.084 |
Tik | +6.062 |
stride | +5.747 |
Kik | +5.548 |
uni | +5.471 |
Neg logit contributions | |
nesday | -10.315 |
mble | -9.878 |
pher | -9.213 |
cream | -8.414 |
displayText | -8.206 |
Token | � |
Token ID | 17358 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
viral | +5.248 |
Tik | +5.170 |
stride | +4.981 |
Kik | +4.929 |
characteristic | +4.825 |
Neg logit contributions | |
nesday | -8.117 |
mble | -8.035 |
pher | -7.273 |
cream | -6.696 |
displayText | -6.535 |
Token | � |
Token ID | 223 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
viral | +3.841 |
Tik | +3.805 |
stride | +3.702 |
Kik | +3.585 |
characteristic | +3.560 |
Neg logit contributions | |
nesday | -4.180 |
mble | -4.159 |
pher | -3.725 |
cream | -3.366 |
displayText | -3.242 |
Token | 一 |
Token ID | 31660 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
viral | +3.042 |
Tik | +3.001 |
stride | +2.915 |
Kik | +2.822 |
characteristic | +2.766 |
Neg logit contributions | |
nesday | -5.177 |
mble | -5.152 |
pher | -4.669 |
cream | -4.309 |
displayText | -4.186 |
Token | � |
Token ID | 25001 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
viral | +7.354 |
Tik | +7.192 |
stride | +6.949 |
Kik | +6.887 |
characteristic | +6.802 |
Neg logit contributions | |
nesday | -11.876 |
mble | -11.636 |
pher | -10.536 |
cream | -9.606 |
displayText | -9.562 |
Token | � |
Token ID | 245 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
viral | +5.139 |
Tik | +5.064 |
stride | +4.884 |
Kik | +4.736 |
characteristic | +4.701 |
Neg logit contributions | |
nesday | -7.769 |
mble | -7.669 |
pher | -6.939 |
cream | -6.412 |
displayText | -6.271 |
Token | � |
Token ID | 165 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
viral | +5.036 |
Tik | +4.945 |
stride | +4.811 |
Kik | +4.694 |
characteristic | +4.612 |
Neg logit contributions | |
nesday | -7.916 |
mble | -7.860 |
pher | -7.095 |
cream | -6.510 |
displayText | -6.322 |
Token | � |
Token ID | 246 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
viral | +4.592 |
Tik | +4.556 |
stride | +4.425 |
Kik | +4.264 |
characteristic | +4.223 |
Neg logit contributions | |
nesday | -5.404 |
mble | -5.279 |
pher | -4.770 |
cream | -4.350 |
displayText | -4.226 |
Token | � |
Token ID | 253 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
viral | +2.025 |
Tik | +2.017 |
stride | +1.959 |
Kik | +1.886 |
characteristic | +1.857 |
Neg logit contributions | |
nesday | -2.541 |
mble | -2.517 |
pher | -2.257 |
cream | -2.061 |
displayText | -1.992 |
Token | charge |
Token ID | 3877 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
mble | +5.057 |
nesday | +5.022 |
pher | +4.692 |
cream | +4.303 |
displayText | +4.122 |
Neg logit contributions | |
Tik | -2.702 |
viral | -2.632 |
stride | -2.584 |
uni | -2.546 |
Kik | -2.462 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-03 |
Pos logit contributions | |
Tik | +0.512 |
viral | +0.509 |
stride | +0.490 |
Kik | +0.467 |
uni | +0.458 |
Neg logit contributions | |
nesday | -0.976 |
mble | -0.971 |
pher | -0.891 |
cream | -0.827 |
displayText | -0.794 |
Token | These |
Token ID | 2312 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
nesday | +0.010 |
mble | +0.010 |
pher | +0.009 |
cream | +0.009 |
displayText | +0.008 |
Neg logit contributions | |
viral | -0.006 |
Tik | -0.006 |
stride | -0.005 |
characteristic | -0.005 |
Kik | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
nesday | +1.002 |
mble | +0.999 |
pher | +0.908 |
cream | +0.838 |
displayText | +0.805 |
Neg logit contributions | |
Tik | -0.587 |
viral | -0.583 |
stride | -0.574 |
Kik | -0.543 |
uni | -0.534 |
Token | B |
Token ID | 33 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
nesday | +1.570 |
mble | +1.564 |
pher | +1.412 |
cream | +1.296 |
displayText | +1.232 |
Neg logit contributions | |
Tik | -1.276 |
viral | -1.274 |
stride | -1.246 |
Kik | -1.187 |
characteristic | -1.171 |
Token | aghd |
Token ID | 16650 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
viral | +3.842 |
Tik | +3.810 |
stride | +3.626 |
uni | +3.492 |
Kik | +3.486 |
Neg logit contributions | |
nesday | -6.850 |
mble | -6.821 |
pher | -6.150 |
cream | -5.744 |
displayText | -5.609 |
Token | ad |
Token ID | 324 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Tik | +6.726 |
viral | +6.626 |
uni | +6.414 |
stride | +6.100 |
characteristic | +5.865 |
Neg logit contributions | |
mble | -12.824 |
nesday | -12.758 |
pher | -11.361 |
cream | -10.773 |
displayText | -10.370 |
Token | batteries |
Token ID | 13591 |
Feature activation | +4.47e-03 |
Pos logit contributions | |
viral | +0.946 |
Tik | +0.942 |
stride | +0.916 |
Kik | +0.873 |
characteristic | +0.860 |
Neg logit contributions | |
nesday | -1.409 |
mble | -1.402 |
pher | -1.268 |
cream | -1.166 |
displayText | -1.124 |
Token | " |
Token ID | 1 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
nesday | +0.021 |
mble | +0.021 |
pher | +0.019 |
cream | +0.017 |
displayText | +0.017 |
Neg logit contributions | |
viral | -0.013 |
Tik | -0.013 |
stride | -0.012 |
Kik | -0.012 |
characteristic | -0.011 |
Token | may |
Token ID | 743 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
viral | +0.827 |
Tik | +0.824 |
stride | +0.797 |
Kik | +0.759 |
characteristic | +0.745 |
Neg logit contributions | |
nesday | -1.401 |
mble | -1.393 |
pher | -1.268 |
cream | -1.172 |
displayText | -1.130 |
Token | have |
Token ID | 423 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
viral | +1.881 |
Tik | +1.863 |
stride | +1.822 |
Kik | +1.714 |
characteristic | +1.713 |
Neg logit contributions | |
nesday | -2.979 |
mble | -2.965 |
pher | -2.674 |
cream | -2.479 |
displayText | -2.407 |
Token | by |
Token ID | 416 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
nesday | +4.715 |
mble | +4.690 |
pher | +4.301 |
cream | +3.905 |
displayText | +3.671 |
Neg logit contributions | |
Tik | -3.258 |
viral | -3.233 |
stride | -3.159 |
uni | -3.034 |
Kik | -3.010 |
Token | the |
Token ID | 262 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
nesday | +0.370 |
mble | +0.368 |
pher | +0.334 |
cream | +0.309 |
displayText | +0.295 |
Neg logit contributions | |
Tik | -0.228 |
viral | -0.227 |
stride | -0.222 |
Kik | -0.210 |
uni | -0.208 |
Token | vulnerability |
Token ID | 15131 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
Tik | +0.231 |
viral | +0.230 |
stride | +0.223 |
Kik | +0.211 |
uni | +0.207 |
Neg logit contributions | |
nesday | -0.426 |
mble | -0.424 |
pher | -0.386 |
cream | -0.359 |
displayText | -0.346 |
Token | of |
Token ID | 286 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
nesday | +0.113 |
mble | +0.113 |
pher | +0.103 |
cream | +0.096 |
displayText | +0.092 |
Neg logit contributions | |
Tik | -0.059 |
viral | -0.059 |
stride | -0.057 |
Kik | -0.054 |
uni | -0.053 |
Token | his |
Token ID | 465 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
nesday | +2.490 |
mble | +2.485 |
pher | +2.251 |
cream | +2.048 |
displayText | +1.920 |
Neg logit contributions | |
Tik | -1.848 |
viral | -1.846 |
stride | -1.802 |
uni | -1.712 |
Kik | -1.709 |
Token | prog |
Token ID | 1172 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
viral | +1.738 |
Tik | +1.717 |
stride | +1.666 |
Kik | +1.562 |
characteristic | +1.545 |
Neg logit contributions | |
nesday | -3.829 |
mble | -3.801 |
pher | -3.476 |
cream | -3.243 |
displayText | -3.169 |
Token | eny |
Token ID | 28558 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
viral | +8.129 |
Tik | +7.819 |
stride | +7.798 |
uni | +7.691 |
Kik | +7.626 |
Neg logit contributions | |
nesday | -10.938 |
mble | -10.597 |
pher | -9.330 |
displayText | -8.967 |
cream | -8.685 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
viral | +1.655 |
Tik | +1.647 |
stride | +1.587 |
Kik | +1.512 |
characteristic | +1.496 |
Neg logit contributions | |
nesday | -2.961 |
mble | -2.944 |
pher | -2.665 |
cream | -2.473 |
displayText | -2.414 |
Token | that |
Token ID | 326 |
Feature activation | -2.17e-03 |
Pos logit contributions | |
viral | +0.328 |
Tik | +0.327 |
stride | +0.317 |
Kik | +0.299 |
uni | +0.296 |
Neg logit contributions | |
nesday | -0.548 |
mble | -0.544 |
pher | -0.496 |
cream | -0.457 |
displayText | -0.439 |
Token | he |
Token ID | 339 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
viral | +0.006 |
Tik | +0.006 |
stride | +0.006 |
Kik | +0.006 |
uni | +0.005 |
Neg logit contributions | |
nesday | -0.010 |
mble | -0.010 |
pher | -0.009 |
cream | -0.008 |
displayText | -0.008 |
Token | began |
Token ID | 2540 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
viral | +1.911 |
Tik | +1.897 |
stride | +1.849 |
characteristic | +1.756 |
Kik | +1.755 |
Neg logit contributions | |
nesday | -2.808 |
mble | -2.804 |
pher | -2.476 |
cream | -2.307 |
displayText | -2.240 |
Token | Hall |
Token ID | 4789 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
viral | +0.626 |
Tik | +0.622 |
stride | +0.606 |
Kik | +0.577 |
characteristic | +0.567 |
Neg logit contributions | |
nesday | -0.962 |
mble | -0.957 |
pher | -0.868 |
cream | -0.798 |
displayText | -0.771 |
Token | Collection |
Token ID | 12251 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
Tik | +3.037 |
viral | +3.032 |
stride | +2.879 |
Kik | +2.737 |
characteristic | +2.727 |
Neg logit contributions | |
nesday | -6.368 |
mble | -6.321 |
pher | -5.773 |
cream | -5.383 |
displayText | -5.229 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
nesday | +3.408 |
mble | +3.378 |
pher | +3.115 |
cream | +2.902 |
displayText | +2.840 |
Neg logit contributions | |
viral | -1.560 |
Tik | -1.539 |
stride | -1.521 |
Kik | -1.422 |
squid | -1.364 |
Token | replacing |
Token ID | 13586 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
nesday | +0.852 |
mble | +0.841 |
pher | +0.773 |
cream | +0.713 |
displayText | +0.688 |
Neg logit contributions | |
viral | -0.474 |
Tik | -0.469 |
stride | -0.458 |
Kik | -0.433 |
uni | -0.422 |
Token | Confederate |
Token ID | 21900 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
viral | +0.245 |
Tik | +0.244 |
stride | +0.238 |
Kik | +0.225 |
characteristic | +0.222 |
Neg logit contributions | |
nesday | -0.380 |
mble | -0.377 |
pher | -0.343 |
cream | -0.315 |
displayText | -0.303 |
Token | General |
Token ID | 3611 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
nesday | +0.073 |
mble | +0.072 |
pher | +0.066 |
cream | +0.061 |
displayText | +0.059 |
Neg logit contributions | |
viral | -0.041 |
Tik | -0.041 |
stride | -0.039 |
Kik | -0.037 |
uni | -0.037 |
Token | Edmund |
Token ID | 35646 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
Tik | +8.310 |
viral | +8.022 |
stride | +7.950 |
Kik | +7.553 |
characteristic | +7.441 |
Neg logit contributions | |
mble | -11.370 |
nesday | -11.279 |
pher | -9.864 |
cream | -9.204 |
displayText | -9.103 |
Token | Kirby |
Token ID | 23965 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
nesday | +2.088 |
mble | +2.011 |
pher | +1.888 |
cream | +1.711 |
displayText | +1.625 |
Neg logit contributions | |
viral | -1.395 |
Tik | -1.356 |
stride | -1.346 |
characteristic | -1.259 |
uni | -1.259 |
Token | Smith |
Token ID | 4176 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
nesday | +0.442 |
mble | +0.440 |
pher | +0.406 |
cream | +0.377 |
displayText | +0.364 |
Neg logit contributions | |
viral | -0.227 |
Tik | -0.223 |
stride | -0.218 |
Kik | -0.202 |
uni | -0.200 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
viral | +1.127 |
Tik | +1.120 |
stride | +1.078 |
Kik | +1.013 |
characteristic | +0.993 |
Neg logit contributions | |
nesday | -2.478 |
mble | -2.465 |
pher | -2.262 |
cream | -2.109 |
displayText | -2.046 |
Token | 7 |
Token ID | 22 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
nesday | +0.060 |
mble | +0.060 |
pher | +0.054 |
cream | +0.050 |
displayText | +0.048 |
Neg logit contributions | |
viral | -0.038 |
Tik | -0.038 |
stride | -0.036 |
Kik | -0.035 |
characteristic | -0.034 |
Token | AL |
Token ID | 1847 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
nesday | +0.273 |
mble | +0.272 |
pher | +0.236 |
cream | +0.213 |
displayText | +0.203 |
Neg logit contributions | |
Tik | -0.316 |
viral | -0.314 |
stride | -0.308 |
Kik | -0.298 |
uni | -0.295 |
Token | EM |
Token ID | 3620 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
nesday | +1.814 |
mble | +1.781 |
pher | +1.614 |
cream | +1.494 |
displayText | +1.441 |
Neg logit contributions | |
Tik | -1.384 |
viral | -1.361 |
stride | -1.341 |
uni | -1.266 |
Kik | -1.261 |
Token | — |
Token ID | 851 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
nesday | +1.988 |
mble | +1.964 |
pher | +1.802 |
cream | +1.659 |
displayText | +1.606 |
Neg logit contributions | |
viral | -1.315 |
Tik | -1.294 |
stride | -1.283 |
Kik | -1.209 |
characteristic | -1.204 |
Token | Israeli |
Token ID | 6085 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Tik | +1.326 |
viral | +1.323 |
stride | +1.272 |
Kik | +1.215 |
characteristic | +1.189 |
Neg logit contributions | |
nesday | -2.326 |
mble | -2.321 |
pher | -2.102 |
cream | -1.949 |
displayText | -1.886 |
Token | and |
Token ID | 290 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
nesday | +1.447 |
mble | +1.423 |
pher | +1.303 |
cream | +1.198 |
displayText | +1.155 |
Neg logit contributions | |
viral | -0.950 |
Tik | -0.941 |
stride | -0.918 |
Kik | -0.879 |
uni | -0.864 |
Token | Turkish |
Token ID | 9663 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
nesday | +2.425 |
mble | +2.391 |
pher | +2.213 |
cream | +2.046 |
displayText | +1.985 |
Neg logit contributions | |
Tik | -1.191 |
viral | -1.183 |
stride | -1.162 |
Kik | -1.088 |
uni | -1.079 |
Token | officials |
Token ID | 2828 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
nesday | +6.966 |
mble | +6.767 |
pher | +6.339 |
cream | +5.759 |
displayText | +5.583 |
Neg logit contributions | |
Tik | -5.261 |
viral | -5.201 |
stride | -5.075 |
uni | -4.973 |
Kik | -4.949 |
Token | have |
Token ID | 423 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
nesday | +0.714 |
mble | +0.708 |
pher | +0.645 |
cream | +0.592 |
displayText | +0.571 |
Neg logit contributions | |
viral | -0.470 |
Tik | -0.468 |
stride | -0.453 |
Kik | -0.435 |
characteristic | -0.426 |
Token | reached |
Token ID | 4251 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
nesday | +0.254 |
mble | +0.253 |
pher | +0.227 |
cream | +0.208 |
displayText | +0.200 |
Neg logit contributions | |
viral | -0.198 |
Tik | -0.197 |
stride | -0.192 |
Kik | -0.184 |
characteristic | -0.181 |
Token | a |
Token ID | 257 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
viral | +0.332 |
Tik | +0.331 |
stride | +0.321 |
Kik | +0.306 |
characteristic | +0.302 |
Neg logit contributions | |
nesday | -0.495 |
mble | -0.492 |
pher | -0.444 |
cream | -0.409 |
displayText | -0.395 |
Token | preliminary |
Token ID | 15223 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
nesday | +1.510 |
mble | +1.503 |
pher | +1.362 |
cream | +1.250 |
displayText | +1.208 |
Neg logit contributions | |
Tik | -1.024 |
viral | -1.021 |
stride | -0.988 |
Kik | -0.954 |
uni | -0.934 |
Token | . |
Token ID | 13 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
viral | +1.097 |
Tik | +1.093 |
stride | +1.056 |
Kik | +1.003 |
characteristic | +0.988 |
Neg logit contributions | |
nesday | -1.940 |
mble | -1.929 |
pher | -1.753 |
cream | -1.625 |
displayText | -1.574 |
Token | The |
Token ID | 383 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
viral | +0.249 |
Tik | +0.247 |
stride | +0.240 |
Kik | +0.227 |
characteristic | +0.222 |
Neg logit contributions | |
nesday | -0.448 |
mble | -0.447 |
pher | -0.409 |
cream | -0.377 |
displayText | -0.365 |
Token | Blessed |
Token ID | 33398 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
mble | +1.970 |
nesday | +1.959 |
pher | +1.792 |
cream | +1.647 |
displayText | +1.575 |
Neg logit contributions | |
viral | -1.209 |
Tik | -1.201 |
stride | -1.170 |
Kik | -1.119 |
uni | -1.077 |
Token | Trinity |
Token ID | 22844 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
nesday | +0.228 |
mble | +0.226 |
pher | +0.206 |
cream | +0.189 |
displayText | +0.180 |
Neg logit contributions | |
viral | -0.167 |
Tik | -0.165 |
stride | -0.162 |
Kik | -0.154 |
characteristic | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
nesday | +0.298 |
mble | +0.297 |
pher | +0.274 |
cream | +0.252 |
displayText | +0.244 |
Neg logit contributions | |
viral | -0.160 |
Tik | -0.159 |
stride | -0.154 |
Kik | -0.145 |
characteristic | -0.141 |
Token | Creation |
Token ID | 21582 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
viral | +0.520 |
Tik | +0.515 |
stride | +0.500 |
Kik | +0.474 |
characteristic | +0.465 |
Neg logit contributions | |
nesday | -0.924 |
mble | -0.920 |
pher | -0.840 |
cream | -0.776 |
displayText | -0.750 |
Token | . |
Token ID | 13 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
nesday | +8.472 |
mble | +8.428 |
pher | +7.849 |
cream | +7.147 |
displayText | +6.875 |
Neg logit contributions | |
viral | -5.000 |
Tik | -4.914 |
stride | -4.809 |
Kik | -4.642 |
squid | -4.523 |
Token | The |
Token ID | 383 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
nesday | +0.345 |
mble | +0.344 |
pher | +0.314 |
cream | +0.289 |
displayText | +0.277 |
Neg logit contributions | |
viral | -0.220 |
Tik | -0.217 |
stride | -0.213 |
Kik | -0.201 |
characteristic | -0.198 |
Token | Angels |
Token ID | 17654 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
mble | +1.062 |
nesday | +1.060 |
pher | +0.963 |
cream | +0.887 |
displayText | +0.846 |
Neg logit contributions | |
viral | -0.672 |
Tik | -0.669 |
stride | -0.653 |
Kik | -0.621 |
characteristic | -0.604 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
viral | +0.537 |
Tik | +0.533 |
stride | +0.513 |
Kik | +0.485 |
characteristic | +0.475 |
Neg logit contributions | |
nesday | -1.081 |
mble | -1.077 |
pher | -0.986 |
cream | -0.917 |
displayText | -0.887 |
Token | The |
Token ID | 383 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
viral | +0.739 |
Tik | +0.733 |
stride | +0.714 |
Kik | +0.677 |
characteristic | +0.668 |
Neg logit contributions | |
nesday | -1.192 |
mble | -1.186 |
pher | -1.079 |
cream | -0.995 |
displayText | -0.959 |
Token | simple |
Token ID | 2829 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
viral | +1.904 |
Tik | +1.881 |
stride | +1.818 |
Kik | +1.723 |
characteristic | +1.707 |
Neg logit contributions | |
nesday | -3.316 |
mble | -3.288 |
pher | -2.980 |
cream | -2.763 |
displayText | -2.688 |
Token | tasks |
Token ID | 8861 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
mble | +0.800 |
nesday | +0.799 |
pher | +0.727 |
cream | +0.668 |
displayText | +0.642 |
Neg logit contributions | |
Tik | -0.529 |
viral | -0.525 |
stride | -0.514 |
Kik | -0.492 |
uni | -0.484 |
Token | that |
Token ID | 326 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
nesday | +0.961 |
mble | +0.955 |
pher | +0.872 |
cream | +0.806 |
displayText | +0.773 |
Neg logit contributions | |
Tik | -0.606 |
viral | -0.600 |
stride | -0.583 |
Kik | -0.559 |
uni | -0.547 |
Token | should |
Token ID | 815 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
viral | +0.967 |
Tik | +0.963 |
stride | +0.930 |
Kik | +0.882 |
characteristic | +0.867 |
Neg logit contributions | |
nesday | -1.779 |
mble | -1.770 |
pher | -1.612 |
cream | -1.495 |
displayText | -1.448 |
Token | be |
Token ID | 307 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
viral | +1.535 |
Tik | +1.517 |
stride | +1.486 |
Kik | +1.404 |
characteristic | +1.393 |
Neg logit contributions | |
nesday | -2.425 |
mble | -2.417 |
pher | -2.175 |
cream | -2.016 |
displayText | -1.959 |
Token | handled |
Token ID | 12118 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
viral | +0.921 |
Tik | +0.915 |
stride | +0.891 |
Kik | +0.854 |
characteristic | +0.845 |
Neg logit contributions | |
nesday | -1.157 |
mble | -1.151 |
pher | -1.027 |
cream | -0.940 |
displayText | -0.908 |
Token | in |
Token ID | 287 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
nesday | +7.340 |
mble | +7.214 |
pher | +6.847 |
cream | +6.231 |
displayText | +5.722 |
Neg logit contributions | |
Tik | -5.395 |
viral | -5.145 |
Kik | -5.022 |
stride | -4.998 |
uni | -4.963 |
Token | a |
Token ID | 257 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
viral | +0.856 |
Tik | +0.853 |
stride | +0.826 |
Kik | +0.786 |
characteristic | +0.774 |
Neg logit contributions | |
nesday | -1.405 |
mble | -1.397 |
pher | -1.267 |
cream | -1.170 |
displayText | -1.133 |
Token | few |
Token ID | 1178 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
viral | +0.867 |
Tik | +0.865 |
stride | +0.835 |
Kik | +0.793 |
characteristic | +0.780 |
Neg logit contributions | |
nesday | -1.516 |
mble | -1.508 |
pher | -1.373 |
cream | -1.270 |
displayText | -1.228 |
Token | seconds |
Token ID | 4201 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
nesday | +1.466 |
mble | +1.462 |
pher | +1.329 |
cream | +1.211 |
displayText | +1.159 |
Neg logit contributions | |
Tik | -1.088 |
viral | -1.083 |
stride | -1.052 |
Kik | -1.007 |
uni | -0.995 |
Token | with |
Token ID | 351 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
nesday | +1.982 |
mble | +1.981 |
pher | +1.805 |
cream | +1.668 |
displayText | +1.591 |
Neg logit contributions | |
Tik | -1.284 |
viral | -1.263 |
stride | -1.224 |
Kik | -1.182 |
uni | -1.164 |
Token | Let |
Token ID | 3914 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
nesday | +0.001 |
mble | +0.001 |
pher | +0.001 |
cream | +0.001 |
displayText | +0.001 |
Neg logit contributions | |
viral | -0.000 |
Tik | -0.000 |
stride | -0.000 |
Kik | -0.000 |
characteristic | -0.000 |
Token | us |
Token ID | 514 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
viral | +2.034 |
Tik | +2.032 |
stride | +1.960 |
Kik | +1.871 |
characteristic | +1.853 |
Neg logit contributions | |
nesday | -3.108 |
mble | -3.095 |
pher | -2.797 |
cream | -2.582 |
displayText | -2.496 |
Token | remember |
Token ID | 3505 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
viral | +0.900 |
Tik | +0.898 |
stride | +0.865 |
Kik | +0.833 |
characteristic | +0.817 |
Neg logit contributions | |
nesday | -1.360 |
mble | -1.353 |
pher | -1.227 |
cream | -1.125 |
displayText | -1.086 |
Token | that |
Token ID | 326 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
viral | +0.155 |
Tik | +0.154 |
stride | +0.149 |
Kik | +0.142 |
characteristic | +0.139 |
Neg logit contributions | |
nesday | -0.254 |
mble | -0.253 |
pher | -0.229 |
cream | -0.211 |
displayText | -0.204 |
Token | the |
Token ID | 262 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
viral | +1.699 |
Tik | +1.692 |
stride | +1.634 |
Kik | +1.551 |
characteristic | +1.529 |
Neg logit contributions | |
nesday | -3.022 |
mble | -3.005 |
pher | -2.734 |
cream | -2.534 |
displayText | -2.457 |
Token | Sloven |
Token ID | 30694 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
viral | +0.222 |
Tik | +0.221 |
stride | +0.213 |
Kik | +0.203 |
characteristic | +0.199 |
Neg logit contributions | |
nesday | -0.395 |
mble | -0.393 |
pher | -0.357 |
cream | -0.331 |
displayText | -0.320 |
Token | ian |
Token ID | 666 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
nesday | +8.973 |
mble | +8.719 |
pher | +7.992 |
cream | +6.983 |
displayText | +6.555 |
Neg logit contributions | |
Tik | -10.713 |
viral | -10.645 |
stride | -10.331 |
Kik | -10.136 |
Hawai | -10.036 |
Token | government |
Token ID | 1230 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
nesday | +4.628 |
mble | +4.594 |
pher | +4.201 |
cream | +3.884 |
displayText | +3.760 |
Neg logit contributions | |
Tik | -2.758 |
viral | -2.756 |
stride | -2.651 |
Kik | -2.527 |
uni | -2.518 |
Token | declared |
Token ID | 6875 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
nesday | +0.724 |
mble | +0.718 |
pher | +0.658 |
cream | +0.606 |
displayText | +0.587 |
Neg logit contributions | |
viral | -0.424 |
Tik | -0.423 |
stride | -0.408 |
Kik | -0.390 |
characteristic | -0.381 |
Token | independence |
Token ID | 10404 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
viral | +2.597 |
Tik | +2.585 |
stride | +2.512 |
Kik | +2.393 |
characteristic | +2.382 |
Neg logit contributions | |
nesday | -3.525 |
mble | -3.508 |
pher | -3.162 |
cream | -2.911 |
displayText | -2.815 |
Token | in |
Token ID | 287 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
viral | +1.797 |
Tik | +1.781 |
stride | +1.724 |
Kik | +1.618 |
characteristic | +1.612 |
Neg logit contributions | |
mble | -3.502 |
nesday | -3.498 |
pher | -3.172 |
cream | -2.949 |
displayText | -2.867 |
Token | Us |
Token ID | 4021 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
nesday | +0.631 |
mble | +0.626 |
pher | +0.575 |
cream | +0.533 |
displayText | +0.511 |
Neg logit contributions | |
viral | -0.367 |
Tik | -0.364 |
stride | -0.359 |
Kik | -0.334 |
characteristic | -0.331 |
Token | , |
Token ID | 11 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
mble | +1.828 |
nesday | +1.821 |
pher | +1.650 |
cream | +1.539 |
displayText | +1.468 |
Neg logit contributions | |
viral | -1.182 |
Tik | -1.161 |
stride | -1.150 |
Kik | -1.081 |
uni | -1.074 |
Token | Matt |
Token ID | 4705 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
viral | +1.367 |
Tik | +1.365 |
stride | +1.315 |
Kik | +1.258 |
characteristic | +1.234 |
Neg logit contributions | |
nesday | -2.250 |
mble | -2.238 |
pher | -2.028 |
cream | -1.872 |
displayText | -1.814 |
Token | el |
Token ID | 417 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
nesday | +1.614 |
mble | +1.613 |
pher | +1.447 |
cream | +1.311 |
displayText | +1.248 |
Neg logit contributions | |
viral | -1.326 |
Tik | -1.306 |
stride | -1.283 |
Kik | -1.218 |
characteristic | -1.217 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
mble | +4.106 |
nesday | +4.085 |
pher | +3.711 |
cream | +3.467 |
displayText | +3.269 |
Neg logit contributions | |
viral | -2.778 |
stride | -2.707 |
Tik | -2.684 |
characteristic | -2.551 |
Kik | -2.533 |
Token | Ner |
Token ID | 21783 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
viral | +0.330 |
Tik | +0.328 |
stride | +0.319 |
Kik | +0.301 |
characteristic | +0.298 |
Neg logit contributions | |
nesday | -0.557 |
mble | -0.554 |
pher | -0.504 |
cream | -0.466 |
displayText | -0.449 |
Token | f |
Token ID | 69 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
mble | +7.006 |
nesday | +6.744 |
pher | +6.374 |
cream | +6.039 |
onica | +5.423 |
Neg logit contributions | |
Tik | -5.966 |
viral | -5.962 |
stride | -5.852 |
characteristic | -5.559 |
Kik | -5.466 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
nesday | +2.650 |
mble | +2.642 |
pher | +2.397 |
cream | +2.267 |
displayText | +2.119 |
Neg logit contributions | |
viral | -1.491 |
Tik | -1.456 |
stride | -1.450 |
characteristic | -1.346 |
Kik | -1.343 |
Token | Some |
Token ID | 2773 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
viral | +0.323 |
Tik | +0.319 |
stride | +0.313 |
Kik | +0.295 |
characteristic | +0.293 |
Neg logit contributions | |
nesday | -0.521 |
mble | -0.518 |
pher | -0.473 |
cream | -0.437 |
displayText | -0.421 |
Token | of |
Token ID | 286 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
mble | +2.956 |
nesday | +2.939 |
pher | +2.691 |
cream | +2.482 |
displayText | +2.355 |
Neg logit contributions | |
Tik | -1.761 |
viral | -1.747 |
stride | -1.728 |
uni | -1.639 |
Kik | -1.635 |
Token | these |
Token ID | 777 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
nesday | +2.465 |
mble | +2.459 |
pher | +2.235 |
cream | +2.074 |
displayText | +1.972 |
Neg logit contributions | |
viral | -1.546 |
stride | -1.535 |
Tik | -1.535 |
uni | -1.440 |
Kik | -1.430 |
Token | of |
Token ID | 286 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
Tik | +0.195 |
viral | +0.195 |
stride | +0.189 |
Kik | +0.179 |
uni | +0.176 |
Neg logit contributions | |
nesday | -0.363 |
mble | -0.361 |
pher | -0.327 |
cream | -0.305 |
displayText | -0.295 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
nesday | +2.663 |
mble | +2.654 |
pher | +2.368 |
cream | +2.169 |
displayText | +2.068 |
Neg logit contributions | |
viral | -1.739 |
Tik | -1.721 |
stride | -1.664 |
uni | -1.637 |
Kik | -1.600 |
Token | UEFA |
Token ID | 40858 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
nesday | +1.008 |
mble | +1.005 |
pher | +0.911 |
cream | +0.847 |
displayText | +0.819 |
Neg logit contributions | |
Tik | -0.506 |
viral | -0.505 |
stride | -0.484 |
Kik | -0.459 |
uni | -0.456 |
Token | Championships |
Token ID | 24782 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
nesday | +4.367 |
mble | +4.319 |
pher | +3.811 |
cream | +3.476 |
displayText | +3.245 |
Neg logit contributions | |
Tik | -3.691 |
viral | -3.669 |
stride | -3.576 |
Kik | -3.455 |
uni | -3.436 |
Token | qualifying |
Token ID | 18677 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Tik | +0.108 |
viral | +0.108 |
stride | +0.104 |
Kik | +0.099 |
characteristic | +0.096 |
Neg logit contributions | |
nesday | -0.211 |
mble | -0.210 |
pher | -0.191 |
cream | -0.178 |
displayText | -0.171 |
Token | tournament |
Token ID | 7756 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
nesday | +0.726 |
mble | +0.724 |
pher | +0.658 |
cream | +0.611 |
displayText | +0.588 |
Neg logit contributions | |
Tik | -0.382 |
viral | -0.382 |
stride | -0.365 |
Kik | -0.348 |
uni | -0.344 |
Token | in |
Token ID | 287 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
nesday | +0.899 |
mble | +0.893 |
pher | +0.809 |
cream | +0.752 |
displayText | +0.721 |
Neg logit contributions | |
Tik | -0.490 |
viral | -0.489 |
stride | -0.470 |
Kik | -0.448 |
uni | -0.441 |
Token | October |
Token ID | 3267 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
viral | +0.196 |
Tik | +0.195 |
stride | +0.188 |
Kik | +0.179 |
uni | +0.176 |
Neg logit contributions | |
nesday | -0.349 |
mble | -0.346 |
pher | -0.315 |
cream | -0.291 |
displayText | -0.281 |
Token | . |
Token ID | 13 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
viral | +0.012 |
Tik | +0.012 |
stride | +0.012 |
Kik | +0.011 |
characteristic | +0.011 |
Neg logit contributions | |
nesday | -0.025 |
mble | -0.025 |
pher | -0.023 |
cream | -0.021 |
displayText | -0.021 |
Token | � |
Token ID | 447 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
nesday | +3.211 |
mble | +3.179 |
pher | +2.928 |
cream | +2.733 |
displayText | +2.627 |
Neg logit contributions | |
viral | -1.829 |
stride | -1.770 |
Tik | -1.747 |
characteristic | -1.664 |
squid | -1.631 |
Token | � |
Token ID | 251 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
mble | +0.525 |
nesday | +0.523 |
pher | +0.454 |
cream | +0.401 |
displayText | +0.378 |
Neg logit contributions | |
Tik | -0.673 |
viral | -0.671 |
stride | -0.657 |
Kik | -0.637 |
characteristic | -0.630 |
Token | day |
Token ID | 1110 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
Tik | +1.322 |
viral | +1.321 |
stride | +1.259 |
Kik | +1.181 |
characteristic | +1.155 |
Neg logit contributions | |
nesday | -3.352 |
mble | -3.335 |
pher | -3.068 |
cream | -2.864 |
displayText | -2.781 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
viral | +2.649 |
Tik | +2.623 |
stride | +2.543 |
Kik | +2.432 |
characteristic | +2.392 |
Neg logit contributions | |
nesday | -4.235 |
mble | -4.212 |
pher | -3.796 |
cream | -3.512 |
displayText | -3.415 |
Token |
|
Token ID | 198 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
viral | +0.310 |
Tik | +0.309 |
stride | +0.300 |
Kik | +0.284 |
characteristic | +0.281 |
Neg logit contributions | |
nesday | -0.509 |
mble | -0.506 |
pher | -0.460 |
cream | -0.424 |
displayText | -0.410 |
Token |
|
Token ID | 198 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Tik | +0.763 |
viral | +0.762 |
stride | +0.715 |
Kik | +0.677 |
characteristic | +0.647 |
Neg logit contributions | |
mble | -2.179 |
nesday | -2.179 |
pher | -1.931 |
cream | -1.817 |
displayText | -1.779 |
Token | What |
Token ID | 2061 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
nesday | +0.862 |
mble | +0.858 |
pher | +0.763 |
cream | +0.688 |
displayText | +0.656 |
Neg logit contributions | |
viral | -0.876 |
Tik | -0.873 |
stride | -0.854 |
Kik | -0.820 |
characteristic | -0.813 |
Token | does |
Token ID | 857 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
nesday | +5.604 |
mble | +5.560 |
pher | +5.112 |
cream | +4.621 |
displayText | +4.467 |
Neg logit contributions | |
Tik | -3.377 |
viral | -3.359 |
stride | -3.349 |
uni | -3.202 |
squid | -3.140 |
Token | this |
Token ID | 428 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
nesday | +0.709 |
mble | +0.702 |
pher | +0.640 |
cream | +0.589 |
displayText | +0.562 |
Neg logit contributions | |
Tik | -0.421 |
viral | -0.419 |
stride | -0.407 |
Kik | -0.386 |
uni | -0.383 |
Token | mean |
Token ID | 1612 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
nesday | +2.346 |
mble | +2.333 |
pher | +2.095 |
cream | +1.917 |
displayText | +1.817 |
Neg logit contributions | |
Tik | -1.779 |
viral | -1.759 |
stride | -1.711 |
Kik | -1.672 |
uni | -1.636 |
Token | ? |
Token ID | 30 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
Tik | +0.097 |
viral | +0.097 |
stride | +0.094 |
Kik | +0.090 |
characteristic | +0.088 |
Neg logit contributions | |
nesday | -0.146 |
mble | -0.145 |
pher | -0.131 |
cream | -0.121 |
displayText | -0.116 |
Token | A |
Token ID | 317 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Tik | +1.407 |
viral | +1.407 |
stride | +1.350 |
Kik | +1.298 |
characteristic | +1.265 |
Neg logit contributions | |
nesday | -2.311 |
mble | -2.300 |
pher | -2.073 |
cream | -1.918 |
displayText | -1.861 |
Token | lot |
Token ID | 1256 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
Tik | +0.669 |
viral | +0.669 |
stride | +0.643 |
Kik | +0.608 |
characteristic | +0.596 |
Neg logit contributions | |
nesday | -1.354 |
mble | -1.347 |
pher | -1.231 |
cream | -1.144 |
displayText | -1.106 |
Token | that |
Token ID | 326 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
viral | +0.353 |
Tik | +0.352 |
stride | +0.339 |
Kik | +0.324 |
characteristic | +0.314 |
Neg logit contributions | |
nesday | -0.666 |
mble | -0.664 |
pher | -0.608 |
cream | -0.566 |
displayText | -0.544 |
Token | can |
Token ID | 460 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
viral | +1.655 |
Tik | +1.650 |
stride | +1.587 |
Kik | +1.508 |
characteristic | +1.484 |
Neg logit contributions | |
nesday | -3.089 |
mble | -3.072 |
pher | -2.794 |
cream | -2.596 |
displayText | -2.515 |
Token | help |
Token ID | 1037 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
viral | +0.511 |
Tik | +0.510 |
stride | +0.492 |
Kik | +0.470 |
characteristic | +0.461 |
Neg logit contributions | |
nesday | -0.863 |
mble | -0.858 |
pher | -0.782 |
cream | -0.722 |
displayText | -0.697 |
Token | rejuven |
Token ID | 46834 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
mble | +0.308 |
nesday | +0.307 |
pher | +0.281 |
cream | +0.258 |
displayText | +0.248 |
Neg logit contributions | |
viral | -0.184 |
Tik | -0.184 |
stride | -0.177 |
Kik | -0.169 |
characteristic | -0.167 |
Token | ate |
Token ID | 378 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
mble | +2.814 |
nesday | +2.797 |
pher | +2.472 |
cream | +2.200 |
displayText | +2.054 |
Neg logit contributions | |
Tik | -3.409 |
viral | -3.397 |
stride | -3.293 |
Kik | -3.211 |
characteristic | -3.192 |
Token | both |
Token ID | 1111 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
viral | +0.385 |
Tik | +0.384 |
stride | +0.374 |
Kik | +0.353 |
characteristic | +0.349 |
Neg logit contributions | |
mble | -0.685 |
nesday | -0.679 |
pher | -0.624 |
cream | -0.578 |
displayText | -0.551 |
Token | the |
Token ID | 262 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
mble | +3.714 |
nesday | +3.645 |
pher | +3.412 |
cream | +3.154 |
displayText | +2.960 |
Neg logit contributions | |
viral | -2.125 |
Tik | -2.123 |
stride | -2.104 |
uni | -1.996 |
Kik | -1.957 |
Token | local |
Token ID | 1957 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
mble | +1.672 |
nesday | +1.644 |
pher | +1.526 |
cream | +1.431 |
displayText | +1.352 |
Neg logit contributions | |
viral | -0.837 |
Tik | -0.831 |
stride | -0.819 |
uni | -0.754 |
Kik | -0.751 |
Token | economy |
Token ID | 3773 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
mble | +2.832 |
nesday | +2.764 |
pher | +2.587 |
cream | +2.362 |
displayText | +2.197 |
Neg logit contributions | |
Tik | -2.007 |
viral | -2.005 |
stride | -1.991 |
Kik | -1.868 |
uni | -1.847 |
Token | and |
Token ID | 290 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
mble | +2.322 |
nesday | +2.321 |
pher | +2.149 |
cream | +2.010 |
displayText | +1.930 |
Neg logit contributions | |
Tik | -1.011 |
viral | -1.011 |
stride | -0.962 |
Kik | -0.940 |
uni | -0.894 |
Token | the |
Token ID | 262 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
mble | +1.027 |
nesday | +1.023 |
pher | +0.938 |
cream | +0.862 |
displayText | +0.825 |
Neg logit contributions | |
Tik | -0.601 |
viral | -0.599 |
stride | -0.581 |
Kik | -0.557 |
characteristic | -0.546 |
Token | - |
Token ID | 12 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
mble | +3.471 |
nesday | +3.424 |
pher | +3.206 |
cream | +2.999 |
displayText | +2.778 |
Neg logit contributions | |
Tik | -1.894 |
viral | -1.851 |
stride | -1.803 |
Kik | -1.728 |
characteristic | -1.660 |
Token | data |
Token ID | 7890 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
Tik | +0.658 |
viral | +0.658 |
stride | +0.641 |
Kik | +0.616 |
characteristic | +0.606 |
Neg logit contributions | |
nesday | -0.738 |
mble | -0.734 |
pher | -0.659 |
cream | -0.604 |
displayText | -0.574 |
Token | units |
Token ID | 4991 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
mble | +4.318 |
nesday | +4.293 |
pher | +3.983 |
cream | +3.708 |
displayText | +3.498 |
Neg logit contributions | |
Tik | -1.868 |
viral | -1.848 |
stride | -1.827 |
uni | -1.675 |
Kik | -1.674 |
Token | , |
Token ID | 11 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
viral | +1.042 |
Tik | +1.038 |
stride | +1.003 |
Kik | +0.955 |
characteristic | +0.942 |
Neg logit contributions | |
nesday | -1.757 |
mble | -1.749 |
pher | -1.582 |
cream | -1.464 |
displayText | -1.419 |
Token | made |
Token ID | 925 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
nesday | +2.942 |
mble | +2.896 |
pher | +2.661 |
cream | +2.436 |
displayText | +2.342 |
Neg logit contributions | |
viral | -1.999 |
Tik | -1.993 |
stride | -1.935 |
Kik | -1.854 |
characteristic | -1.821 |
Token | modifications |
Token ID | 19008 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
nesday | +1.878 |
mble | +1.866 |
pher | +1.687 |
cream | +1.562 |
displayText | +1.502 |
Neg logit contributions | |
Tik | -1.212 |
viral | -1.212 |
stride | -1.179 |
Kik | -1.128 |
uni | -1.115 |
Token | to |
Token ID | 284 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
nesday | +3.893 |
mble | +3.813 |
pher | +3.555 |
cream | +3.256 |
displayText | +3.073 |
Neg logit contributions | |
viral | -2.800 |
Tik | -2.796 |
stride | -2.732 |
Kik | -2.624 |
uni | -2.577 |
Token | improve |
Token ID | 2987 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
nesday | +1.296 |
mble | +1.285 |
pher | +1.175 |
cream | +1.077 |
displayText | +1.030 |
Neg logit contributions | |
Tik | -0.790 |
viral | -0.787 |
stride | -0.756 |
Kik | -0.728 |
characteristic | -0.717 |
Token | the |
Token ID | 262 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
Tik | +1.136 |
viral | +1.135 |
stride | +1.092 |
Kik | +1.040 |
characteristic | +1.020 |
Neg logit contributions | |
nesday | -2.038 |
mble | -2.032 |
pher | -1.852 |
cream | -1.712 |
displayText | -1.654 |
Token | detection |
Token ID | 13326 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
Tik | +0.091 |
viral | +0.091 |
stride | +0.087 |
Kik | +0.083 |
uni | +0.081 |
Neg logit contributions | |
nesday | -0.175 |
mble | -0.174 |
pher | -0.159 |
cream | -0.147 |
displayText | -0.142 |
Token | of |
Token ID | 286 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
nesday | +0.433 |
mble | +0.432 |
pher | +0.398 |
cream | +0.368 |
displayText | +0.354 |
Neg logit contributions | |
Tik | -0.219 |
viral | -0.219 |
stride | -0.209 |
Kik | -0.200 |
uni | -0.197 |
Token | is |
Token ID | 318 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
viral | +0.499 |
Tik | +0.497 |
stride | +0.479 |
Kik | +0.454 |
characteristic | +0.446 |
Neg logit contributions | |
nesday | -0.956 |
mble | -0.951 |
pher | -0.868 |
cream | -0.806 |
displayText | -0.781 |
Token | possible |
Token ID | 1744 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
viral | +0.392 |
Tik | +0.391 |
stride | +0.379 |
Kik | +0.361 |
characteristic | +0.355 |
Neg logit contributions | |
nesday | -0.612 |
mble | -0.609 |
pher | -0.552 |
cream | -0.509 |
displayText | -0.491 |
Token | to |
Token ID | 284 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
viral | +0.537 |
Tik | +0.535 |
stride | +0.518 |
Kik | +0.494 |
characteristic | +0.486 |
Neg logit contributions | |
nesday | -0.830 |
mble | -0.826 |
pher | -0.749 |
cream | -0.690 |
displayText | -0.665 |
Token | live |
Token ID | 2107 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
viral | +0.316 |
Tik | +0.315 |
stride | +0.304 |
Kik | +0.289 |
characteristic | +0.283 |
Neg logit contributions | |
nesday | -0.580 |
mble | -0.577 |
pher | -0.527 |
cream | -0.487 |
displayText | -0.472 |
Token | only |
Token ID | 691 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
nesday | +1.122 |
mble | +1.119 |
pher | +1.028 |
cream | +0.949 |
displayText | +0.908 |
Neg logit contributions | |
Tik | -0.608 |
viral | -0.602 |
stride | -0.581 |
Kik | -0.555 |
uni | -0.545 |
Token | as |
Token ID | 355 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
nesday | +2.614 |
mble | +2.600 |
pher | +2.393 |
cream | +2.195 |
displayText | +2.097 |
Neg logit contributions | |
Tik | -1.542 |
viral | -1.524 |
stride | -1.488 |
Kik | -1.413 |
uni | -1.401 |
Token | long |
Token ID | 890 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
nesday | +3.878 |
mble | +3.875 |
pher | +3.607 |
cream | +3.244 |
displayText | +3.073 |
Neg logit contributions | |
Tik | -2.437 |
viral | -2.419 |
stride | -2.362 |
Kik | -2.236 |
uni | -2.228 |
Token | as |
Token ID | 355 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
viral | +2.239 |
Tik | +2.198 |
stride | +2.131 |
characteristic | +1.974 |
Kik | +1.961 |
Neg logit contributions | |
nesday | -5.870 |
mble | -5.826 |
pher | -5.308 |
cream | -4.983 |
displayText | -4.918 |
Token | life |
Token ID | 1204 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
viral | +1.021 |
Tik | +1.017 |
stride | +0.977 |
Kik | +0.920 |
characteristic | +0.903 |
Neg logit contributions | |
nesday | -2.228 |
mble | -2.217 |
pher | -2.031 |
cream | -1.892 |
displayText | -1.837 |
Token | intox |
Token ID | 21275 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
nesday | +1.163 |
mble | +1.159 |
pher | +1.071 |
cream | +0.981 |
displayText | +0.939 |
Neg logit contributions | |
Tik | -0.692 |
viral | -0.687 |
stride | -0.661 |
Kik | -0.631 |
uni | -0.619 |
Token | icates |
Token ID | 16856 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
nesday | +1.383 |
mble | +1.330 |
pher | +1.054 |
cream | +0.814 |
displayText | +0.631 |
Neg logit contributions | |
viral | -4.480 |
Tik | -4.457 |
stride | -4.421 |
Kik | -4.278 |
characteristic | -4.223 |
Token | relatively |
Token ID | 5365 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
viral | +0.487 |
Tik | +0.484 |
stride | +0.468 |
Kik | +0.443 |
characteristic | +0.438 |
Neg logit contributions | |
nesday | -0.889 |
mble | -0.884 |
pher | -0.804 |
cream | -0.746 |
displayText | -0.724 |
Token | low |
Token ID | 1877 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
nesday | +0.727 |
mble | +0.725 |
pher | +0.672 |
cream | +0.628 |
displayText | +0.606 |
Neg logit contributions | |
Tik | -0.271 |
viral | -0.269 |
stride | -0.258 |
Kik | -0.241 |
uni | -0.234 |
Token | , |
Token ID | 11 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
viral | +0.764 |
Tik | +0.761 |
stride | +0.734 |
Kik | +0.697 |
characteristic | +0.684 |
Neg logit contributions | |
nesday | -1.415 |
mble | -1.408 |
pher | -1.284 |
cream | -1.190 |
displayText | -1.152 |
Token | but |
Token ID | 475 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
viral | +0.745 |
Tik | +0.742 |
stride | +0.715 |
Kik | +0.676 |
characteristic | +0.663 |
Neg logit contributions | |
nesday | -1.475 |
mble | -1.468 |
pher | -1.342 |
cream | -1.246 |
displayText | -1.207 |
Token | nonetheless |
Token ID | 19018 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
viral | +1.016 |
Tik | +1.012 |
stride | +0.977 |
Kik | +0.925 |
characteristic | +0.908 |
Neg logit contributions | |
nesday | -1.934 |
mble | -1.926 |
pher | -1.757 |
cream | -1.630 |
displayText | -1.578 |
Token | a |
Token ID | 257 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
viral | +2.854 |
Tik | +2.802 |
stride | +2.714 |
characteristic | +2.594 |
Kik | +2.555 |
Neg logit contributions | |
nesday | -5.597 |
mble | -5.500 |
pher | -4.968 |
cream | -4.666 |
displayText | -4.581 |
Token | problem |
Token ID | 1917 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
viral | +1.979 |
Tik | +1.957 |
stride | +1.905 |
characteristic | +1.805 |
Kik | +1.804 |
Neg logit contributions | |
nesday | -3.286 |
mble | -3.252 |
pher | -2.951 |
cream | -2.730 |
displayText | -2.659 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
viral | +0.606 |
Tik | +0.605 |
stride | +0.583 |
Kik | +0.555 |
uni | +0.538 |
Neg logit contributions | |
nesday | -1.138 |
mble | -1.136 |
pher | -1.040 |
cream | -0.963 |
displayText | -0.929 |
Token | The |
Token ID | 383 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Tik | +0.669 |
viral | +0.665 |
stride | +0.641 |
Kik | +0.617 |
characteristic | +0.602 |
Neg logit contributions | |
nesday | -1.058 |
mble | -1.052 |
pher | -0.947 |
cream | -0.874 |
displayText | -0.848 |
Token | education |
Token ID | 3707 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
nesday | +0.954 |
mble | +0.952 |
pher | +0.867 |
cream | +0.807 |
displayText | +0.775 |
Neg logit contributions | |
viral | -0.508 |
Tik | -0.505 |
stride | -0.490 |
Kik | -0.463 |
characteristic | -0.451 |
Token | sector |
Token ID | 6567 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
mble | +2.463 |
nesday | +2.448 |
pher | +2.243 |
cream | +2.064 |
displayText | +1.973 |
Neg logit contributions | |
Tik | -1.472 |
viral | -1.471 |
stride | -1.413 |
Kik | -1.366 |
uni | -1.332 |
Token | the |
Token ID | 262 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
viral | +1.041 |
Tik | +1.033 |
stride | +0.996 |
Kik | +0.942 |
characteristic | +0.925 |
Neg logit contributions | |
nesday | -2.095 |
mble | -2.084 |
pher | -1.905 |
cream | -1.771 |
displayText | -1.720 |
Token | use |
Token ID | 779 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
viral | +0.743 |
Tik | +0.741 |
stride | +0.711 |
Kik | +0.669 |
characteristic | +0.656 |
Neg logit contributions | |
nesday | -1.654 |
mble | -1.647 |
pher | -1.509 |
cream | -1.406 |
displayText | -1.364 |
Token | of |
Token ID | 286 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
nesday | +0.952 |
mble | +0.947 |
pher | +0.864 |
cream | +0.803 |
displayText | +0.780 |
Neg logit contributions | |
viral | -0.472 |
Tik | -0.469 |
stride | -0.453 |
Kik | -0.428 |
characteristic | -0.420 |
Token | an |
Token ID | 281 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
nesday | +1.463 |
mble | +1.460 |
pher | +1.337 |
cream | +1.242 |
displayText | +1.191 |
Neg logit contributions | |
Tik | -0.707 |
viral | -0.687 |
stride | -0.674 |
Kik | -0.629 |
uni | -0.625 |
Token | annotation |
Token ID | 23025 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
viral | +0.246 |
Tik | +0.244 |
stride | +0.234 |
Kik | +0.220 |
characteristic | +0.215 |
Neg logit contributions | |
nesday | -0.597 |
mble | -0.594 |
pher | -0.546 |
cream | -0.510 |
displayText | -0.495 |
Token | automatically |
Token ID | 6338 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
viral | +1.164 |
Tik | +1.159 |
stride | +1.110 |
Kik | +1.039 |
characteristic | +1.017 |
Neg logit contributions | |
nesday | -2.859 |
mble | -2.847 |
pher | -2.616 |
cream | -2.444 |
displayText | -2.373 |
Token | added |
Token ID | 2087 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
viral | +0.918 |
Tik | +0.913 |
stride | +0.875 |
Kik | +0.819 |
characteristic | +0.804 |
Neg logit contributions | |
nesday | -2.240 |
mble | -2.229 |
pher | -2.047 |
cream | -1.912 |
displayText | -1.858 |
Token | to |
Token ID | 284 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
nesday | +0.723 |
mble | +0.717 |
pher | +0.645 |
cream | +0.594 |
displayText | +0.569 |
Neg logit contributions | |
Tik | -0.516 |
viral | -0.513 |
stride | -0.501 |
Kik | -0.480 |
characteristic | -0.469 |
Token | all |
Token ID | 477 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
Tik | +0.568 |
viral | +0.566 |
stride | +0.548 |
Kik | +0.517 |
characteristic | +0.509 |
Neg logit contributions | |
nesday | -1.081 |
mble | -1.077 |
pher | -0.981 |
cream | -0.911 |
displayText | -0.878 |
Token | of |
Token ID | 286 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
viral | +1.989 |
Tik | +1.958 |
stride | +1.884 |
Kik | +1.789 |
characteristic | +1.753 |
Neg logit contributions | |
nesday | -4.147 |
mble | -4.124 |
pher | -3.777 |
cream | -3.513 |
displayText | -3.424 |
Token | their |
Token ID | 511 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
nesday | +0.960 |
mble | +0.954 |
pher | +0.864 |
cream | +0.798 |
displayText | +0.766 |
Neg logit contributions | |
Tik | -0.556 |
viral | -0.554 |
stride | -0.541 |
Kik | -0.508 |
uni | -0.505 |
Token | aboard |
Token ID | 15500 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
nesday | +3.804 |
mble | +3.799 |
pher | +3.539 |
cream | +3.259 |
displayText | +3.101 |
Neg logit contributions | |
Tik | -1.847 |
viral | -1.797 |
stride | -1.729 |
uni | -1.661 |
Kik | -1.645 |
Token | in |
Token ID | 287 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
viral | +0.276 |
Tik | +0.274 |
stride | +0.265 |
Kik | +0.251 |
characteristic | +0.246 |
Neg logit contributions | |
nesday | -0.514 |
mble | -0.512 |
pher | -0.465 |
cream | -0.431 |
displayText | -0.419 |
Token | 2006 |
Token ID | 4793 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
nesday | +0.410 |
mble | +0.407 |
pher | +0.373 |
cream | +0.345 |
displayText | +0.334 |
Neg logit contributions | |
viral | -0.209 |
Tik | -0.208 |
stride | -0.200 |
Kik | -0.190 |
uni | -0.188 |
Token | — |
Token ID | 960 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
nesday | +1.740 |
mble | +1.731 |
pher | +1.588 |
cream | +1.466 |
displayText | +1.419 |
Neg logit contributions | |
Tik | -0.968 |
viral | -0.965 |
stride | -0.931 |
Kik | -0.889 |
characteristic | -0.872 |
Token | once |
Token ID | 27078 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
viral | +0.461 |
Tik | +0.459 |
stride | +0.447 |
Kik | +0.429 |
characteristic | +0.424 |
Neg logit contributions | |
nesday | -0.553 |
mble | -0.550 |
pher | -0.489 |
cream | -0.445 |
displayText | -0.430 |
Token | again |
Token ID | 757 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
mble | +5.469 |
nesday | +5.410 |
pher | +5.032 |
cream | +4.503 |
displayText | +4.299 |
Neg logit contributions | |
Tik | -3.856 |
viral | -3.834 |
stride | -3.726 |
uni | -3.571 |
Kik | -3.567 |
Token | , |
Token ID | 11 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
viral | +0.367 |
Tik | +0.366 |
stride | +0.354 |
Kik | +0.337 |
characteristic | +0.331 |
Neg logit contributions | |
nesday | -0.616 |
mble | -0.613 |
pher | -0.558 |
cream | -0.515 |
displayText | -0.498 |
Token | in |
Token ID | 287 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
viral | +0.251 |
Tik | +0.250 |
stride | +0.241 |
Kik | +0.229 |
characteristic | +0.225 |
Neg logit contributions | |
nesday | -0.473 |
mble | -0.471 |
pher | -0.430 |
cream | -0.398 |
displayText | -0.386 |
Token | a |
Token ID | 257 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
nesday | +0.133 |
mble | +0.133 |
pher | +0.121 |
cream | +0.111 |
displayText | +0.107 |
Neg logit contributions | |
viral | -0.082 |
Tik | -0.082 |
stride | -0.079 |
Kik | -0.076 |
characteristic | -0.074 |
Token | time |
Token ID | 640 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
nesday | +0.574 |
mble | +0.572 |
pher | +0.523 |
cream | +0.484 |
displayText | +0.465 |
Neg logit contributions | |
Tik | -0.309 |
viral | -0.307 |
stride | -0.295 |
Kik | -0.282 |
uni | -0.276 |
Token | of |
Token ID | 286 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
nesday | +0.146 |
mble | +0.145 |
pher | +0.133 |
cream | +0.123 |
displayText | +0.119 |
Neg logit contributions | |
Tik | -0.078 |
viral | -0.078 |
stride | -0.075 |
Kik | -0.072 |
characteristic | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
viral | +0.063 |
Tik | +0.063 |
stride | +0.061 |
Kik | +0.057 |
characteristic | +0.056 |
Neg logit contributions | |
nesday | -0.129 |
mble | -0.127 |
pher | -0.117 |
cream | -0.109 |
displayText | -0.105 |
Token | B |
Token ID | 347 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
nesday | +1.164 |
mble | +1.151 |
pher | +1.065 |
cream | +0.985 |
displayText | +0.957 |
Neg logit contributions | |
viral | -0.616 |
Tik | -0.605 |
stride | -0.598 |
Kik | -0.556 |
characteristic | -0.553 |
Token | illed |
Token ID | 2967 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
viral | +2.097 |
Tik | +2.093 |
stride | +2.030 |
Kik | +1.938 |
characteristic | +1.915 |
Neg logit contributions | |
nesday | -2.776 |
mble | -2.765 |
pher | -2.477 |
cream | -2.273 |
displayText | -2.190 |
Token | as |
Token ID | 355 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
nesday | +4.626 |
mble | +4.578 |
pher | +4.244 |
cream | +3.873 |
displayText | +3.813 |
Neg logit contributions | |
viral | -2.375 |
Tik | -2.336 |
stride | -2.302 |
Kik | -2.195 |
uni | -2.144 |
Token | an |
Token ID | 281 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
nesday | +4.321 |
mble | +4.314 |
pher | +3.936 |
cream | +3.544 |
displayText | +3.468 |
Neg logit contributions | |
viral | -2.868 |
Tik | -2.839 |
stride | -2.753 |
Kik | -2.658 |
uni | -2.613 |
Token | effort |
Token ID | 3626 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
nesday | +1.248 |
mble | +1.245 |
pher | +1.141 |
cream | +1.063 |
displayText | +1.037 |
Neg logit contributions | |
viral | -0.540 |
Tik | -0.540 |
stride | -0.513 |
Kik | -0.487 |
characteristic | -0.473 |
Token | that |
Token ID | 326 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
viral | +0.630 |
Tik | +0.630 |
stride | +0.611 |
Kik | +0.586 |
characteristic | +0.576 |
Neg logit contributions | |
nesday | -0.845 |
mble | -0.838 |
pher | -0.755 |
cream | -0.690 |
displayText | -0.665 |
Token | � |
Token ID | 564 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
viral | +0.184 |
Tik | +0.184 |
stride | +0.178 |
Kik | +0.168 |
characteristic | +0.165 |
Neg logit contributions | |
nesday | -0.349 |
mble | -0.347 |
pher | -0.318 |
cream | -0.293 |
displayText | -0.285 |
Token | � |
Token ID | 250 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
viral | +0.608 |
Tik | +0.605 |
stride | +0.588 |
Kik | +0.564 |
characteristic | +0.557 |
Neg logit contributions | |
nesday | -0.777 |
mble | -0.771 |
pher | -0.690 |
cream | -0.630 |
displayText | -0.607 |
Token | inv |
Token ID | 16340 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
viral | +0.689 |
Tik | +0.688 |
stride | +0.666 |
Kik | +0.637 |
characteristic | +0.630 |
Neg logit contributions | |
nesday | -0.942 |
mble | -0.937 |
pher | -0.840 |
cream | -0.771 |
displayText | -0.747 |
Token | igor |
Token ID | 36274 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
nesday | +0.497 |
mble | +0.485 |
pher | +0.417 |
cream | +0.353 |
displayText | +0.332 |
Neg logit contributions | |
viral | -0.840 |
Tik | -0.837 |
stride | -0.823 |
Kik | -0.796 |
characteristic | -0.792 |
Token | . |
Token ID | 13 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
mble | +2.529 |
nesday | +2.514 |
pher | +2.329 |
cream | +2.135 |
displayText | +2.054 |
Neg logit contributions | |
Tik | -1.260 |
viral | -1.244 |
stride | -1.202 |
Kik | -1.130 |
uni | -1.129 |
Token |
|
Token ID | 198 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Tik | +1.109 |
viral | +1.108 |
stride | +1.065 |
Kik | +1.018 |
characteristic | +0.996 |
Neg logit contributions | |
nesday | -1.934 |
mble | -1.925 |
pher | -1.742 |
cream | -1.613 |
displayText | -1.564 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Tik | +1.038 |
viral | +1.031 |
stride | +0.971 |
Kik | +0.924 |
uni | +0.884 |
Neg logit contributions | |
nesday | -3.125 |
mble | -3.119 |
pher | -2.743 |
cream | -2.584 |
displayText | -2.531 |
Token | Her |
Token ID | 9360 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
nesday | +0.796 |
mble | +0.793 |
pher | +0.707 |
cream | +0.640 |
displayText | +0.612 |
Neg logit contributions | |
viral | -0.767 |
Tik | -0.765 |
stride | -0.746 |
Kik | -0.718 |
characteristic | -0.710 |
Token | early |
Token ID | 1903 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
nesday | +1.157 |
mble | +1.155 |
pher | +1.060 |
cream | +0.979 |
displayText | +0.943 |
Neg logit contributions | |
Tik | -0.597 |
viral | -0.591 |
stride | -0.567 |
Kik | -0.544 |
uni | -0.529 |
Token | poems |
Token ID | 31888 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
viral | +1.528 |
Tik | +1.523 |
stride | +1.470 |
Kik | +1.395 |
characteristic | +1.368 |
Neg logit contributions | |
nesday | -2.812 |
mble | -2.800 |
pher | -2.553 |
cream | -2.366 |
displayText | -2.292 |
Token | were |
Token ID | 547 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
viral | +1.045 |
Tik | +1.040 |
stride | +1.011 |
Kik | +0.956 |
characteristic | +0.948 |
Neg logit contributions | |
nesday | -1.753 |
mble | -1.741 |
pher | -1.576 |
cream | -1.459 |
displayText | -1.415 |
Token | all |
Token ID | 477 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
mble | +2.354 |
nesday | +2.349 |
pher | +2.168 |
cream | +1.988 |
displayText | +1.919 |
Neg logit contributions | |
Tik | -1.414 |
viral | -1.397 |
stride | -1.363 |
Kik | -1.298 |
uni | -1.287 |
Token | elbows |
Token ID | 37076 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
mble | +1.635 |
nesday | +1.629 |
pher | +1.490 |
cream | +1.360 |
displayText | +1.305 |
Neg logit contributions | |
Tik | -1.096 |
viral | -1.084 |
stride | -1.061 |
Kik | -1.012 |
uni | -0.997 |
Token | and |
Token ID | 290 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
nesday | +5.468 |
mble | +5.343 |
pher | +5.160 |
cream | +4.718 |
displayText | +4.428 |
Neg logit contributions | |
Tik | -3.142 |
viral | -3.130 |
stride | -3.019 |
Kik | -2.941 |
uni | -2.889 |
Token | knees |
Token ID | 14475 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
nesday | +0.818 |
mble | +0.814 |
pher | +0.745 |
cream | +0.685 |
displayText | +0.653 |
Neg logit contributions | |
Tik | -0.520 |
viral | -0.520 |
stride | -0.499 |
Kik | -0.480 |
uni | -0.473 |
Token | political |
Token ID | 1964 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Tik | +0.037 |
viral | +0.037 |
stride | +0.035 |
Kik | +0.034 |
characteristic | +0.033 |
Neg logit contributions | |
nesday | -0.068 |
mble | -0.068 |
pher | -0.061 |
cream | -0.057 |
displayText | -0.055 |
Token | sm |
Token ID | 895 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
nesday | +1.126 |
mble | +1.120 |
pher | +1.022 |
cream | +0.948 |
displayText | +0.917 |
Neg logit contributions | |
Tik | -0.602 |
viral | -0.601 |
stride | -0.579 |
Kik | -0.551 |
characteristic | -0.538 |
Token | earing |
Token ID | 6648 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
nesday | +5.570 |
mble | +5.513 |
pher | +5.059 |
cream | +4.585 |
umbledore | +4.252 |
Neg logit contributions | |
viral | -4.294 |
Tik | -4.264 |
stride | -4.221 |
squid | -3.962 |
Kik | -3.953 |
Token | of |
Token ID | 286 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
Tik | +0.437 |
viral | +0.435 |
stride | +0.421 |
Kik | +0.401 |
uni | +0.395 |
Neg logit contributions | |
nesday | -0.813 |
mble | -0.807 |
pher | -0.739 |
cream | -0.685 |
displayText | -0.658 |
Token | a |
Token ID | 257 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
nesday | +0.271 |
mble | +0.269 |
pher | +0.244 |
cream | +0.224 |
displayText | +0.216 |
Neg logit contributions | |
viral | -0.171 |
Tik | -0.171 |
stride | -0.167 |
Kik | -0.158 |
uni | -0.156 |
Token | wholly |
Token ID | 18174 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Tik | +0.425 |
viral | +0.420 |
stride | +0.410 |
Kik | +0.387 |
uni | +0.380 |
Neg logit contributions | |
nesday | -0.816 |
mble | -0.811 |
pher | -0.744 |
cream | -0.688 |
displayText | -0.665 |
Token | benevolent |
Token ID | 45599 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
viral | +5.659 |
Tik | +5.342 |
stride | +5.195 |
characteristic | +5.144 |
Kik | +4.911 |
Neg logit contributions | |
nesday | -10.444 |
mble | -10.404 |
pher | -9.382 |
cream | -8.660 |
displayText | -8.413 |
Token | foundation |
Token ID | 8489 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Tik | +0.698 |
viral | +0.698 |
stride | +0.672 |
Kik | +0.637 |
uni | +0.629 |
Neg logit contributions | |
nesday | -1.380 |
mble | -1.377 |
pher | -1.258 |
cream | -1.171 |
displayText | -1.127 |
Token | , |
Token ID | 11 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
nesday | +1.149 |
mble | +1.143 |
pher | +1.056 |
cream | +0.972 |
displayText | +0.929 |
Neg logit contributions | |
Tik | -0.650 |
viral | -0.649 |
stride | -0.624 |
Kik | -0.598 |
uni | -0.592 |
Token | due |
Token ID | 2233 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
viral | +0.250 |
Tik | +0.249 |
stride | +0.241 |
Kik | +0.229 |
uni | +0.225 |
Neg logit contributions | |
nesday | -0.464 |
mble | -0.462 |
pher | -0.424 |
cream | -0.392 |
displayText | -0.378 |
Token | only |
Token ID | 691 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
mble | +5.283 |
nesday | +5.269 |
pher | +4.782 |
cream | +4.353 |
displayText | +4.169 |
Neg logit contributions | |
viral | -4.097 |
Tik | -4.092 |
stride | -3.973 |
Kik | -3.880 |
uni | -3.766 |
Token | bit |
Token ID | 2545 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
viral | +1.579 |
Tik | +1.568 |
stride | +1.527 |
Kik | +1.463 |
characteristic | +1.444 |
Neg logit contributions | |
nesday | -2.080 |
mble | -2.071 |
pher | -1.848 |
cream | -1.695 |
displayText | -1.642 |
Token | co |
Token ID | 1073 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
viral | +0.366 |
Tik | +0.365 |
stride | +0.357 |
Kik | +0.346 |
characteristic | +0.343 |
Neg logit contributions | |
nesday | -0.255 |
mble | -0.253 |
pher | -0.217 |
cream | -0.191 |
displayText | -0.180 |
Token | int |
Token ID | 600 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
viral | +1.481 |
Tik | +1.459 |
stride | +1.437 |
uni | +1.364 |
Kik | +1.358 |
Neg logit contributions | |
mble | -2.206 |
nesday | -2.203 |
pher | -1.957 |
cream | -1.805 |
displayText | -1.778 |
Token | alk |
Token ID | 971 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
viral | +0.588 |
Tik | +0.584 |
stride | +0.558 |
Kik | +0.519 |
characteristic | +0.505 |
Neg logit contributions | |
nesday | -1.710 |
mble | -1.695 |
pher | -1.565 |
cream | -1.463 |
displayText | -1.435 |
Token | . |
Token ID | 13 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
viral | +1.826 |
Tik | +1.801 |
stride | +1.725 |
uni | +1.649 |
Kik | +1.612 |
Neg logit contributions | |
nesday | -4.803 |
mble | -4.776 |
pher | -4.298 |
cream | -4.019 |
displayText | -3.989 |
Token | org |
Token ID | 2398 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
viral | +0.866 |
Tik | +0.845 |
stride | +0.810 |
Kik | +0.779 |
uni | +0.770 |
Neg logit contributions | |
nesday | -1.981 |
mble | -1.952 |
pher | -1.776 |
cream | -1.668 |
displayText | -1.621 |
Token | / |
Token ID | 14 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
viral | +3.930 |
Tik | +3.741 |
stride | +3.549 |
Kik | +3.473 |
search | +3.420 |
Neg logit contributions | |
mble | -9.787 |
nesday | -9.684 |
pher | -8.566 |
displayText | -8.115 |
cream | -8.102 |
Token | index |
Token ID | 9630 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
viral | +0.991 |
Tik | +0.988 |
stride | +0.941 |
Kik | +0.906 |
uni | +0.884 |
Neg logit contributions | |
nesday | -2.230 |
mble | -2.208 |
pher | -2.003 |
cream | -1.876 |
displayText | -1.834 |
Token | . |
Token ID | 13 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
nesday | +3.954 |
mble | +3.934 |
pher | +3.620 |
cream | +3.365 |
displayText | +3.243 |
Neg logit contributions | |
viral | -1.924 |
Tik | -1.917 |
stride | -1.841 |
Kik | -1.736 |
characteristic | -1.709 |
Token | php |
Token ID | 10121 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Tik | +0.145 |
viral | +0.145 |
stride | +0.133 |
Kik | +0.122 |
uni | +0.122 |
Neg logit contributions | |
nesday | -0.590 |
mble | -0.588 |
pher | -0.540 |
cream | -0.511 |
displayText | -0.502 |
Token | ? |
Token ID | 30 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
viral | +5.329 |
Tik | +5.131 |
stride | +4.941 |
uni | +4.932 |
Kik | +4.887 |
Neg logit contributions | |
mble | -9.025 |
nesday | -8.848 |
pher | -7.631 |
displayText | -7.098 |
cream | -7.082 |
Token | appeal |
Token ID | 5198 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
viral | +0.616 |
Tik | +0.614 |
stride | +0.592 |
Kik | +0.562 |
characteristic | +0.551 |
Neg logit contributions | |
nesday | -1.171 |
mble | -1.165 |
pher | -1.065 |
cream | -0.988 |
displayText | -0.955 |
Token | to |
Token ID | 284 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
viral | +1.095 |
Tik | +1.093 |
stride | +1.063 |
Kik | +1.018 |
characteristic | +1.002 |
Neg logit contributions | |
nesday | -1.466 |
mble | -1.458 |
pher | -1.312 |
cream | -1.203 |
displayText | -1.157 |
Token | children |
Token ID | 1751 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
viral | +1.474 |
Tik | +1.468 |
stride | +1.417 |
Kik | +1.342 |
characteristic | +1.320 |
Neg logit contributions | |
nesday | -2.770 |
mble | -2.755 |
pher | -2.511 |
cream | -2.330 |
displayText | -2.259 |
Token | and |
Token ID | 290 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
viral | +0.725 |
Tik | +0.723 |
stride | +0.695 |
Kik | +0.659 |
characteristic | +0.643 |
Neg logit contributions | |
nesday | -1.493 |
mble | -1.486 |
pher | -1.362 |
cream | -1.267 |
displayText | -1.226 |
Token | can |
Token ID | 460 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
Tik | +0.012 |
viral | +0.012 |
stride | +0.012 |
Kik | +0.011 |
characteristic | +0.011 |
Neg logit contributions | |
nesday | -0.022 |
mble | -0.022 |
pher | -0.020 |
cream | -0.019 |
displayText | -0.018 |
Token | stand |
Token ID | 1302 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
nesday | +0.103 |
mble | +0.102 |
pher | +0.093 |
cream | +0.086 |
displayText | +0.082 |
Neg logit contributions | |
viral | -0.068 |
Tik | -0.068 |
stride | -0.065 |
Kik | -0.063 |
characteristic | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
viral | +4.633 |
Tik | +4.514 |
stride | +4.323 |
characteristic | +4.032 |
Hawai | +3.905 |
Neg logit contributions | |
nesday | -8.677 |
mble | -8.557 |
pher | -7.770 |
displayText | -7.196 |
cream | -7.159 |
Token | test |
Token ID | 1332 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
viral | +0.673 |
Tik | +0.671 |
stride | +0.636 |
Kik | +0.592 |
characteristic | +0.574 |
Neg logit contributions | |
nesday | -2.027 |
mble | -2.020 |
pher | -1.864 |
cream | -1.750 |
displayText | -1.701 |
Token | of |
Token ID | 286 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
Tik | +0.800 |
viral | +0.798 |
stride | +0.766 |
Kik | +0.729 |
uni | +0.712 |
Neg logit contributions | |
nesday | -1.527 |
mble | -1.523 |
pher | -1.386 |
cream | -1.291 |
displayText | -1.245 |
Token | time |
Token ID | 640 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
nesday | +2.517 |
mble | +2.478 |
pher | +2.249 |
cream | +2.045 |
displayText | +1.917 |
Neg logit contributions | |
Tik | -1.942 |
viral | -1.917 |
stride | -1.847 |
uni | -1.826 |
Kik | -1.823 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
nesday | +1.449 |
mble | +1.447 |
pher | +1.330 |
cream | +1.241 |
displayText | +1.187 |
Neg logit contributions | |
Tik | -0.761 |
viral | -0.754 |
stride | -0.724 |
Kik | -0.700 |
uni | -0.683 |
Token | $ |
Token ID | 720 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
nesday | +1.913 |
mble | +1.890 |
pher | +1.742 |
cream | +1.614 |
displayText | +1.555 |
Neg logit contributions | |
viral | -1.006 |
Tik | -0.998 |
stride | -0.959 |
Kik | -0.933 |
uni | -0.904 |
Token | ($ |
Token ID | 16763 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
nesday | +0.285 |
mble | +0.285 |
pher | +0.258 |
cream | +0.236 |
displayText | +0.229 |
Neg logit contributions | |
viral | -0.206 |
Tik | -0.206 |
stride | -0.199 |
Kik | -0.193 |
characteristic | -0.188 |
Token | w |
Token ID | 86 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
nesday | +1.275 |
mble | +1.271 |
pher | +1.150 |
cream | +1.053 |
displayText | +1.018 |
Neg logit contributions | |
Tik | -0.959 |
viral | -0.958 |
stride | -0.924 |
Kik | -0.898 |
characteristic | -0.877 |
Token | path |
Token ID | 6978 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
viral | +1.251 |
Tik | +1.236 |
stride | +1.219 |
uni | +1.127 |
characteristic | +1.114 |
Neg logit contributions | |
mble | -3.117 |
nesday | -3.114 |
pher | -2.788 |
cream | -2.616 |
displayText | -2.555 |
Token | )" |
Token ID | 16725 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Tik | +2.150 |
viral | +2.143 |
stride | +2.074 |
Kik | +1.982 |
characteristic | +1.958 |
Neg logit contributions | |
nesday | -3.098 |
mble | -3.074 |
pher | -2.763 |
cream | -2.542 |
displayText | -2.442 |
Token | break |
Token ID | 2270 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
viral | +3.437 |
Tik | +3.422 |
stride | +3.301 |
Kik | +3.129 |
characteristic | +3.083 |
Neg logit contributions | |
nesday | -6.240 |
mble | -6.193 |
pher | -5.593 |
cream | -5.243 |
displayText | -5.038 |
Token | } |
Token ID | 1782 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Tik | +5.901 |
viral | +5.887 |
stride | +5.758 |
Kik | +5.273 |
characteristic | +5.258 |
Neg logit contributions | |
nesday | -12.395 |
mble | -12.204 |
pher | -11.053 |
cream | -10.527 |
displayText | -9.944 |
Token | } |
Token ID | 1782 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
viral | +2.773 |
Tik | +2.763 |
stride | +2.669 |
Kik | +2.512 |
characteristic | +2.489 |
Neg logit contributions | |
nesday | -5.106 |
mble | -5.067 |
pher | -4.592 |
cream | -4.277 |
displayText | -4.129 |
Token | else |
Token ID | 2073 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
viral | +2.585 |
Tik | +2.575 |
stride | +2.488 |
Kik | +2.347 |
characteristic | +2.327 |
Neg logit contributions | |
nesday | -4.577 |
mble | -4.539 |
pher | -4.118 |
cream | -3.824 |
displayText | -3.705 |
Token | { |
Token ID | 1391 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
viral | +1.791 |
Tik | +1.778 |
stride | +1.717 |
Kik | +1.608 |
characteristic | +1.583 |
Neg logit contributions | |
nesday | -3.897 |
mble | -3.860 |
pher | -3.527 |
cream | -3.287 |
displayText | -3.191 |
Token | $ |
Token ID | 720 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
viral | +2.773 |
Tik | +2.768 |
stride | +2.686 |
Kik | +2.567 |
characteristic | +2.539 |
Neg logit contributions | |
nesday | -3.716 |
mble | -3.689 |
pher | -3.301 |
cream | -3.040 |
displayText | -2.919 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Tik | +1.896 |
viral | +1.893 |
stride | +1.809 |
Kik | +1.728 |
characteristic | +1.703 |
Neg logit contributions | |
mble | -3.270 |
nesday | -3.259 |
pher | -2.940 |
cream | -2.734 |
displayText | -2.666 |
Token | also |
Token ID | 635 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
nesday | +0.628 |
mble | +0.623 |
pher | +0.570 |
cream | +0.528 |
displayText | +0.505 |
Neg logit contributions | |
viral | -0.324 |
Tik | -0.322 |
stride | -0.317 |
Kik | -0.294 |
uni | -0.292 |
Token | known |
Token ID | 1900 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
nesday | +0.620 |
mble | +0.616 |
pher | +0.563 |
cream | +0.519 |
displayText | +0.503 |
Neg logit contributions | |
viral | -0.353 |
Tik | -0.352 |
stride | -0.341 |
Kik | -0.324 |
characteristic | -0.318 |
Token | as |
Token ID | 355 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
nesday | +2.935 |
mble | +2.910 |
pher | +2.674 |
cream | +2.489 |
displayText | +2.420 |
Neg logit contributions | |
viral | -1.411 |
Tik | -1.406 |
stride | -1.382 |
Kik | -1.298 |
characteristic | -1.263 |
Token | R |
Token ID | 371 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
nesday | +0.877 |
mble | +0.873 |
pher | +0.796 |
cream | +0.736 |
displayText | +0.710 |
Neg logit contributions | |
viral | -0.463 |
Tik | -0.457 |
stride | -0.451 |
Kik | -0.418 |
characteristic | -0.416 |
Token | ang |
Token ID | 648 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
viral | +1.656 |
Tik | +1.650 |
stride | +1.610 |
Kik | +1.537 |
characteristic | +1.520 |
Neg logit contributions | |
nesday | -2.109 |
mble | -2.098 |
pher | -1.883 |
cream | -1.721 |
displayText | -1.653 |
Token | oon |
Token ID | 2049 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Tik | +4.006 |
viral | +3.890 |
stride | +3.649 |
Kik | +3.608 |
uni | +3.594 |
Neg logit contributions | |
mble | -8.680 |
nesday | -8.639 |
pher | -7.939 |
cream | -7.419 |
displayText | -7.323 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
viral | +1.246 |
Tik | +1.245 |
stride | +1.198 |
Kik | +1.147 |
characteristic | +1.123 |
Neg logit contributions | |
nesday | -2.085 |
mble | -2.076 |
pher | -1.884 |
cream | -1.742 |
displayText | -1.691 |
Token | says |
Token ID | 1139 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
viral | +0.033 |
Tik | +0.033 |
stride | +0.032 |
Kik | +0.031 |
characteristic | +0.030 |
Neg logit contributions | |
nesday | -0.057 |
mble | -0.057 |
pher | -0.052 |
cream | -0.048 |
displayText | -0.046 |
Token | MS |
Token ID | 6579 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
viral | +1.044 |
Tik | +1.042 |
stride | +1.008 |
Kik | +0.952 |
characteristic | +0.936 |
Neg logit contributions | |
nesday | -1.951 |
mble | -1.942 |
pher | -1.771 |
cream | -1.641 |
displayText | -1.585 |
Token | F |
Token ID | 37 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
viral | +2.083 |
Tik | +2.067 |
stride | +1.987 |
Kik | +1.927 |
uni | +1.894 |
Neg logit contributions | |
nesday | -4.541 |
mble | -4.509 |
pher | -3.957 |
cream | -3.705 |
displayText | -3.614 |