Token | i |
Token ID | 72 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
sanction | +2.938 |
Unsure | +2.879 |
cul | +2.805 |
hey | +2.782 |
sch | +2.773 |
Neg logit contributions | |
Tea | -3.778 |
76561 | -3.559 |
abit | -3.481 |
acle | -3.322 |
Oracle | -3.298 |
Token | | |
Token ID | 930 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
sanction | +1.072 |
Unsure | +1.038 |
hey | +1.011 |
cul | +0.999 |
sch | +0.996 |
Neg logit contributions | |
Tea | -1.150 |
abit | -1.067 |
76561 | -1.064 |
acle | -1.014 |
Oracle | -0.996 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
sanction | +1.712 |
Unsure | +1.663 |
hey | +1.603 |
sch | +1.576 |
CSI | +1.565 |
Neg logit contributions | |
Tea | -2.805 |
abit | -2.672 |
76561 | -2.618 |
acle | -2.545 |
Oracle | -2.475 |
Token | 53 |
Token ID | 4310 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
sanction | +0.934 |
Unsure | +0.905 |
hey | +0.872 |
cul | +0.854 |
sch | +0.852 |
Neg logit contributions | |
Tea | -1.640 |
abit | -1.565 |
76561 | -1.538 |
acle | -1.498 |
Oracle | -1.468 |
Token | | |
Token ID | 930 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Tea | +0.073 |
abit | +0.067 |
76561 | +0.066 |
acle | +0.064 |
Oracle | +0.063 |
Neg logit contributions | |
sanction | -0.072 |
Unsure | -0.070 |
hey | -0.068 |
cul | -0.067 |
sch | -0.067 |
Token | | |
Token ID | 930 |
Feature activation | +3.59e+01 |
Pos logit contributions | |
Tea | +0.233 |
abit | +0.216 |
76561 | +0.213 |
acle | +0.206 |
Oracle | +0.202 |
Neg logit contributions | |
sanction | -0.231 |
Unsure | -0.223 |
hey | -0.217 |
cul | -0.215 |
sch | -0.214 |
Token | 9 |
Token ID | 860 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
Tea | +15.326 |
Oracle | +15.318 |
abit | +13.820 |
acle | +13.127 |
Oracle | +12.525 |
Neg logit contributions | |
gr | -22.130 |
akuya | -21.714 |
fw | -21.652 |
riction | -21.514 |
sanction | -20.851 |
Token | | |
Token ID | 930 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
sanction | +0.517 |
Unsure | +0.502 |
hey | +0.489 |
cul | +0.482 |
sch | +0.481 |
Neg logit contributions | |
Tea | -0.539 |
abit | -0.502 |
76561 | -0.495 |
acle | -0.477 |
Oracle | -0.466 |
Token | org |
Token ID | 8745 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
sanction | +4.687 |
Unsure | +4.562 |
hey | +4.536 |
sch | +4.524 |
kinetic | +4.435 |
Neg logit contributions | |
Tea | -4.485 |
abit | -4.129 |
76561 | -4.084 |
acle | -3.775 |
Oracle | -3.651 |
Token | . |
Token ID | 764 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
Tea | +0.171 |
abit | +0.157 |
76561 | +0.155 |
acle | +0.149 |
Oracle | +0.146 |
Neg logit contributions | |
sanction | -0.201 |
Unsure | -0.195 |
hey | -0.190 |
cul | -0.188 |
sch | -0.187 |
Token | cl |
Token ID | 537 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
sanction | +3.008 |
hey | +2.883 |
sch | +2.873 |
kinetic | +2.820 |
Unsure | +2.650 |
Neg logit contributions | |
Tea | -13.939 |
abit | -13.213 |
76561 | -13.175 |
Oracle | -12.309 |
acle | -12.280 |
Token | Irvine |
Token ID | 37277 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
Tea | +0.262 |
abit | +0.244 |
76561 | +0.240 |
acle | +0.233 |
Oracle | +0.229 |
Neg logit contributions | |
sanction | -0.240 |
Unsure | -0.231 |
hey | -0.225 |
cul | -0.222 |
sch | -0.221 |
Token | , |
Token ID | 11 |
Feature activation | +8.44e+00 |
Pos logit contributions | |
Tea | +4.962 |
abit | +4.563 |
Oracle | +4.460 |
acle | +4.401 |
76561 | +4.185 |
Neg logit contributions | |
sanction | -4.936 |
Unsure | -4.759 |
proble | -4.586 |
kinetic | -4.580 |
fw | -4.547 |
Token | California |
Token ID | 3442 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
Tea | +3.974 |
Oracle | +3.560 |
abit | +3.351 |
acle | +3.257 |
Oracle | +3.098 |
Neg logit contributions | |
proble | -8.440 |
sanction | -8.360 |
fw | -8.229 |
Unsure | -8.207 |
opoly | -8.133 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
Tea | +2.747 |
abit | +2.564 |
76561 | +2.460 |
acle | +2.453 |
Oracle | +2.427 |
Neg logit contributions | |
sanction | -2.469 |
Unsure | -2.362 |
hey | -2.280 |
kinetic | -2.265 |
cul | -2.264 |
Token | Hide |
Token ID | 10415 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
Tea | +8.781 |
Oracle | +7.939 |
acle | +7.684 |
abit | +7.375 |
Oracle | +7.148 |
Neg logit contributions | |
sanction | -8.430 |
proble | -8.039 |
kinetic | -7.920 |
riction | -7.708 |
explan | -7.613 |
Token | Caption |
Token ID | 11260 |
Feature activation | +3.41e+01 |
Pos logit contributions | |
sanction | +1.867 |
Unsure | +1.855 |
hey | +1.776 |
cul | +1.744 |
sch | +1.736 |
Neg logit contributions | |
Tea | -3.038 |
abit | -2.899 |
76561 | -2.866 |
acle | -2.728 |
Oracle | -2.654 |
Token | 9 |
Token ID | 860 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
Oracle | +11.623 |
Tea | +11.443 |
acle | +9.801 |
Tea | +9.417 |
Oath | +9.051 |
Neg logit contributions | |
proble | -30.313 |
volunte | -29.268 |
challeng | -29.013 |
subur | -28.849 |
condem | -28.741 |
Token | of |
Token ID | 286 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
Tea | +2.871 |
abit | +2.607 |
76561 | +2.575 |
acle | +2.534 |
Oracle | +2.493 |
Neg logit contributions | |
sanction | -3.041 |
proble | -2.986 |
Unsure | -2.892 |
cul | -2.825 |
kinetic | -2.808 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
sanction | +1.570 |
Unsure | +1.547 |
hey | +1.515 |
sch | +1.485 |
CSI | +1.441 |
Neg logit contributions | |
Tea | -3.654 |
abit | -3.488 |
76561 | -3.449 |
acle | -3.314 |
Oracle | -3.258 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Tea | +6.258 |
Oracle | +5.795 |
acle | +5.664 |
abit | +5.448 |
76561 | +5.391 |
Neg logit contributions | |
proble | -9.227 |
sanction | -8.937 |
condem | -8.562 |
explan | -8.243 |
riction | -8.195 |
Token | : |
Token ID | 25 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
Tea | +1.377 |
abit | +1.258 |
76561 | +1.244 |
acle | +1.214 |
Oracle | +1.188 |
Neg logit contributions | |
sanction | -1.458 |
Unsure | -1.394 |
proble | -1.363 |
hey | -1.357 |
cul | -1.348 |
Token | Northern |
Token ID | 8342 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
sanction | +2.121 |
Unsure | +2.012 |
hey | +1.978 |
sch | +1.961 |
cul | +1.932 |
Neg logit contributions | |
Tea | -2.840 |
abit | -2.660 |
76561 | -2.647 |
acle | -2.542 |
Oracle | -2.453 |
Token | Territory |
Token ID | 25219 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
sanction | +3.263 |
Unsure | +3.069 |
sch | +3.048 |
hey | +2.985 |
cul | +2.962 |
Neg logit contributions | |
Tea | -4.450 |
76561 | -4.208 |
abit | -4.145 |
acle | -3.945 |
Oracle | -3.864 |
Token | , |
Token ID | 11 |
Feature activation | +7.23e+00 |
Pos logit contributions | |
Tea | +5.110 |
abit | +4.777 |
acle | +4.608 |
Oracle | +4.595 |
76561 | +4.559 |
Neg logit contributions | |
sanction | -4.844 |
Unsure | -4.766 |
fw | -4.583 |
hey | -4.565 |
cul | -4.559 |
Token | the |
Token ID | 262 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
Tea | +5.437 |
abit | +5.125 |
acle | +4.982 |
Oracle | +4.979 |
76561 | +4.920 |
Neg logit contributions | |
sanction | -5.068 |
Unsure | -4.979 |
fw | -4.859 |
cul | -4.800 |
hey | -4.795 |
Token | Administrator |
Token ID | 22998 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
Tea | +2.051 |
abit | +1.911 |
76561 | +1.874 |
acle | +1.842 |
Oracle | +1.822 |
Neg logit contributions | |
sanction | -1.889 |
Unsure | -1.837 |
hey | -1.779 |
cul | -1.771 |
fw | -1.745 |
Token | .[ |
Token ID | 3693 |
Feature activation | +3.35e+01 |
Pos logit contributions | |
Tea | +3.179 |
abit | +2.977 |
76561 | +2.888 |
acle | +2.859 |
Oracle | +2.832 |
Neg logit contributions | |
sanction | -2.797 |
Unsure | -2.726 |
hey | -2.660 |
kinetic | -2.606 |
fw | -2.604 |
Token | 199 |
Token ID | 19104 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
Tea | +16.428 |
abit | +15.777 |
76561 | +14.386 |
Oracle | +13.723 |
acle | +13.338 |
Neg logit contributions | |
CSI | -19.087 |
proble | -18.971 |
sanction | -18.606 |
kinetic | -18.334 |
Unsure | -18.291 |
Token | ] |
Token ID | 60 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
Tea | +0.416 |
abit | +0.384 |
76561 | +0.377 |
acle | +0.365 |
Oracle | +0.357 |
Neg logit contributions | |
sanction | -0.449 |
Unsure | -0.435 |
hey | -0.423 |
cul | -0.419 |
sch | -0.417 |
Token | In |
Token ID | 554 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Tea | +6.147 |
Oracle | +5.632 |
abit | +5.598 |
acle | +5.543 |
76561 | +5.533 |
Neg logit contributions | |
sanction | -4.606 |
proble | -4.269 |
kinetic | -4.264 |
cul | -4.238 |
hey | -4.237 |
Token | the |
Token ID | 262 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
Tea | +0.897 |
abit | +0.840 |
76561 | +0.825 |
acle | +0.806 |
Oracle | +0.791 |
Neg logit contributions | |
sanction | -0.727 |
Unsure | -0.705 |
hey | -0.682 |
cul | -0.674 |
sch | -0.667 |
Token | Commonwealth |
Token ID | 17165 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
sanction | +1.788 |
Unsure | +1.694 |
hey | +1.666 |
sch | +1.647 |
cul | +1.625 |
Neg logit contributions | |
Tea | -2.583 |
abit | -2.427 |
76561 | -2.412 |
acle | -2.320 |
Oracle | -2.249 |
Token | ( |
Token ID | 7 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
sanction | +1.887 |
Unsure | +1.861 |
hey | +1.780 |
cul | +1.761 |
sch | +1.741 |
Neg logit contributions | |
Tea | -3.519 |
abit | -3.363 |
76561 | -3.316 |
acle | -3.182 |
Oracle | -3.171 |
Token | cv |
Token ID | 33967 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
sanction | +2.190 |
cul | +2.137 |
Unsure | +2.066 |
win | +2.052 |
fw | +1.970 |
Neg logit contributions | |
Tea | -6.309 |
abit | -5.884 |
76561 | -5.866 |
Oracle | -5.762 |
acle | -5.682 |
Token | 2 |
Token ID | 17 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
Tea | +3.095 |
abit | +2.797 |
76561 | +2.726 |
acle | +2.701 |
Oracle | +2.577 |
Neg logit contributions | |
sanction | -3.910 |
proble | -3.871 |
Unsure | -3.738 |
hey | -3.682 |
kinetic | -3.671 |
Token | . |
Token ID | 13 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
Tea | +0.685 |
abit | +0.637 |
76561 | +0.628 |
acle | +0.612 |
Oracle | +0.599 |
Neg logit contributions | |
sanction | -0.567 |
Unsure | -0.544 |
hey | -0.529 |
cul | -0.523 |
sch | -0.520 |
Token | M |
Token ID | 44 |
Feature activation | +1.94e+01 |
Pos logit contributions | |
Tea | +2.713 |
abit | +2.448 |
76561 | +2.444 |
acle | +2.342 |
Oracle | +2.304 |
Neg logit contributions | |
sanction | -2.893 |
Unsure | -2.769 |
proble | -2.729 |
hey | -2.713 |
sch | -2.683 |
Token | OR |
Token ID | 1581 |
Feature activation | +3.25e+01 |
Pos logit contributions | |
Tea | +7.237 |
Oracle | +6.707 |
acle | +6.396 |
abit | +6.116 |
Oracle | +6.079 |
Neg logit contributions | |
proble | -20.167 |
princ | -18.505 |
subur | -18.388 |
citiz | -18.377 |
condem | -18.207 |
Token | PH |
Token ID | 11909 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
PH | +14.577 |
Tea | +12.042 |
APH | +11.983 |
Oracle | +11.717 |
acle | +10.892 |
Neg logit contributions | |
proble | -28.200 |
subur | -27.696 |
�� | -27.693 |
princ | -26.758 |
volunte | -26.565 |
Token | _ |
Token ID | 62 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
Tea | +4.995 |
abit | +4.458 |
76561 | +4.444 |
acle | +4.405 |
Oracle | +4.248 |
Neg logit contributions | |
proble | -5.107 |
sanction | -5.003 |
Unsure | -4.681 |
kinetic | -4.634 |
condem | -4.568 |
Token | RECT |
Token ID | 23988 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
Tea | +6.858 |
Oracle | +5.798 |
abit | +5.785 |
76561 | +5.689 |
acle | +5.481 |
Neg logit contributions | |
proble | -13.166 |
sanction | -12.636 |
hey | -11.862 |
kinetic | -11.834 |
Unsure | -11.783 |
Token | , |
Token ID | 11 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
Tea | +2.908 |
abit | +2.662 |
76561 | +2.643 |
acle | +2.596 |
Oracle | +2.514 |
Neg logit contributions | |
sanction | -2.722 |
proble | -2.607 |
Unsure | -2.587 |
cul | -2.508 |
kinetic | -2.502 |
Token | ( |
Token ID | 357 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
sanction | +3.359 |
sch | +3.097 |
Unsure | +3.040 |
kinetic | +2.978 |
cul | +2.969 |
Neg logit contributions | |
Tea | -7.565 |
76561 | -7.147 |
abit | -7.105 |
acle | -6.756 |
Oracle | -6.753 |
Token |
|
Token ID | 198 |
Feature activation | +3.16e+01 |
Pos logit contributions | |
sanction | +2.199 |
Unsure | +2.193 |
hey | +2.122 |
sch | +2.066 |
cul | +2.047 |
Neg logit contributions | |
Tea | -3.343 |
abit | -3.201 |
76561 | -3.174 |
acle | -3.012 |
Oracle | -2.943 |
Token | 2003 |
Token ID | 16088 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
Tea | +15.946 |
Oracle | +14.053 |
76561 | +12.212 |
abit | +10.788 |
Oracle | +10.492 |
Neg logit contributions | |
proble | -25.791 |
subur | -24.384 |
sanction | -24.328 |
princ | -24.270 |
condem | -23.054 |
Token | Bernie |
Token ID | 10477 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
sanction | +2.501 |
Unsure | +2.435 |
hey | +2.374 |
sch | +2.352 |
cul | +2.312 |
Neg logit contributions | |
Tea | -2.998 |
abit | -2.831 |
76561 | -2.782 |
acle | -2.656 |
Oracle | -2.547 |
Token | Mac |
Token ID | 4100 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
Tea | +0.253 |
abit | +0.239 |
76561 | +0.236 |
acle | +0.230 |
Oracle | +0.227 |
Neg logit contributions | |
sanction | -0.136 |
Unsure | -0.129 |
hey | -0.124 |
cul | -0.123 |
sch | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
Tea | +9.277 |
abit | +8.357 |
Oracle | +8.141 |
acle | +8.084 |
76561 | +7.860 |
Neg logit contributions | |
sanction | -10.420 |
Unsure | -9.781 |
cul | -9.761 |
opoly | -9.580 |
proble | -9.518 |
Token |
|
Token ID | 198 |
Feature activation | +3.23e+01 |
Pos logit contributions | |
Unsure | +3.433 |
sanction | +3.358 |
hey | +3.323 |
sch | +3.212 |
win | +3.202 |
Neg logit contributions | |
Tea | -5.936 |
abit | -5.759 |
76561 | -5.730 |
acle | -5.366 |
Oracle | -5.224 |
Token | 2003 |
Token ID | 16088 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Tea | +16.505 |
Oracle | +14.799 |
76561 | +12.730 |
abit | +11.165 |
bench | +10.896 |
Neg logit contributions | |
proble | -26.455 |
subur | -25.409 |
princ | -24.862 |
sanction | -24.461 |
condem | -23.457 |
Token | Eric |
Token ID | 7651 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
sanction | +1.310 |
Unsure | +1.272 |
hey | +1.237 |
sch | +1.224 |
cul | +1.215 |
Neg logit contributions | |
Tea | -1.472 |
abit | -1.381 |
76561 | -1.359 |
acle | -1.304 |
Oracle | -1.261 |
Token | McCorm |
Token ID | 42037 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
sanction | +2.334 |
Unsure | +2.265 |
hey | +2.169 |
sch | +2.167 |
cul | +2.132 |
Neg logit contributions | |
Tea | -4.078 |
76561 | -3.840 |
abit | -3.838 |
acle | -3.695 |
Oracle | -3.597 |
Token | ack |
Token ID | 441 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
sanction | +3.316 |
hey | +3.223 |
Unsure | +3.189 |
win | +3.112 |
sch | +3.108 |
Neg logit contributions | |
Tea | -10.974 |
76561 | -10.624 |
Oracle | -10.084 |
abit | -10.059 |
Oracle | -9.935 |
Token |
|
Token ID | 198 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
Tea | +8.548 |
abit | +7.643 |
Oracle | +7.624 |
acle | +7.330 |
Oracle | +7.020 |
Neg logit contributions | |
sanction | -9.691 |
cul | -9.424 |
Unsure | -9.259 |
riction | -9.131 |
opoly | -9.073 |
Token | Matt |
Token ID | 4705 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
sanction | +3.367 |
Unsure | +3.285 |
hey | +3.221 |
sch | +3.192 |
CSI | +3.136 |
Neg logit contributions | |
Tea | -4.171 |
abit | -3.972 |
76561 | -3.888 |
acle | -3.702 |
Oracle | -3.550 |
Token | Le |
Token ID | 1004 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Tea | +0.506 |
abit | +0.476 |
76561 | +0.469 |
acle | +0.457 |
Oracle | +0.448 |
Neg logit contributions | |
sanction | -0.358 |
Unsure | -0.343 |
hey | -0.332 |
cul | -0.329 |
sch | -0.326 |
Token | Bl |
Token ID | 3629 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
Tea | +1.597 |
abit | +1.493 |
76561 | +1.463 |
acle | +1.433 |
Oracle | +1.401 |
Neg logit contributions | |
sanction | -1.224 |
Unsure | -1.179 |
hey | -1.135 |
cul | -1.125 |
kinetic | -1.115 |
Token | anc |
Token ID | 1192 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
sanction | +0.572 |
Unsure | +0.552 |
hey | +0.535 |
cul | +0.531 |
sch | +0.527 |
Neg logit contributions | |
Tea | -0.690 |
abit | -0.642 |
76561 | -0.641 |
acle | -0.615 |
Oracle | -0.607 |
Token |
|
Token ID | 198 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Tea | +7.517 |
abit | +6.838 |
Oracle | +6.563 |
acle | +6.469 |
76561 | +6.376 |
Neg logit contributions | |
sanction | -8.303 |
cul | -7.882 |
Unsure | -7.818 |
opoly | -7.671 |
proble | -7.630 |
Token |
|
Token ID | 198 |
Feature activation | +3.16e+01 |
Pos logit contributions | |
sanction | +2.199 |
Unsure | +2.193 |
hey | +2.122 |
sch | +2.066 |
cul | +2.047 |
Neg logit contributions | |
Tea | -3.343 |
abit | -3.201 |
76561 | -3.174 |
acle | -3.012 |
Oracle | -2.943 |
Token | 2003 |
Token ID | 16088 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
Tea | +15.946 |
Oracle | +14.053 |
76561 | +12.212 |
abit | +10.788 |
Oracle | +10.492 |
Neg logit contributions | |
proble | -25.791 |
subur | -24.384 |
sanction | -24.328 |
princ | -24.270 |
condem | -23.054 |
Token | Bernie |
Token ID | 10477 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
sanction | +2.501 |
Unsure | +2.435 |
hey | +2.374 |
sch | +2.352 |
cul | +2.312 |
Neg logit contributions | |
Tea | -2.998 |
abit | -2.831 |
76561 | -2.782 |
acle | -2.656 |
Oracle | -2.547 |
Token | Mac |
Token ID | 4100 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
Tea | +0.253 |
abit | +0.239 |
76561 | +0.236 |
acle | +0.230 |
Oracle | +0.227 |
Neg logit contributions | |
sanction | -0.136 |
Unsure | -0.129 |
hey | -0.124 |
cul | -0.123 |
sch | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
Tea | +9.277 |
abit | +8.357 |
Oracle | +8.141 |
acle | +8.084 |
76561 | +7.860 |
Neg logit contributions | |
sanction | -10.420 |
Unsure | -9.781 |
cul | -9.761 |
opoly | -9.580 |
proble | -9.518 |
Token |
|
Token ID | 198 |
Feature activation | +3.23e+01 |
Pos logit contributions | |
Unsure | +3.433 |
sanction | +3.358 |
hey | +3.323 |
sch | +3.212 |
win | +3.202 |
Neg logit contributions | |
Tea | -5.936 |
abit | -5.759 |
76561 | -5.730 |
acle | -5.366 |
Oracle | -5.224 |
Token | Le |
Token ID | 1004 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
sanction | +4.509 |
Unsure | +4.443 |
hey | +4.337 |
sch | +4.316 |
CSI | +4.215 |
Neg logit contributions | |
Tea | -7.065 |
abit | -6.766 |
76561 | -6.731 |
acle | -6.286 |
Oracle | -6.150 |
Token | a |
Token ID | 64 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
sanction | +2.050 |
Unsure | +2.013 |
hey | +1.964 |
cul | +1.960 |
sch | +1.927 |
Neg logit contributions | |
Tea | -2.036 |
abit | -1.897 |
76561 | -1.895 |
acle | -1.783 |
Oracle | -1.773 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
sanction | +1.824 |
Unsure | +1.810 |
hey | +1.657 |
CSI | +1.639 |
sch | +1.618 |
Neg logit contributions | |
Tea | -5.157 |
abit | -4.964 |
76561 | -4.894 |
acle | -4.751 |
Oracle | -4.598 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
sanction | +1.414 |
Unsure | +1.387 |
hey | +1.347 |
sch | +1.323 |
cul | +1.306 |
Neg logit contributions | |
Tea | -2.004 |
abit | -1.908 |
76561 | -1.877 |
acle | -1.809 |
Oracle | -1.759 |
Token | The |
Token ID | 383 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
Unsure | +3.178 |
CSI | +2.641 |
Why | +2.557 |
sch | +2.467 |
hey | +2.392 |
Neg logit contributions | |
abit | -13.601 |
Tea | -13.482 |
76561 | -13.176 |
acle | -12.512 |
ethy | -12.317 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +3.16e+01 |
Pos logit contributions | |
sanction | +3.390 |
Unsure | +3.333 |
CSI | +3.227 |
hey | +3.219 |
sch | +3.184 |
Neg logit contributions | |
Tea | -4.157 |
abit | -3.949 |
76561 | -3.879 |
acle | -3.630 |
Oracle | -3.507 |
Token | 9 |
Token ID | 860 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
Oracle | +12.817 |
Tea | +12.622 |
acle | +10.894 |
Tea | +10.742 |
Oath | +10.535 |
Neg logit contributions | |
volunte | -24.284 |
teasp | -23.877 |
subur | -23.875 |
proble | -23.678 |
�� | -23.618 |
Token | of |
Token ID | 286 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
Tea | +3.110 |
abit | +2.832 |
76561 | +2.801 |
acle | +2.752 |
Oracle | +2.706 |
Neg logit contributions | |
sanction | -3.338 |
proble | -3.259 |
Unsure | -3.185 |
cul | -3.125 |
riction | -3.093 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Unsure | +2.423 |
sanction | +2.416 |
hey | +2.384 |
sch | +2.376 |
CSI | +2.251 |
Neg logit contributions | |
Tea | -6.375 |
abit | -6.097 |
76561 | -6.019 |
acle | -5.778 |
Oracle | -5.699 |
Token | Photo |
Token ID | 5555 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Tea | +0.971 |
abit | +0.892 |
76561 | +0.875 |
acle | +0.853 |
Oracle | +0.840 |
Neg logit contributions | |
sanction | -1.144 |
Unsure | -1.095 |
hey | -1.069 |
cul | -1.067 |
sch | -1.060 |
Token | : |
Token ID | 25 |
Feature activation | -7.81e+00 |
Pos logit contributions | |
Tea | +1.270 |
abit | +1.162 |
76561 | +1.151 |
acle | +1.118 |
Oracle | +1.097 |
Neg logit contributions | |
sanction | -1.328 |
Unsure | -1.272 |
hey | -1.238 |
cul | -1.230 |
proble | -1.227 |
Token | eur |
Token ID | 23365 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Tea | +0.135 |
abit | +0.127 |
76561 | +0.125 |
acle | +0.122 |
Oracle | +0.120 |
Neg logit contributions | |
sanction | -0.088 |
Unsure | -0.085 |
hey | -0.082 |
cul | -0.081 |
sch | -0.080 |
Token | " |
Token ID | 1 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
sanction | +1.382 |
Unsure | +1.317 |
hey | +1.272 |
cul | +1.264 |
sch | +1.261 |
Neg logit contributions | |
Tea | -1.909 |
abit | -1.780 |
76561 | -1.777 |
acle | -1.703 |
Oracle | -1.673 |
Token | for |
Token ID | 329 |
Feature activation | +1.83e+01 |
Pos logit contributions | |
sanction | +1.198 |
Unsure | +1.130 |
hey | +1.100 |
sch | +1.087 |
cul | +1.084 |
Neg logit contributions | |
Tea | -1.802 |
abit | -1.690 |
76561 | -1.686 |
acle | -1.617 |
Oracle | -1.582 |
Token | the |
Token ID | 262 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
Tea | +12.314 |
abit | +11.547 |
Oracle | +11.478 |
acle | +11.078 |
76561 | +10.895 |
Neg logit contributions | |
Unsure | -11.332 |
cul | -10.723 |
win | -10.695 |
malink | -10.656 |
proble | -10.612 |
Token | protection |
Token ID | 4800 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Tea | +2.956 |
abit | +2.774 |
76561 | +2.693 |
acle | +2.644 |
Oracle | +2.611 |
Neg logit contributions | |
sanction | -2.526 |
Unsure | -2.510 |
cul | -2.410 |
hey | -2.386 |
fw | -2.357 |
Token | of |
Token ID | 286 |
Feature activation | +3.11e+01 |
Pos logit contributions | |
Tea | +1.100 |
abit | +1.028 |
76561 | +1.009 |
acle | +0.980 |
Oracle | +0.961 |
Neg logit contributions | |
sanction | -1.008 |
Unsure | -0.982 |
hey | -0.948 |
cul | -0.942 |
sch | -0.934 |
Token | free |
Token ID | 1479 |
Feature activation | +1.90e+01 |
Pos logit contributions | |
Tea | +17.630 |
Oracle | +16.664 |
abit | +15.630 |
acle | +15.385 |
Tea | +14.944 |
Neg logit contributions | |
Unsure | -16.049 |
proble | -15.395 |
fw | -15.260 |
win | -15.245 |
riction | -15.044 |
Token | expression |
Token ID | 5408 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
Tea | +10.271 |
Oracle | +9.049 |
acle | +8.846 |
abit | +8.523 |
76561 | +8.243 |
Neg logit contributions | |
Unsure | -15.179 |
proble | -14.241 |
CSI | -13.870 |
malink | -13.743 |
sanction | -13.696 |
Token | , |
Token ID | 11 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
Tea | +2.766 |
abit | +2.590 |
76561 | +2.535 |
acle | +2.466 |
Oracle | +2.437 |
Neg logit contributions | |
sanction | -2.563 |
Unsure | -2.530 |
cul | -2.420 |
hey | -2.415 |
sch | -2.378 |
Token | told |
Token ID | 1297 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
sanction | +2.652 |
Unsure | +2.506 |
hey | +2.466 |
sch | +2.459 |
kinetic | +2.414 |
Neg logit contributions | |
Tea | -3.228 |
abit | -3.004 |
76561 | -2.992 |
acle | -2.862 |
Oracle | -2.769 |
Token | HuffPost |
Token ID | 35130 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
sanction | +4.608 |
Unsure | +4.351 |
hey | +4.246 |
sch | +4.244 |
kinetic | +4.197 |
Neg logit contributions | |
Tea | -5.886 |
76561 | -5.642 |
abit | -5.516 |
acle | -5.287 |
Oracle | -5.115 |
Token | ( |
Token ID | 7 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
sanction | +2.317 |
Unsure | +2.314 |
hey | +2.209 |
win | +2.163 |
cul | +2.157 |
Neg logit contributions | |
Tea | -4.554 |
abit | -4.386 |
76561 | -4.323 |
acle | -4.140 |
Oracle | -4.109 |
Token | cv |
Token ID | 33967 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
cul | +2.816 |
sanction | +2.757 |
win | +2.682 |
Unsure | +2.602 |
fw | +2.537 |
Neg logit contributions | |
Tea | -8.755 |
abit | -8.158 |
76561 | -8.148 |
Oracle | -8.039 |
acle | -7.865 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
Tea | +2.131 |
abit | +1.950 |
76561 | +1.907 |
acle | +1.874 |
Oracle | +1.800 |
Neg logit contributions | |
sanction | -2.508 |
proble | -2.411 |
Unsure | -2.404 |
hey | -2.361 |
kinetic | -2.345 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
sanction | +2.322 |
Unsure | +2.291 |
hey | +2.195 |
cul | +2.164 |
sch | +2.155 |
Neg logit contributions | |
Tea | -3.545 |
abit | -3.384 |
76561 | -3.349 |
acle | -3.195 |
Oracle | -3.146 |
Token | M |
Token ID | 44 |
Feature activation | +1.89e+01 |
Pos logit contributions | |
Tea | +1.561 |
abit | +1.429 |
76561 | +1.417 |
acle | +1.365 |
Oracle | +1.340 |
Neg logit contributions | |
sanction | -1.548 |
Unsure | -1.484 |
hey | -1.452 |
sch | -1.434 |
kinetic | -1.427 |
Token | OR |
Token ID | 1581 |
Feature activation | +3.08e+01 |
Pos logit contributions | |
Tea | +7.348 |
Oracle | +6.799 |
acle | +6.312 |
Oracle | +6.220 |
abit | +6.043 |
Neg logit contributions | |
proble | -19.683 |
princ | -18.243 |
subur | -18.027 |
citiz | -17.831 |
condem | -17.769 |
Token | PH |
Token ID | 11909 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
PH | +13.147 |
Tea | +10.545 |
Oracle | +10.376 |
APH | +10.070 |
acle | +9.315 |
Neg logit contributions | |
proble | -28.874 |
subur | -28.173 |
�� | -28.041 |
princ | -27.388 |
volunte | -27.220 |
Token | _ |
Token ID | 62 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Tea | +0.398 |
abit | +0.372 |
76561 | +0.368 |
acle | +0.358 |
Oracle | +0.350 |
Neg logit contributions | |
sanction | -0.303 |
Unsure | -0.291 |
hey | -0.282 |
cul | -0.279 |
sch | -0.277 |
Token | RECT |
Token ID | 23988 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Tea | +4.717 |
abit | +3.884 |
Oracle | +3.824 |
76561 | +3.764 |
Oracle | +3.588 |
Neg logit contributions | |
proble | -10.597 |
sanction | -10.330 |
kinetic | -9.812 |
hey | -9.740 |
Unsure | -9.727 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
sanction | +0.287 |
Unsure | +0.277 |
hey | +0.268 |
cul | +0.264 |
sch | +0.264 |
Neg logit contributions | |
Tea | -0.370 |
abit | -0.347 |
76561 | -0.342 |
acle | -0.331 |
Oracle | -0.325 |
Token | ( |
Token ID | 357 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
sanction | +3.901 |
Unsure | +3.790 |
sch | +3.627 |
hey | +3.568 |
CSI | +3.566 |
Neg logit contributions | |
Tea | -11.616 |
abit | -11.169 |
76561 | -11.007 |
acle | -10.456 |
ethy | -10.294 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
Tea | +2.894 |
abit | +2.647 |
76561 | +2.564 |
acle | +2.468 |
Oracle | +2.440 |
Neg logit contributions | |
sanction | -4.259 |
Unsure | -4.156 |
hey | -4.060 |
cul | -4.043 |
fw | -4.001 |
Token | 98 |
Token ID | 4089 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
sanction | +2.267 |
Unsure | +2.155 |
cul | +2.073 |
hey | +2.070 |
win | +2.062 |
Neg logit contributions | |
Tea | -3.586 |
abit | -3.440 |
76561 | -3.421 |
acle | -3.293 |
Oracle | -3.236 |
Token | ] |
Token ID | 60 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
Tea | +4.819 |
abit | +4.414 |
acle | +4.175 |
Oracle | +4.108 |
76561 | +4.108 |
Neg logit contributions | |
sanction | -5.973 |
Unsure | -5.880 |
cul | -5.679 |
hey | -5.673 |
kinetic | -5.614 |
Token | Sporting |
Token ID | 31790 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
sanction | +2.538 |
Unsure | +2.427 |
hey | +2.375 |
sch | +2.358 |
CSI | +2.343 |
Neg logit contributions | |
Tea | -3.501 |
abit | -3.268 |
76561 | -3.238 |
acle | -3.127 |
Oracle | -3.000 |
Token | News |
Token ID | 3000 |
Feature activation | +6.72e+00 |
Pos logit contributions | |
sanction | +1.243 |
Unsure | +1.201 |
hey | +1.156 |
cul | +1.145 |
sch | +1.144 |
Neg logit contributions | |
Tea | -1.594 |
abit | -1.493 |
76561 | -1.492 |
acle | -1.438 |
Oracle | -1.392 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +3.02e+01 |
Pos logit contributions | |
Tea | +4.088 |
abit | +3.749 |
76561 | +3.578 |
acle | +3.487 |
Oracle | +3.481 |
Neg logit contributions | |
sanction | -5.982 |
Unsure | -5.802 |
hey | -5.623 |
cul | -5.603 |
fw | -5.555 |
Token | 99 |
Token ID | 2079 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Tea | +16.470 |
abit | +13.668 |
Oracle | +12.985 |
acle | +12.393 |
Oracle | +12.228 |
Neg logit contributions | |
kinetic | -18.544 |
sanction | -18.518 |
Kub | -18.399 |
proble | -18.198 |
CSI | -18.127 |
Token | ] |
Token ID | 60 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
Tea | +2.134 |
abit | +1.960 |
76561 | +1.894 |
acle | +1.867 |
Oracle | +1.830 |
Neg logit contributions | |
sanction | -2.394 |
Unsure | -2.333 |
hey | -2.260 |
cul | -2.248 |
kinetic | -2.226 |
Token | SB |
Token ID | 18056 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
sanction | +2.071 |
Unsure | +1.986 |
hey | +1.939 |
sch | +1.919 |
CSI | +1.907 |
Neg logit contributions | |
Tea | -2.841 |
abit | -2.657 |
76561 | -2.632 |
acle | -2.542 |
Oracle | -2.447 |
Token | Nation |
Token ID | 8741 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
sanction | +1.405 |
Unsure | +1.362 |
hey | +1.314 |
cul | +1.301 |
sch | +1.296 |
Neg logit contributions | |
Tea | -1.695 |
abit | -1.587 |
76561 | -1.579 |
acle | -1.522 |
Oracle | -1.481 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +2.19e+01 |
Pos logit contributions | |
Tea | +4.706 |
abit | +4.269 |
76561 | +4.007 |
Oracle | +3.925 |
acle | +3.918 |
Neg logit contributions | |
sanction | -8.582 |
Unsure | -8.286 |
cul | -8.107 |
hey | -8.082 |
riction | -7.990 |
Token | s |
Token ID | 264 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
sanction | +0.621 |
Unsure | +0.587 |
hey | +0.563 |
sch | +0.553 |
cul | +0.546 |
Neg logit contributions | |
Tea | -1.466 |
abit | -1.388 |
76561 | -1.379 |
acle | -1.341 |
Oracle | -1.313 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
sanction | +0.596 |
Unsure | +0.578 |
hey | +0.560 |
cul | +0.552 |
sch | +0.550 |
Neg logit contributions | |
Tea | -0.781 |
abit | -0.734 |
76561 | -0.726 |
acle | -0.701 |
Oracle | -0.687 |
Token | t |
Token ID | 83 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Tea | +6.268 |
abit | +5.698 |
76561 | +5.424 |
acle | +5.402 |
Oracle | +5.160 |
Neg logit contributions | |
proble | -9.085 |
sanction | -8.594 |
explan | -8.114 |
condem | -8.056 |
kinetic | -8.044 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
Tea | +0.269 |
abit | +0.251 |
76561 | +0.248 |
acle | +0.241 |
Oracle | +0.236 |
Neg logit contributions | |
sanction | -0.218 |
Unsure | -0.209 |
hey | -0.203 |
cul | -0.201 |
sch | -0.200 |
Token | I |
Token ID | 314 |
Feature activation | +9.74e+00 |
Pos logit contributions | |
Tea | +8.417 |
Oracle | +8.020 |
abit | +7.689 |
acle | +7.641 |
76561 | +7.576 |
Neg logit contributions | |
sanction | -6.661 |
cul | -6.404 |
riction | -6.389 |
Unsure | -6.304 |
opoly | -6.300 |
Token | TA |
Token ID | 5603 |
Feature activation | +3.00e+01 |
Pos logit contributions | |
Tea | +4.920 |
abit | +3.976 |
acle | +3.945 |
76561 | +3.896 |
Oracle | +3.778 |
Neg logit contributions | |
proble | -9.705 |
sanction | -9.681 |
kinetic | -9.333 |
Unsure | -9.238 |
sch | -9.182 |
Token | 9 |
Token ID | 860 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
Tea | +16.747 |
abit | +15.961 |
Oracle | +15.855 |
acle | +14.524 |
Oath | +13.634 |
Neg logit contributions | |
akuya | -16.088 |
sanction | -15.998 |
fw | -15.906 |
gr | -15.241 |
plaus | -15.215 |
Token | Manuel |
Token ID | 25995 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Tea | +10.178 |
Oracle | +9.764 |
abit | +9.219 |
acle | +8.994 |
Oracle | +8.859 |
Neg logit contributions | |
sanction | -8.779 |
proble | -8.489 |
cul | -8.441 |
riction | -8.379 |
fw | -8.282 |
Token | Bel |
Token ID | 3944 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
sanction | +0.318 |
Unsure | +0.309 |
hey | +0.302 |
cul | +0.299 |
sch | +0.299 |
Neg logit contributions | |
Tea | -0.241 |
abit | -0.220 |
76561 | -0.217 |
acle | -0.208 |
Oracle | -0.201 |
Token | lett |
Token ID | 15503 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
Tea | +1.063 |
abit | +0.986 |
76561 | +0.958 |
acle | +0.943 |
Oracle | +0.916 |
Neg logit contributions | |
sanction | -1.101 |
Unsure | -1.061 |
hey | -1.026 |
sch | -1.016 |
CSI | -1.011 |
Token | i |
Token ID | 72 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Tea | +3.142 |
abit | +2.939 |
acle | +2.745 |
Oracle | +2.718 |
76561 | +2.710 |
Neg logit contributions | |
sanction | -3.768 |
Unsure | -3.701 |
cul | -3.523 |
kinetic | -3.523 |
hey | -3.522 |
Token | or |
Token ID | 273 |
Feature activation | +8.32e+00 |
Pos logit contributions | |
Tea | +2.008 |
abit | +1.891 |
acle | +1.789 |
76561 | +1.769 |
Oracle | +1.718 |
Neg logit contributions | |
sanction | -2.351 |
Unsure | -2.277 |
hey | -2.219 |
kinetic | -2.197 |
CSI | -2.185 |
Token | zon |
Token ID | 26361 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
Tea | +6.742 |
abit | +6.679 |
acle | +6.339 |
Oracle | +6.014 |
Oracle | +5.885 |
Neg logit contributions | |
sanction | -5.601 |
Unsure | -5.211 |
proble | -5.198 |
hey | -5.083 |
CSI | -5.026 |
Token | era |
Token ID | 8607 |
Feature activation | +7.34e+00 |
Pos logit contributions | |
Tea | +5.453 |
abit | +5.236 |
acle | +5.072 |
76561 | +4.966 |
Oracle | +4.823 |
Neg logit contributions | |
sanction | -3.800 |
Unsure | -3.538 |
proble | -3.519 |
hey | -3.426 |
kinetic | -3.407 |
Token | - |
Token ID | 12 |
Feature activation | +8.55e+00 |
Pos logit contributions | |
Tea | +5.179 |
abit | +4.839 |
76561 | +4.605 |
acle | +4.565 |
Oracle | +4.559 |
Neg logit contributions | |
sanction | -5.693 |
Unsure | -5.584 |
hey | -5.294 |
cul | -5.292 |
kinetic | -5.284 |
Token | Z |
Token ID | 57 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
Tea | +4.456 |
abit | +3.854 |
76561 | +3.590 |
acle | +3.447 |
Oracle | +3.361 |
Neg logit contributions | |
sanction | -8.434 |
Unsure | -8.186 |
kinetic | -7.941 |
hey | -7.920 |
CSI | -7.917 |
Token | ak |
Token ID | 461 |
Feature activation | +2.99e+01 |
Pos logit contributions | |
Tea | +4.072 |
abit | +3.908 |
acle | +3.744 |
76561 | +3.699 |
Oracle | +3.596 |
Neg logit contributions | |
sanction | -2.873 |
Unsure | -2.707 |
proble | -2.679 |
hey | -2.607 |
CSI | -2.595 |
Token | arp |
Token ID | 5117 |
Feature activation | +2.03e+01 |
Pos logit contributions | |
abit | +11.980 |
acle | +11.275 |
Tea | +9.912 |
Oracle | +9.350 |
arp | +9.057 |
Neg logit contributions | |
proble | -24.840 |
condem | -23.417 |
subur | -23.271 |
citiz | -23.159 |
explan | -23.028 |
Token | at |
Token ID | 265 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
abit | +7.193 |
acle | +6.618 |
Tea | +6.552 |
ethy | +5.560 |
at | +5.300 |
Neg logit contributions | |
proble | -20.528 |
explan | -19.550 |
sanction | -19.541 |
princ | -19.403 |
subur | -19.169 |
Token | ty |
Token ID | 774 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
sanction | +0.118 |
Unsure | +0.114 |
hey | +0.111 |
cul | +0.110 |
sch | +0.109 |
Neg logit contributions | |
Tea | -0.114 |
abit | -0.106 |
76561 | -0.105 |
acle | -0.101 |
Oracle | -0.099 |
Token | a |
Token ID | 64 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
Tea | +2.661 |
abit | +2.468 |
acle | +2.359 |
76561 | +2.328 |
Oracle | +2.216 |
Neg logit contributions | |
sanction | -3.560 |
Unsure | -3.413 |
proble | -3.397 |
hey | -3.328 |
kinetic | -3.314 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Tea | +4.056 |
abit | +3.791 |
76561 | +3.718 |
acle | +3.682 |
Oracle | +3.610 |
Neg logit contributions | |
sanction | -3.753 |
Unsure | -3.721 |
cul | -3.512 |
hey | -3.504 |
kinetic | -3.457 |
Token | While |
Token ID | 3633 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Tea | +2.670 |
abit | +2.450 |
76561 | +2.427 |
acle | +2.355 |
Oracle | +2.307 |
Neg logit contributions | |
sanction | -1.829 |
Unsure | -1.744 |
hey | -1.680 |
kinetic | -1.671 |
sch | -1.663 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Tea | +1.338 |
abit | +1.250 |
76561 | +1.230 |
acle | +1.200 |
Oracle | +1.184 |
Neg logit contributions | |
sanction | -1.078 |
Unsure | -1.046 |
hey | -1.009 |
cul | -1.007 |
sch | -0.992 |
Token | First |
Token ID | 3274 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
Tea | +1.172 |
abit | +1.094 |
76561 | +1.079 |
acle | +1.054 |
Oracle | +1.037 |
Neg logit contributions | |
sanction | -0.886 |
Unsure | -0.858 |
hey | -0.828 |
cul | -0.822 |
sch | -0.811 |
Token | Amendment |
Token ID | 8441 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
Tea | +3.434 |
abit | +3.114 |
acle | +2.916 |
76561 | +2.848 |
Oracle | +2.799 |
Neg logit contributions | |
sanction | -6.709 |
Unsure | -6.533 |
hey | -6.473 |
kinetic | -6.472 |
cul | -6.462 |
Token | right |
Token ID | 826 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
Tea | +0.816 |
abit | +0.765 |
76561 | +0.754 |
acle | +0.733 |
Oracle | +0.722 |
Neg logit contributions | |
sanction | -0.621 |
Unsure | -0.600 |
hey | -0.581 |
cul | -0.577 |
sch | -0.572 |
Token | to |
Token ID | 284 |
Feature activation | +2.97e+01 |
Pos logit contributions | |
Tea | +2.391 |
abit | +2.229 |
76561 | +2.183 |
acle | +2.119 |
Oracle | +2.095 |
Neg logit contributions | |
sanction | -2.238 |
Unsure | -2.197 |
hey | -2.120 |
cul | -2.108 |
CSI | -2.094 |
Token | free |
Token ID | 1479 |
Feature activation | +2.14e+01 |
Pos logit contributions | |
Tea | +16.495 |
Oracle | +14.998 |
abit | +14.528 |
acle | +14.466 |
venge | +13.330 |
Neg logit contributions | |
� | -16.216 |
proble | -16.196 |
fw | -16.132 |
gren | -16.105 |
orno | -15.944 |
Token | expression |
Token ID | 5408 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
Tea | +10.718 |
Oracle | +9.504 |
acle | +8.974 |
abit | +8.453 |
Oracle | +8.376 |
Neg logit contributions | |
Unsure | -16.692 |
proble | -16.562 |
CSI | -15.795 |
� | -15.774 |
win | -15.652 |
Token | is |
Token ID | 318 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
Tea | +0.865 |
abit | +0.811 |
76561 | +0.799 |
acle | +0.779 |
Oracle | +0.766 |
Neg logit contributions | |
sanction | -0.636 |
Unsure | -0.616 |
hey | -0.593 |
cul | -0.590 |
sch | -0.583 |
Token | important |
Token ID | 1593 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Tea | +2.679 |
abit | +2.505 |
76561 | +2.430 |
acle | +2.398 |
Oracle | +2.398 |
Neg logit contributions | |
sanction | -2.284 |
Unsure | -2.238 |
cul | -2.166 |
hey | -2.157 |
CSI | -2.115 |
Token | , |
Token ID | 11 |
Feature activation | +8.49e+00 |
Pos logit contributions | |
sanction | +1.421 |
Unsure | +1.346 |
hey | +1.324 |
sch | +1.300 |
cul | +1.297 |
Neg logit contributions | |
Tea | -1.836 |
abit | -1.711 |
76561 | -1.700 |
acle | -1.640 |
Oracle | -1.599 |
Token | 2003 |
Token ID | 16088 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Tea | +16.505 |
Oracle | +14.799 |
76561 | +12.730 |
abit | +11.165 |
bench | +10.896 |
Neg logit contributions | |
proble | -26.455 |
subur | -25.409 |
princ | -24.862 |
sanction | -24.461 |
condem | -23.457 |
Token | Eric |
Token ID | 7651 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
sanction | +1.310 |
Unsure | +1.272 |
hey | +1.237 |
sch | +1.224 |
cul | +1.215 |
Neg logit contributions | |
Tea | -1.472 |
abit | -1.381 |
76561 | -1.359 |
acle | -1.304 |
Oracle | -1.261 |
Token | McCorm |
Token ID | 42037 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
sanction | +2.334 |
Unsure | +2.265 |
hey | +2.169 |
sch | +2.167 |
cul | +2.132 |
Neg logit contributions | |
Tea | -4.078 |
76561 | -3.840 |
abit | -3.838 |
acle | -3.695 |
Oracle | -3.597 |
Token | ack |
Token ID | 441 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
sanction | +3.316 |
hey | +3.223 |
Unsure | +3.189 |
win | +3.112 |
sch | +3.108 |
Neg logit contributions | |
Tea | -10.974 |
76561 | -10.624 |
Oracle | -10.084 |
abit | -10.059 |
Oracle | -9.935 |
Token |
|
Token ID | 198 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
Tea | +8.548 |
abit | +7.643 |
Oracle | +7.624 |
acle | +7.330 |
Oracle | +7.020 |
Neg logit contributions | |
sanction | -9.691 |
cul | -9.424 |
Unsure | -9.259 |
riction | -9.131 |
opoly | -9.073 |
Token |
|
Token ID | 198 |
Feature activation | +2.97e+01 |
Pos logit contributions | |
sanction | +2.371 |
Unsure | +2.364 |
hey | +2.291 |
sch | +2.232 |
win | +2.202 |
Neg logit contributions | |
Tea | -3.669 |
abit | -3.516 |
76561 | -3.490 |
acle | -3.305 |
Oracle | -3.223 |
Token | 2003 |
Token ID | 16088 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
Tea | +16.006 |
Oracle | +13.976 |
76561 | +12.531 |
abit | +11.566 |
Oracle | +10.946 |
Neg logit contributions | |
proble | -22.412 |
sanction | -22.075 |
subur | -20.824 |
princ | -20.673 |
guts | -20.397 |
Token | Ray |
Token ID | 7760 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
sanction | +1.867 |
Unsure | +1.813 |
hey | +1.765 |
sch | +1.747 |
cul | +1.728 |
Neg logit contributions | |
Tea | -2.175 |
abit | -2.044 |
76561 | -2.016 |
acle | -1.927 |
Oracle | -1.856 |
Token | Rom |
Token ID | 3570 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
sanction | +2.724 |
Unsure | +2.656 |
sch | +2.607 |
hey | +2.565 |
CSI | +2.504 |
Neg logit contributions | |
Tea | -5.325 |
76561 | -5.096 |
abit | -5.089 |
acle | -4.850 |
Oracle | -4.690 |
Token | ano |
Token ID | 5733 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
Tea | +1.957 |
abit | +1.823 |
acle | +1.750 |
76561 | +1.743 |
Oracle | +1.666 |
Neg logit contributions | |
sanction | -2.373 |
Unsure | -2.298 |
hey | -2.233 |
proble | -2.220 |
kinetic | -2.219 |
Token | 2004 |
Token ID | 5472 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Tea | +5.786 |
abit | +5.270 |
Oracle | +5.134 |
acle | +5.040 |
76561 | +5.021 |
Neg logit contributions | |
sanction | -6.520 |
cul | -6.282 |
Unsure | -6.270 |
hey | -6.127 |
opoly | -6.122 |
Token | Tony |
Token ID | 8832 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
sanction | +1.973 |
Unsure | +1.913 |
hey | +1.864 |
sch | +1.840 |
cul | +1.824 |
Neg logit contributions | |
Tea | -2.357 |
abit | -2.221 |
76561 | -2.180 |
acle | -2.097 |
Oracle | -2.027 |
Token | Shal |
Token ID | 47974 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
sanction | +1.505 |
Unsure | +1.446 |
hey | +1.413 |
sch | +1.400 |
cul | +1.392 |
Neg logit contributions | |
Tea | -1.770 |
76561 | -1.652 |
abit | -1.649 |
acle | -1.571 |
Oracle | -1.533 |
Token | h |
Token ID | 71 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
sanction | +1.997 |
Unsure | +1.944 |
hey | +1.903 |
cul | +1.903 |
sch | +1.874 |
Neg logit contributions | |
Tea | -2.672 |
76561 | -2.532 |
abit | -2.475 |
acle | -2.374 |
Oracle | -2.350 |
Token | oub |
Token ID | 12944 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
sanction | +4.401 |
Unsure | +4.376 |
hey | +4.268 |
win | +4.246 |
cul | +4.225 |
Neg logit contributions | |
Tea | -4.801 |
76561 | -4.536 |
abit | -4.213 |
Oracle | -4.088 |
acle | -4.072 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Tea | +9.187 |
abit | +8.427 |
Oracle | +8.251 |
acle | +8.032 |
76561 | +7.621 |
Neg logit contributions | |
sanction | -10.171 |
cul | -9.597 |
proble | -9.509 |
Unsure | -9.508 |
fw | -9.387 |
Token |
|
Token ID | 198 |
Feature activation | +2.96e+01 |
Pos logit contributions | |
sanction | +1.124 |
Unsure | +1.099 |
hey | +1.065 |
sch | +1.044 |
cul | +1.042 |
Neg logit contributions | |
Tea | -1.531 |
abit | -1.449 |
76561 | -1.434 |
acle | -1.375 |
Oracle | -1.345 |
Token | 2003 |
Token ID | 16088 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
Tea | +15.012 |
Oracle | +13.061 |
76561 | +11.582 |
abit | +11.240 |
Oracle | +10.258 |
Neg logit contributions | |
proble | -22.657 |
sanction | -22.510 |
CSI | -21.286 |
guts | -21.053 |
princ | -20.687 |
Token | Larry |
Token ID | 13633 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
sanction | +2.165 |
Unsure | +2.100 |
hey | +2.050 |
sch | +2.025 |
cul | +2.002 |
Neg logit contributions | |
Tea | -2.645 |
abit | -2.498 |
76561 | -2.452 |
acle | -2.353 |
Oracle | -2.267 |
Token | David |
Token ID | 3271 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
sanction | +3.732 |
Unsure | +3.664 |
hey | +3.646 |
sch | +3.589 |
cul | +3.514 |
Neg logit contributions | |
Tea | -5.126 |
76561 | -5.034 |
abit | -4.790 |
acle | -4.499 |
Oracle | -4.388 |
Token |
|
Token ID | 198 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Tea | +4.824 |
abit | +4.425 |
76561 | +4.253 |
Oracle | +4.247 |
acle | +4.231 |
Neg logit contributions | |
sanction | -4.668 |
Unsure | -4.470 |
cul | -4.427 |
fw | -4.325 |
hey | -4.321 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e+01 |
Pos logit contributions | |
sanction | +1.169 |
Unsure | +1.144 |
hey | +1.108 |
sch | +1.086 |
cul | +1.084 |
Neg logit contributions | |
Tea | -1.600 |
abit | -1.515 |
76561 | -1.498 |
acle | -1.438 |
Oracle | -1.406 |
Token | ( |
Token ID | 7 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
Tea | +0.796 |
abit | +0.746 |
76561 | +0.737 |
acle | +0.719 |
Oracle | +0.704 |
Neg logit contributions | |
sanction | -0.533 |
Unsure | -0.507 |
hey | -0.492 |
cul | -0.484 |
sch | -0.482 |
Token | cv |
Token ID | 33967 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
sanction | +2.898 |
cul | +2.797 |
Unsure | +2.771 |
win | +2.692 |
sch | +2.679 |
Neg logit contributions | |
Tea | -5.733 |
abit | -5.348 |
76561 | -5.296 |
Oracle | -5.139 |
acle | -5.105 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
Tea | +2.134 |
abit | +1.951 |
76561 | +1.911 |
acle | +1.875 |
Oracle | +1.799 |
Neg logit contributions | |
sanction | -2.498 |
Unsure | -2.395 |
proble | -2.384 |
hey | -2.349 |
kinetic | -2.328 |
Token | . |
Token ID | 13 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
sanction | +0.154 |
Unsure | +0.149 |
hey | +0.144 |
cul | +0.142 |
sch | +0.142 |
Neg logit contributions | |
Tea | -0.196 |
abit | -0.183 |
76561 | -0.181 |
acle | -0.175 |
Oracle | -0.172 |
Token | M |
Token ID | 44 |
Feature activation | +1.75e+01 |
Pos logit contributions | |
sanction | +2.194 |
Unsure | +2.111 |
cul | +2.055 |
hey | +2.044 |
sch | +2.030 |
Neg logit contributions | |
Tea | -2.627 |
abit | -2.465 |
76561 | -2.434 |
acle | -2.345 |
Oracle | -2.308 |
Token | OR |
Token ID | 1581 |
Feature activation | +2.96e+01 |
Pos logit contributions | |
Tea | +7.763 |
acle | +6.804 |
abit | +6.736 |
Oracle | +6.732 |
Oracle | +6.495 |
Neg logit contributions | |
proble | -16.822 |
sanction | -15.701 |
princ | -15.310 |
condem | -15.213 |
citiz | -15.182 |
Token | PH |
Token ID | 11909 |
Feature activation | +9.31e+00 |
Pos logit contributions | |
PH | +13.425 |
Tea | +11.726 |
Oracle | +11.292 |
APH | +11.275 |
acle | +10.967 |
Neg logit contributions | |
proble | -26.314 |
�� | -25.777 |
subur | -25.774 |
princ | -25.216 |
volunte | -25.024 |
Token | _ |
Token ID | 62 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
Tea | +6.675 |
acle | +5.861 |
abit | +5.850 |
76561 | +5.847 |
Oracle | +5.646 |
Neg logit contributions | |
proble | -7.754 |
sanction | -7.351 |
condem | -6.914 |
kinetic | -6.821 |
Unsure | -6.782 |
Token | RECT |
Token ID | 23988 |
Feature activation | +8.98e+00 |
Pos logit contributions | |
Tea | +2.970 |
abit | +2.749 |
76561 | +2.717 |
acle | +2.662 |
Oracle | +2.592 |
Neg logit contributions | |
sanction | -2.406 |
Unsure | -2.301 |
hey | -2.244 |
kinetic | -2.212 |
sch | -2.182 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
Tea | +6.599 |
abit | +6.137 |
acle | +6.023 |
76561 | +5.879 |
Oracle | +5.578 |
Neg logit contributions | |
sanction | -6.623 |
Unsure | -6.409 |
hey | -6.161 |
kinetic | -6.123 |
cul | -6.093 |
Token | ( |
Token ID | 357 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
sanction | +5.973 |
sch | +5.706 |
Unsure | +5.506 |
CSI | +5.411 |
cul | +5.410 |
Neg logit contributions | |
Tea | -10.718 |
76561 | -10.051 |
abit | -9.888 |
Oracle | -9.476 |
Oracle | -9.233 |
Token |
|
Token ID | 198 |
Feature activation | +2.96e+01 |
Pos logit contributions | |
sanction | +1.124 |
Unsure | +1.099 |
hey | +1.065 |
sch | +1.044 |
cul | +1.042 |
Neg logit contributions | |
Tea | -1.531 |
abit | -1.449 |
76561 | -1.434 |
acle | -1.375 |
Oracle | -1.345 |
Token | 2003 |
Token ID | 16088 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
Tea | +15.012 |
Oracle | +13.061 |
76561 | +11.582 |
abit | +11.240 |
Oracle | +10.258 |
Neg logit contributions | |
proble | -22.657 |
sanction | -22.510 |
CSI | -21.286 |
guts | -21.053 |
princ | -20.687 |
Token | Larry |
Token ID | 13633 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
sanction | +2.165 |
Unsure | +2.100 |
hey | +2.050 |
sch | +2.025 |
cul | +2.002 |
Neg logit contributions | |
Tea | -2.645 |
abit | -2.498 |
76561 | -2.452 |
acle | -2.353 |
Oracle | -2.267 |
Token | David |
Token ID | 3271 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
sanction | +3.732 |
Unsure | +3.664 |
hey | +3.646 |
sch | +3.589 |
cul | +3.514 |
Neg logit contributions | |
Tea | -5.126 |
76561 | -5.034 |
abit | -4.790 |
acle | -4.499 |
Oracle | -4.388 |
Token |
|
Token ID | 198 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Tea | +4.824 |
abit | +4.425 |
76561 | +4.253 |
Oracle | +4.247 |
acle | +4.231 |
Neg logit contributions | |
sanction | -4.668 |
Unsure | -4.470 |
cul | -4.427 |
fw | -4.325 |
hey | -4.321 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e+01 |
Pos logit contributions | |
sanction | +1.169 |
Unsure | +1.144 |
hey | +1.108 |
sch | +1.086 |
cul | +1.084 |
Neg logit contributions | |
Tea | -1.600 |
abit | -1.515 |
76561 | -1.498 |
acle | -1.438 |
Oracle | -1.406 |
Token | 2003 |
Token ID | 16088 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
Tea | +15.494 |
Oracle | +13.526 |
76561 | +12.151 |
abit | +11.457 |
Oracle | +10.773 |
Neg logit contributions | |
proble | -22.002 |
sanction | -21.961 |
CSI | -20.577 |
guts | -20.473 |
subur | -20.160 |
Token | Matt |
Token ID | 4705 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
sanction | +3.367 |
Unsure | +3.285 |
hey | +3.221 |
sch | +3.192 |
CSI | +3.136 |
Neg logit contributions | |
Tea | -4.171 |
abit | -3.972 |
76561 | -3.888 |
acle | -3.702 |
Oracle | -3.550 |
Token | Le |
Token ID | 1004 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Tea | +0.506 |
abit | +0.476 |
76561 | +0.469 |
acle | +0.457 |
Oracle | +0.448 |
Neg logit contributions | |
sanction | -0.358 |
Unsure | -0.343 |
hey | -0.332 |
cul | -0.329 |
sch | -0.326 |
Token | Bl |
Token ID | 3629 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
Tea | +1.597 |
abit | +1.493 |
76561 | +1.463 |
acle | +1.433 |
Oracle | +1.401 |
Neg logit contributions | |
sanction | -1.224 |
Unsure | -1.179 |
hey | -1.135 |
cul | -1.125 |
kinetic | -1.115 |
Token | anc |
Token ID | 1192 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
sanction | +0.572 |
Unsure | +0.552 |
hey | +0.535 |
cul | +0.531 |
sch | +0.527 |
Neg logit contributions | |
Tea | -0.690 |
abit | -0.642 |
76561 | -0.641 |
acle | -0.615 |
Oracle | -0.607 |
Token | 3 |
Token ID | 513 |
Feature activation | +7.71e+00 |
Pos logit contributions | |
Tea | +13.343 |
Oracle | +12.262 |
abit | +12.230 |
76561 | +12.184 |
acle | +11.670 |
Neg logit contributions | |
sanction | -12.462 |
riction | -11.928 |
fw | -11.687 |
к | -11.470 |
cul | -11.469 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
Tea | +5.605 |
abit | +5.184 |
76561 | +5.090 |
Oracle | +5.035 |
acle | +5.031 |
Neg logit contributions | |
sanction | -5.812 |
Unsure | -5.580 |
riction | -5.454 |
cul | -5.446 |
fw | -5.387 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
Tea | +9.764 |
abit | +9.485 |
76561 | +9.388 |
Oracle | +9.345 |
acle | +9.165 |
Neg logit contributions | |
sanction | -9.723 |
Unsure | -9.429 |
riction | -9.056 |
fw | -8.969 |
CSI | -8.883 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
sanction | +7.280 |
Unsure | +7.239 |
hey | +7.223 |
cul | +7.130 |
kinetic | +7.043 |
Neg logit contributions | |
Tea | -12.952 |
abit | -12.328 |
76561 | -11.884 |
ethy | -11.262 |
Oracle | -11.138 |
Token | 7 |
Token ID | 767 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
Tea | +8.296 |
76561 | +7.966 |
acle | +7.766 |
Oracle | +7.747 |
abit | +7.742 |
Neg logit contributions | |
sanction | -8.833 |
Unsure | -8.537 |
riction | -8.399 |
fw | -8.184 |
opoly | -8.107 |
Token | 8 |
Token ID | 807 |
Feature activation | +2.94e+01 |
Pos logit contributions | |
Tea | +3.284 |
abit | +3.091 |
76561 | +3.047 |
acle | +3.009 |
Oracle | +2.954 |
Neg logit contributions | |
sanction | -2.174 |
Unsure | -2.107 |
hey | -1.995 |
cul | -1.984 |
riction | -1.971 |
Token | 9 |
Token ID | 860 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
Tea | +17.870 |
Oracle | +17.142 |
abit | +17.016 |
acle | +16.212 |
76561 | +16.131 |
Neg logit contributions | |
fw | -14.643 |
sanction | -14.529 |
Unsure | -14.453 |
akuya | -14.259 |
riction | -14.036 |
Token | 10 |
Token ID | 838 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
Tea | +3.097 |
abit | +2.929 |
76561 | +2.893 |
acle | +2.850 |
Oracle | +2.805 |
Neg logit contributions | |
sanction | -1.815 |
Unsure | -1.731 |
cul | -1.623 |
hey | -1.618 |
sch | -1.599 |
Token | 11 |
Token ID | 1367 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
sanction | +0.426 |
Unsure | +0.407 |
hey | +0.391 |
cul | +0.384 |
sch | +0.382 |
Neg logit contributions | |
Tea | -0.855 |
abit | -0.809 |
76561 | -0.800 |
acle | -0.779 |
Oracle | -0.764 |
Token | 12 |
Token ID | 1105 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
sanction | +2.096 |
Unsure | +1.992 |
hey | +1.951 |
cul | +1.907 |
sch | +1.904 |
Neg logit contributions | |
Tea | -4.715 |
76561 | -4.458 |
abit | -4.435 |
acle | -4.221 |
Oracle | -4.146 |
Token | 13 |
Token ID | 1511 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Tea | +11.057 |
Oracle | +10.179 |
abit | +10.147 |
76561 | +10.062 |
acle | +9.985 |
Neg logit contributions | |
sanction | -9.753 |
riction | -9.416 |
� | -9.271 |
Unsure | -9.232 |
fw | -9.229 |
Token | not |
Token ID | 407 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
Tea | +7.532 |
abit | +7.090 |
Oracle | +6.871 |
76561 | +6.791 |
acle | +6.785 |
Neg logit contributions | |
Unsure | -6.049 |
sanction | -5.928 |
cul | -5.910 |
fw | -5.871 |
opoly | -5.732 |
Token | reciproc |
Token ID | 36564 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
Tea | +6.076 |
abit | +5.648 |
76561 | +5.564 |
acle | +5.543 |
Oracle | +5.500 |
Neg logit contributions | |
Unsure | -4.583 |
sanction | -4.560 |
cul | -4.451 |
fw | -4.397 |
hey | -4.385 |
Token | ated |
Token ID | 515 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
Tea | +3.490 |
abit | +3.302 |
acle | +3.148 |
76561 | +3.104 |
Oracle | +2.912 |
Neg logit contributions | |
sanction | -5.615 |
Unsure | -5.450 |
hey | -5.369 |
CSI | -5.252 |
sch | -5.251 |
Token | are |
Token ID | 389 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
Tea | +3.954 |
abit | +3.693 |
76561 | +3.598 |
acle | +3.558 |
Oracle | +3.500 |
Neg logit contributions | |
sanction | -3.446 |
Unsure | -3.427 |
cul | -3.314 |
hey | -3.309 |
CSI | -3.265 |
Token | withdrawn |
Token ID | 23019 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
Tea | +3.806 |
abit | +3.564 |
76561 | +3.450 |
acle | +3.417 |
Oracle | +3.390 |
Neg logit contributions | |
sanction | -3.070 |
Unsure | -3.069 |
cul | -2.978 |
hey | -2.932 |
opoly | -2.908 |
Token | ."[ |
Token ID | 18161 |
Feature activation | +2.93e+01 |
Pos logit contributions | |
Tea | +3.410 |
abit | +3.195 |
76561 | +3.087 |
acle | +3.038 |
Oracle | +2.991 |
Neg logit contributions | |
sanction | -3.341 |
Unsure | -3.306 |
cul | -3.190 |
hey | -3.190 |
CSI | -3.165 |
Token | 43 |
Token ID | 3559 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
Tea | +13.403 |
abit | +11.617 |
Oracle | +11.201 |
Oracle | +11.085 |
acle | +10.526 |
Neg logit contributions | |
proble | -20.198 |
CSI | -19.890 |
opoly | -19.546 |
riction | -19.516 |
Unsure | -19.514 |
Token | ] |
Token ID | 60 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
sanction | +0.542 |
Unsure | +0.525 |
hey | +0.511 |
cul | +0.505 |
sch | +0.504 |
Neg logit contributions | |
Tea | -0.564 |
abit | -0.525 |
76561 | -0.520 |
acle | -0.500 |
Oracle | -0.490 |
Token |
|
Token ID | 198 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
Unsure | +3.521 |
sanction | +3.466 |
hey | +3.309 |
CSI | +3.251 |
sch | +3.231 |
Neg logit contributions | |
Tea | -5.513 |
abit | -5.369 |
76561 | -5.211 |
acle | -5.000 |
Oracle | -4.848 |
Token |
|
Token ID | 198 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Tea | +0.434 |
abit | +0.404 |
76561 | +0.398 |
acle | +0.387 |
Oracle | +0.380 |
Neg logit contributions | |
sanction | -0.359 |
Unsure | -0.345 |
hey | -0.335 |
cul | -0.332 |
sch | -0.330 |
Token | Syrian |
Token ID | 42747 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
sanction | +1.158 |
Unsure | +1.119 |
hey | +1.081 |
cul | +1.075 |
sch | +1.060 |
Neg logit contributions | |
Tea | -1.692 |
abit | -1.616 |
76561 | -1.588 |
acle | -1.551 |
Oracle | -1.527 |
Token | for |
Token ID | 329 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
Tea | +7.551 |
abit | +6.888 |
acle | +6.802 |
Oracle | +6.755 |
76561 | +6.611 |
Neg logit contributions | |
Unsure | -7.443 |
sanction | -7.429 |
proble | -7.113 |
fw | -7.098 |
cul | -7.013 |
Token | South |
Token ID | 2520 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
Tea | +11.098 |
Oracle | +10.414 |
abit | +10.220 |
acle | +9.959 |
76561 | +9.804 |
Neg logit contributions | |
sanction | -9.563 |
Unsure | -9.122 |
fw | -9.034 |
malink | -8.996 |
opoly | -8.989 |
Token | Surrey |
Token ID | 38805 |
Feature activation | +2.36e+01 |
Pos logit contributions | |
Tea | +6.670 |
abit | +6.021 |
Oracle | +5.773 |
76561 | +5.609 |
acle | +5.598 |
Neg logit contributions | |
sanction | -10.422 |
Unsure | -9.976 |
kinetic | -9.933 |
hey | -9.724 |
fw | -9.663 |
Token | — |
Token ID | 960 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
Tea | +15.640 |
Oracle | +14.005 |
acle | +13.962 |
abit | +13.942 |
76561 | +13.582 |
Neg logit contributions | |
Unsure | -13.197 |
sanction | -13.126 |
fw | -12.802 |
proble | -12.534 |
kinetic | -12.338 |
Token | White |
Token ID | 12256 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
Tea | +5.897 |
abit | +5.286 |
76561 | +5.255 |
acle | +5.073 |
Oracle | +4.984 |
Neg logit contributions | |
sanction | -4.392 |
Unsure | -4.178 |
kinetic | -3.996 |
hey | -3.970 |
sch | -3.948 |
Token | Rock |
Token ID | 4631 |
Feature activation | +2.90e+01 |
Pos logit contributions | |
Tea | +3.797 |
abit | +3.501 |
acle | +3.404 |
76561 | +3.393 |
Oracle | +3.379 |
Neg logit contributions | |
sanction | -3.887 |
proble | -3.664 |
Unsure | -3.649 |
cul | -3.633 |
kinetic | -3.580 |
Token | , |
Token ID | 11 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
Tea | +17.615 |
abit | +15.888 |
acle | +15.731 |
Oracle | +15.305 |
76561 | +15.209 |
Neg logit contributions | |
Unsure | -15.060 |
sanction | -14.733 |
fw | -14.488 |
proble | -14.411 |
kinetic | -14.038 |
Token | says |
Token ID | 1139 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Tea | +4.480 |
abit | +4.177 |
76561 | +4.089 |
acle | +4.027 |
Oracle | +3.973 |
Neg logit contributions | |
sanction | -3.853 |
Unsure | -3.779 |
cul | -3.618 |
fw | -3.605 |
riction | -3.582 |
Token | there |
Token ID | 612 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
Tea | +7.640 |
abit | +6.960 |
acle | +6.776 |
76561 | +6.742 |
Oracle | +6.696 |
Neg logit contributions | |
sanction | -6.907 |
Unsure | -6.693 |
cul | -6.681 |
fw | -6.623 |
opoly | -6.533 |
Token | 's |
Token ID | 338 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
Tea | +2.596 |
abit | +2.418 |
76561 | +2.374 |
acle | +2.328 |
Oracle | +2.285 |
Neg logit contributions | |
sanction | -1.966 |
Unsure | -1.902 |
hey | -1.829 |
cul | -1.823 |
kinetic | -1.809 |
Token | a |
Token ID | 257 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
Tea | +2.782 |
abit | +2.590 |
76561 | +2.554 |
acle | +2.492 |
Oracle | +2.470 |
Neg logit contributions | |
sanction | -1.914 |
Unsure | -1.862 |
cul | -1.792 |
hey | -1.783 |
opoly | -1.750 |
Token | x |
Token ID | 2124 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Unsure | +3.901 |
sch | +3.728 |
hey | +3.713 |
sanction | +3.691 |
CSI | +3.596 |
Neg logit contributions | |
Tea | -10.373 |
abit | -10.130 |
76561 | -9.997 |
acle | -9.468 |
ethy | -9.288 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
sanction | +0.910 |
Unsure | +0.884 |
hey | +0.857 |
cul | +0.843 |
sch | +0.842 |
Neg logit contributions | |
Tea | -1.223 |
abit | -1.153 |
76561 | -1.141 |
acle | -1.099 |
Oracle | -1.077 |
Token | x |
Token ID | 87 |
Feature activation | -8.35e+00 |
Pos logit contributions | |
Unsure | +2.646 |
sanction | +2.593 |
win | +2.565 |
cul | +2.527 |
hey | +2.512 |
Neg logit contributions | |
Tea | -4.866 |
abit | -4.634 |
76561 | -4.617 |
acle | -4.408 |
Oracle | -4.389 |
Token | . |
Token ID | 13 |
Feature activation | -2.13e+01 |
Pos logit contributions | |
Unsure | +4.244 |
win | +4.093 |
sanction | +4.084 |
hey | +4.079 |
sch | +3.989 |
Neg logit contributions | |
Tea | -7.897 |
abit | -7.679 |
76561 | -7.635 |
acle | -7.151 |
Oracle | -7.032 |
Token | x |
Token ID | 87 |
Feature activation | -3.28e+01 |
Pos logit contributions | |
win | +8.127 |
gr | +6.847 |
sign | +6.799 |
Unsure | +6.763 |
cul | +6.755 |
Neg logit contributions | |
��� | -21.126 |
Tea | -19.878 |
fortun | -19.404 |
abit | -19.231 |
Oracle | -18.965 |
Token | . |
Token ID | 13 |
Feature activation | -4.06e+01 |
Pos logit contributions | |
win | +11.426 |
sch | +9.991 |
Unsure | +9.716 |
gr | +9.708 |
cul | +9.581 |
Neg logit contributions | |
��� | -28.649 |
fortun | -26.088 |
abit | -25.496 |
Tea | -25.124 |
76561 | -24.368 |
Token | 156 |
Token ID | 21599 |
Feature activation | -7.04e+00 |
Pos logit contributions | |
win | +12.054 |
156 | +11.562 |
cul | +11.533 |
handled | +11.251 |
56 | +10.592 |
Neg logit contributions | |
abit | -30.938 |
��� | -30.284 |
Tea | -29.152 |
fortun | -28.768 |
BART | -28.662 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Unsure | +3.306 |
sanction | +3.275 |
hey | +3.078 |
sch | +3.039 |
CSI | +3.018 |
Neg logit contributions | |
Tea | -7.147 |
abit | -6.881 |
76561 | -6.719 |
acle | -6.511 |
ethy | -6.312 |
Token | 23 |
Token ID | 1954 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
sanction | +0.110 |
Unsure | +0.106 |
hey | +0.102 |
cul | +0.101 |
sch | +0.100 |
Neg logit contributions | |
Tea | -0.180 |
abit | -0.170 |
76561 | -0.168 |
acle | -0.163 |
Oracle | -0.161 |
Token | 688 |
Token ID | 34427 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
sanction | +5.040 |
Unsure | +4.943 |
cul | +4.770 |
hey | +4.767 |
sch | +4.709 |
Neg logit contributions | |
Tea | -7.436 |
abit | -7.039 |
76561 | -6.757 |
acle | -6.640 |
Oracle | -6.533 |
Token | x |
Token ID | 2124 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Unsure | +3.772 |
hey | +3.682 |
sch | +3.643 |
sanction | +3.586 |
CSI | +3.501 |
Neg logit contributions | |
Tea | -10.553 |
abit | -10.294 |
76561 | -10.161 |
acle | -9.699 |
ethy | -9.501 |
Token | x |
Token ID | 2124 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Unsure | +3.582 |
hey | +3.475 |
sanction | +3.426 |
sch | +3.405 |
CSI | +3.338 |
Neg logit contributions | |
Tea | -9.418 |
abit | -9.089 |
76561 | -9.028 |
acle | -8.544 |
ethy | -8.400 |
Token | . |
Token ID | 13 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
sanction | +1.375 |
Unsure | +1.343 |
hey | +1.301 |
sch | +1.277 |
cul | +1.276 |
Neg logit contributions | |
Tea | -1.923 |
abit | -1.821 |
76561 | -1.803 |
acle | -1.729 |
Oracle | -1.693 |
Token | x |
Token ID | 87 |
Feature activation | -6.27e+00 |
Pos logit contributions | |
sanction | +2.068 |
Unsure | +2.066 |
hey | +1.977 |
win | +1.976 |
cul | +1.971 |
Neg logit contributions | |
Tea | -3.631 |
abit | -3.447 |
76561 | -3.421 |
acle | -3.277 |
Oracle | -3.251 |
Token | . |
Token ID | 13 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
Unsure | +3.423 |
sanction | +3.391 |
hey | +3.310 |
win | +3.253 |
sch | +3.228 |
Neg logit contributions | |
Tea | -5.829 |
abit | -5.623 |
76561 | -5.592 |
acle | -5.246 |
Oracle | -5.151 |
Token | x |
Token ID | 87 |
Feature activation | -1.75e+01 |
Pos logit contributions | |
Unsure | +3.476 |
win | +3.445 |
cul | +3.341 |
sanction | +3.289 |
hey | +3.272 |
Neg logit contributions | |
Tea | -7.066 |
abit | -6.778 |
76561 | -6.742 |
Oracle | -6.423 |
acle | -6.398 |
Token | . |
Token ID | 13 |
Feature activation | -3.98e+01 |
Pos logit contributions | |
win | +6.391 |
Unsure | +6.104 |
gr | +5.863 |
sch | +5.819 |
hey | +5.704 |
Neg logit contributions | |
��� | -17.610 |
Tea | -16.782 |
abit | -16.697 |
76561 | -16.373 |
fortun | -16.307 |
Token | 158 |
Token ID | 21273 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
158 | +9.617 |
cul | +9.441 |
win | +9.249 |
soc | +9.077 |
sign | +8.854 |
Neg logit contributions | |
��� | -34.128 |
Tea | -30.768 |
abit | -30.425 |
BART | -30.249 |
Archdemon | -30.072 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Unsure | +2.663 |
sanction | +2.643 |
hey | +2.497 |
sch | +2.437 |
CSI | +2.424 |
Neg logit contributions | |
Tea | -5.676 |
abit | -5.428 |
76561 | -5.318 |
acle | -5.154 |
Oracle | -4.970 |
Token | 95 |
Token ID | 3865 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
sanction | +0.161 |
Unsure | +0.155 |
hey | +0.149 |
cul | +0.147 |
sch | +0.146 |
Neg logit contributions | |
Tea | -0.267 |
abit | -0.251 |
76561 | -0.248 |
acle | -0.242 |
Oracle | -0.238 |
Token | 228 |
Token ID | 23815 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
sanction | +3.509 |
Unsure | +3.437 |
hey | +3.325 |
cul | +3.283 |
sch | +3.260 |
Neg logit contributions | |
Tea | -5.078 |
abit | -4.813 |
76561 | -4.628 |
acle | -4.576 |
Oracle | -4.485 |
Token | x |
Token ID | 2124 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Unsure | +3.887 |
hey | +3.729 |
sch | +3.698 |
sanction | +3.610 |
CSI | +3.565 |
Neg logit contributions | |
Tea | -10.741 |
abit | -10.448 |
76561 | -10.381 |
acle | -9.766 |
ethy | -9.593 |
Token | recommend |
Token ID | 4313 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
sanction | +3.087 |
Unsure | +2.906 |
hey | +2.847 |
sch | +2.843 |
kinetic | +2.801 |
Neg logit contributions | |
Tea | -4.065 |
76561 | -3.817 |
abit | -3.809 |
acle | -3.603 |
Oracle | -3.530 |
Token | improvements |
Token ID | 8561 |
Feature activation | +8.52e+00 |
Pos logit contributions | |
Tea | +0.574 |
abit | +0.536 |
76561 | +0.526 |
acle | +0.514 |
Oracle | +0.504 |
Neg logit contributions | |
sanction | -0.471 |
Unsure | -0.456 |
hey | -0.442 |
cul | -0.438 |
sch | -0.434 |
Token | . |
Token ID | 13 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
Tea | +5.902 |
abit | +5.607 |
Oracle | +5.190 |
acle | +5.183 |
76561 | +5.136 |
Neg logit contributions | |
sanction | -6.385 |
Unsure | -6.266 |
cul | -6.088 |
hey | -6.082 |
opoly | -6.058 |
Token | ... |
Token ID | 2644 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
sanction | +2.046 |
Unsure | +1.998 |
hey | +1.892 |
sch | +1.861 |
CSI | +1.859 |
Neg logit contributions | |
Tea | -3.167 |
abit | -3.005 |
76561 | -2.988 |
acle | -2.887 |
Oracle | -2.767 |
Token | Environmental |
Token ID | 13272 |
Feature activation | -1.74e+01 |
Pos logit contributions | |
sanction | +3.830 |
Unsure | +3.740 |
hey | +3.563 |
CSI | +3.498 |
sch | +3.479 |
Neg logit contributions | |
Tea | -5.405 |
76561 | -5.166 |
abit | -5.141 |
acle | -5.002 |
Oracle | -4.702 |
Token | Grant |
Token ID | 12181 |
Feature activation | -3.35e+01 |
Pos logit contributions | |
sanction | +9.498 |
impact | +8.202 |
Unsure | +8.185 |
Challenge | +8.049 |
gr | +7.983 |
Neg logit contributions | |
Tea | -14.680 |
76561 | -14.469 |
abit | -13.354 |
acle | -12.846 |
ethy | -12.600 |
Token | makers |
Token ID | 6620 |
Feature activation | -7.46e+00 |
Pos logit contributions | |
win | +11.050 |
cul | +10.653 |
gr | +10.452 |
kn | +9.982 |
sign | +9.843 |
Neg logit contributions | |
76561 | -25.763 |
Tea | -25.519 |
��� | -24.054 |
abit | -23.928 |
acle | -23.879 |
Token | Association |
Token ID | 5396 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
sanction | +3.278 |
Unsure | +3.119 |
hey | +2.916 |
sch | +2.861 |
cul | +2.796 |
Neg logit contributions | |
Tea | -7.840 |
76561 | -7.452 |
abit | -7.420 |
acle | -7.138 |
Oracle | -6.930 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
sanction | +4.000 |
Unsure | +3.797 |
hey | +3.696 |
sch | +3.648 |
CSI | +3.566 |
Neg logit contributions | |
Tea | -5.631 |
abit | -5.304 |
76561 | -5.284 |
acle | -5.111 |
Oracle | -4.902 |
Token | Rockefeller |
Token ID | 32764 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
sanction | +7.534 |
Unsure | +7.361 |
hey | +7.114 |
sch | +7.079 |
opoly | +6.970 |
Neg logit contributions | |
Tea | -12.659 |
abit | -12.331 |
76561 | -12.179 |
acle | -11.667 |
ethy | -11.033 |
Token | Family |
Token ID | 7884 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
sanction | +2.028 |
Unsure | +1.970 |
hey | +1.875 |
CSI | +1.819 |
sch | +1.785 |
Neg logit contributions | |
Tea | -6.360 |
76561 | -6.116 |
abit | -6.068 |
acle | -5.892 |
Oracle | -5.633 |
Token | 38 |
Token ID | 2548 |
Feature activation | -9.78e+00 |
Pos logit contributions | |
Tea | +0.190 |
abit | +0.179 |
76561 | +0.177 |
acle | +0.172 |
Oracle | +0.169 |
Neg logit contributions | |
sanction | -0.112 |
Unsure | -0.107 |
hey | -0.103 |
cul | -0.101 |
sch | -0.101 |
Token | x |
Token ID | 2124 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Unsure | +3.901 |
sch | +3.728 |
hey | +3.713 |
sanction | +3.691 |
CSI | +3.596 |
Neg logit contributions | |
Tea | -10.373 |
abit | -10.130 |
76561 | -9.997 |
acle | -9.468 |
ethy | -9.288 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
sanction | +0.910 |
Unsure | +0.884 |
hey | +0.857 |
cul | +0.843 |
sch | +0.842 |
Neg logit contributions | |
Tea | -1.223 |
abit | -1.153 |
76561 | -1.141 |
acle | -1.099 |
Oracle | -1.077 |
Token | x |
Token ID | 87 |
Feature activation | -8.35e+00 |
Pos logit contributions | |
Unsure | +2.646 |
sanction | +2.593 |
win | +2.565 |
cul | +2.527 |
hey | +2.512 |
Neg logit contributions | |
Tea | -4.866 |
abit | -4.634 |
76561 | -4.617 |
acle | -4.408 |
Oracle | -4.389 |
Token | . |
Token ID | 13 |
Feature activation | -2.13e+01 |
Pos logit contributions | |
Unsure | +4.244 |
win | +4.093 |
sanction | +4.084 |
hey | +4.079 |
sch | +3.989 |
Neg logit contributions | |
Tea | -7.897 |
abit | -7.679 |
76561 | -7.635 |
acle | -7.151 |
Oracle | -7.032 |
Token | x |
Token ID | 87 |
Feature activation | -3.28e+01 |
Pos logit contributions | |
win | +8.127 |
gr | +6.847 |
sign | +6.799 |
Unsure | +6.763 |
cul | +6.755 |
Neg logit contributions | |
��� | -21.126 |
Tea | -19.878 |
fortun | -19.404 |
abit | -19.231 |
Oracle | -18.965 |
Token | . |
Token ID | 13 |
Feature activation | -4.06e+01 |
Pos logit contributions | |
win | +11.426 |
sch | +9.991 |
Unsure | +9.716 |
gr | +9.708 |
cul | +9.581 |
Neg logit contributions | |
��� | -28.649 |
fortun | -26.088 |
abit | -25.496 |
Tea | -25.124 |
76561 | -24.368 |
Token | 156 |
Token ID | 21599 |
Feature activation | -7.04e+00 |
Pos logit contributions | |
win | +12.054 |
156 | +11.562 |
cul | +11.533 |
handled | +11.251 |
56 | +10.592 |
Neg logit contributions | |
abit | -30.938 |
��� | -30.284 |
Tea | -29.152 |
fortun | -28.768 |
BART | -28.662 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Unsure | +3.306 |
sanction | +3.275 |
hey | +3.078 |
sch | +3.039 |
CSI | +3.018 |
Neg logit contributions | |
Tea | -7.147 |
abit | -6.881 |
76561 | -6.719 |
acle | -6.511 |
ethy | -6.312 |
Token | 23 |
Token ID | 1954 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
sanction | +0.110 |
Unsure | +0.106 |
hey | +0.102 |
cul | +0.101 |
sch | +0.100 |
Neg logit contributions | |
Tea | -0.180 |
abit | -0.170 |
76561 | -0.168 |
acle | -0.163 |
Oracle | -0.161 |
Token | 688 |
Token ID | 34427 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
sanction | +5.040 |
Unsure | +4.943 |
cul | +4.770 |
hey | +4.767 |
sch | +4.709 |
Neg logit contributions | |
Tea | -7.436 |
abit | -7.039 |
76561 | -6.757 |
acle | -6.640 |
Oracle | -6.533 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.78e+01 |
Pos logit contributions | |
sanction | +3.380 |
Unsure | +3.233 |
hey | +3.158 |
cul | +3.144 |
sch | +3.124 |
Neg logit contributions | |
Tea | -4.965 |
76561 | -4.697 |
abit | -4.628 |
acle | -4.428 |
Oracle | -4.394 |
Token | { |
Token ID | 1391 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
sanction | +8.163 |
hey | +7.932 |
Unsure | +7.893 |
sch | +7.774 |
cul | +7.672 |
Neg logit contributions | |
76561 | -15.850 |
Tea | -15.595 |
abit | -14.758 |
acle | -13.620 |
ethy | -13.580 |
Token | ( |
Token ID | 7 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Tea | +0.990 |
abit | +0.923 |
76561 | +0.914 |
acle | +0.890 |
Oracle | +0.873 |
Neg logit contributions | |
sanction | -0.669 |
Unsure | -0.637 |
hey | -0.616 |
cul | -0.607 |
sch | -0.605 |
Token | 47 |
Token ID | 2857 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
sanction | +1.516 |
Unsure | +1.466 |
hey | +1.422 |
cul | +1.400 |
sch | +1.398 |
Neg logit contributions | |
Tea | -2.001 |
abit | -1.883 |
76561 | -1.847 |
acle | -1.800 |
Oracle | -1.758 |
Token | s |
Token ID | 82 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
sanction | +0.162 |
Unsure | +0.156 |
hey | +0.151 |
cul | +0.149 |
sch | +0.148 |
Neg logit contributions | |
Tea | -0.206 |
abit | -0.193 |
76561 | -0.190 |
acle | -0.184 |
Oracle | -0.181 |
Token | )} |
Token ID | 38165 |
Feature activation | -3.28e+01 |
Pos logit contributions | |
Tea | +5.459 |
abit | +5.015 |
76561 | +5.012 |
acle | +4.908 |
Oracle | +4.844 |
Neg logit contributions | |
sanction | -4.666 |
proble | -4.542 |
Unsure | -4.358 |
kinetic | -4.256 |
sch | -4.212 |
Token | 58 |
Token ID | 7618 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
hey | +12.820 |
Unsure | +12.544 |
sanction | +12.424 |
sch | +12.158 |
Koreans | +12.128 |
Neg logit contributions | |
76561 | -24.998 |
Tea | -23.345 |
abit | -21.999 |
ethy | -19.907 |
acle | -19.837 |
Token | . |
Token ID | 13 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
Tea | +0.411 |
abit | +0.384 |
76561 | +0.378 |
acle | +0.368 |
Oracle | +0.361 |
Neg logit contributions | |
sanction | -0.336 |
Unsure | -0.322 |
hey | -0.313 |
cul | -0.310 |
sch | -0.308 |
Token | Re |
Token ID | 797 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
sanction | +3.948 |
Unsure | +3.900 |
hey | +3.772 |
sch | +3.732 |
cul | +3.609 |
Neg logit contributions | |
Tea | -6.385 |
76561 | -6.138 |
abit | -6.002 |
acle | -5.685 |
Oracle | -5.489 |
Token | 1 |
Token ID | 16 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
Tea | +1.628 |
abit | +1.517 |
76561 | +1.470 |
acle | +1.450 |
Oracle | +1.411 |
Neg logit contributions | |
sanction | -1.513 |
Unsure | -1.456 |
hey | -1.410 |
kinetic | -1.395 |
cul | -1.390 |
Token | { |
Token ID | 1391 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
sanction | +4.093 |
Unsure | +3.959 |
hey | +3.911 |
sch | +3.858 |
cul | +3.840 |
Neg logit contributions | |
Tea | -5.364 |
76561 | -5.158 |
abit | -5.020 |
acle | -4.762 |
Oracle | -4.649 |
Token | , |
Token ID | 11 |
Feature activation | -9.01e+00 |
Pos logit contributions | |
sanction | +6.705 |
Unsure | +6.105 |
hey | +5.969 |
sch | +5.913 |
cul | +5.832 |
Neg logit contributions | |
Tea | -10.641 |
76561 | -10.274 |
abit | -10.095 |
acle | -9.809 |
Oracle | -9.302 |
Token | 000 |
Token ID | 830 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
sanction | +3.598 |
Unsure | +3.224 |
hey | +3.102 |
cul | +3.092 |
sch | +3.075 |
Neg logit contributions | |
Tea | -9.762 |
abit | -9.234 |
76561 | -9.037 |
acle | -8.936 |
Oracle | -8.673 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
sanction | +6.953 |
Unsure | +6.531 |
hey | +6.252 |
sch | +6.226 |
cul | +6.144 |
Neg logit contributions | |
Tea | -9.084 |
76561 | -8.633 |
abit | -8.434 |
acle | -8.177 |
Oracle | -7.713 |
Token | ... |
Token ID | 2644 |
Feature activation | -9.27e+00 |
Pos logit contributions | |
sanction | +5.847 |
Unsure | +5.708 |
hey | +5.320 |
sch | +5.266 |
CSI | +5.234 |
Neg logit contributions | |
Tea | -9.643 |
abit | -9.049 |
76561 | -8.982 |
acle | -8.774 |
ethy | -8.314 |
Token | Environmental |
Token ID | 13272 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
sanction | +5.761 |
Unsure | +5.607 |
hey | +5.346 |
CSI | +5.263 |
sch | +5.214 |
Neg logit contributions | |
Tea | -7.753 |
abit | -7.376 |
76561 | -7.338 |
acle | -7.219 |
Oracle | -6.779 |
Token | Grant |
Token ID | 12181 |
Feature activation | -3.09e+01 |
Pos logit contributions | |
sanction | +7.656 |
Unsure | +6.676 |
gr | +6.446 |
Challenge | +6.379 |
sch | +6.376 |
Neg logit contributions | |
Tea | -13.647 |
76561 | -13.404 |
abit | -12.615 |
acle | -12.199 |
Oracle | -11.822 |
Token | makers |
Token ID | 6620 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
win | +10.587 |
cul | +10.281 |
gr | +9.867 |
sign | +9.508 |
kn | +9.389 |
Neg logit contributions | |
Tea | -24.298 |
76561 | -23.946 |
abit | -22.863 |
��� | -22.753 |
acle | -22.650 |
Token | Association |
Token ID | 5396 |
Feature activation | -7.93e+00 |
Pos logit contributions | |
sanction | +1.971 |
Unsure | +1.875 |
hey | +1.783 |
sch | +1.747 |
cul | +1.728 |
Neg logit contributions | |
Tea | -4.221 |
abit | -3.995 |
76561 | -3.983 |
acle | -3.841 |
Oracle | -3.744 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
sanction | +4.850 |
Unsure | +4.552 |
hey | +4.493 |
sch | +4.426 |
win | +4.305 |
Neg logit contributions | |
Tea | -7.005 |
abit | -6.584 |
76561 | -6.520 |
acle | -6.339 |
Oracle | -6.077 |
Token | Rockefeller |
Token ID | 32764 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
sanction | +6.023 |
Unsure | +5.916 |
hey | +5.692 |
sch | +5.627 |
CSI | +5.522 |
Neg logit contributions | |
Tea | -10.137 |
abit | -9.865 |
76561 | -9.665 |
acle | -9.366 |
ethy | -8.784 |
Token | Family |
Token ID | 7884 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
sanction | +1.982 |
Unsure | +1.935 |
hey | +1.834 |
CSI | +1.780 |
sch | +1.748 |
Neg logit contributions | |
Tea | -6.182 |
76561 | -5.941 |
abit | -5.907 |
acle | -5.733 |
Oracle | -5.483 |
Token | 13 |
Token ID | 1485 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
Tea | +4.185 |
abit | +3.947 |
76561 | +3.854 |
acle | +3.776 |
Oracle | +3.659 |
Neg logit contributions | |
sanction | -2.903 |
Unsure | -2.766 |
hey | -2.681 |
proble | -2.630 |
CSI | -2.622 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
sanction | +0.333 |
Unsure | +0.322 |
hey | +0.312 |
cul | +0.308 |
sch | +0.307 |
Neg logit contributions | |
Tea | -0.431 |
abit | -0.404 |
76561 | -0.399 |
acle | -0.387 |
Oracle | -0.379 |
Token | 5 |
Token ID | 642 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
sanction | +1.467 |
Unsure | +1.418 |
hey | +1.379 |
sch | +1.345 |
cul | +1.330 |
Neg logit contributions | |
Tea | -2.426 |
abit | -2.274 |
76561 | -2.263 |
acle | -2.174 |
Oracle | -2.129 |
Token | )) |
Token ID | 4008 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
Tea | +3.364 |
abit | +3.163 |
76561 | +3.127 |
acle | +3.045 |
Oracle | +2.954 |
Neg logit contributions | |
sanction | -2.525 |
Unsure | -2.413 |
proble | -2.335 |
hey | -2.320 |
kinetic | -2.309 |
Token | sq |
Token ID | 19862 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
sch | +7.457 |
sanction | +7.438 |
Unsure | +6.980 |
hey | +6.798 |
CSI | +6.748 |
Neg logit contributions | |
Tea | -13.643 |
76561 | -12.637 |
abit | -12.293 |
Oracle | -12.174 |
Oracle | -11.688 |
Token | K |
Token ID | 42 |
Feature activation | -3.08e+01 |
Pos logit contributions | |
Unsure | +2.119 |
win | +1.908 |
fw | +1.820 |
� | +1.778 |
sanction | +1.753 |
Neg logit contributions | |
abit | -14.292 |
Tea | -13.935 |
76561 | -13.850 |
Oracle | -13.524 |
acle | -13.397 |
Token | ernel |
Token ID | 7948 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
fw | +12.100 |
win | +12.018 |
cul | +11.697 |
gr | +11.674 |
Unsure | +10.883 |
Neg logit contributions | |
76561 | -22.799 |
��� | -22.407 |
Tea | -22.349 |
Archdemon | -21.648 |
fortun | -21.503 |
Token | = |
Token ID | 796 |
Feature activation | -8.15e+00 |
Pos logit contributions | |
Tea | +1.381 |
abit | +1.272 |
76561 | +1.253 |
acle | +1.224 |
Oracle | +1.188 |
Neg logit contributions | |
sanction | -1.450 |
Unsure | -1.388 |
hey | -1.358 |
cul | -1.345 |
proble | -1.342 |
Token | c |
Token ID | 269 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
sanction | +2.976 |
sch | +2.764 |
hey | +2.654 |
Unsure | +2.630 |
CSI | +2.616 |
Neg logit contributions | |
Tea | -9.349 |
76561 | -8.885 |
abit | -8.865 |
Oracle | -8.389 |
acle | -8.343 |
Token | v |
Token ID | 85 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Tea | +1.906 |
abit | +1.784 |
76561 | +1.742 |
acle | +1.702 |
Oracle | +1.648 |
Neg logit contributions | |
sanction | -1.841 |
Unsure | -1.764 |
hey | -1.733 |
proble | -1.722 |
kinetic | -1.696 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
Tea | +0.831 |
abit | +0.767 |
76561 | +0.752 |
acle | +0.732 |
Oracle | +0.712 |
Neg logit contributions | |
sanction | -0.895 |
Unsure | -0.864 |
hey | -0.843 |
cul | -0.831 |
sch | -0.830 |
Token | ALL |
Token ID | 11096 |
Feature activation | +9.74e+00 |
Pos logit contributions | |
Tea | +5.796 |
abit | +5.373 |
76561 | +5.362 |
Oracle | +5.266 |
acle | +5.213 |
Neg logit contributions | |
sanction | -4.987 |
Unsure | -4.708 |
riction | -4.647 |
cul | -4.618 |
hey | -4.559 |
Token | PERSON |
Token ID | 46740 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
Tea | +5.830 |
abit | +5.350 |
Oracle | +5.326 |
76561 | +5.264 |
acle | +5.070 |
Neg logit contributions | |
sanction | -8.256 |
riction | -7.875 |
Unsure | -7.782 |
hey | -7.781 |
cul | -7.762 |
Token | EL |
Token ID | 3698 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
Tea | +5.439 |
acle | +4.935 |
abit | +4.870 |
76561 | +4.869 |
Oracle | +4.669 |
Neg logit contributions | |
proble | -7.008 |
sanction | -6.914 |
Unsure | -6.443 |
opoly | -6.373 |
condem | -6.324 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +7.24e+00 |
Pos logit contributions | |
Tea | +7.403 |
76561 | +7.020 |
abit | +6.924 |
Oracle | +6.897 |
acle | +6.818 |
Neg logit contributions | |
sanction | -4.906 |
riction | -4.485 |
Unsure | -4.470 |
cul | -4.373 |
hey | -4.358 |
Token | : |
Token ID | 25 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
Tea | +4.790 |
76561 | +4.309 |
abit | +4.191 |
Oracle | +4.183 |
acle | +4.156 |
Neg logit contributions | |
sanction | -6.106 |
proble | -6.027 |
riction | -5.721 |
opoly | -5.707 |
cul | -5.699 |
Token | 0 |
Token ID | 657 |
Feature activation | -3.08e+01 |
Pos logit contributions | |
Unsure | +6.571 |
CSI | +6.306 |
hey | +6.225 |
sanction | +6.193 |
sch | +6.165 |
Neg logit contributions | |
Tea | -13.319 |
abit | -13.012 |
76561 | -11.946 |
acle | -11.895 |
Oracle | -11.561 |
Token | 605 |
Token ID | 32417 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
556 | +12.413 |
sanction | +11.324 |
Unsure | +10.834 |
56 | +10.658 |
sch | +10.565 |
Neg logit contributions | |
Tea | -22.151 |
abit | -22.066 |
76561 | -20.996 |
cous | -20.630 |
acle | -20.457 |
Token | z |
Token ID | 89 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
Tea | +2.671 |
abit | +2.424 |
76561 | +2.312 |
acle | +2.275 |
Oracle | +2.225 |
Neg logit contributions | |
sanction | -4.170 |
Unsure | -3.996 |
proble | -3.930 |
hey | -3.913 |
cul | -3.886 |
Token | BLACK |
Token ID | 31963 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
sanction | +0.234 |
Unsure | +0.225 |
hey | +0.218 |
cul | +0.214 |
sch | +0.214 |
Neg logit contributions | |
Tea | -0.332 |
abit | -0.312 |
76561 | -0.308 |
acle | -0.300 |
Oracle | -0.293 |
Token | FO |
Token ID | 6080 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
Tea | +3.072 |
abit | +2.655 |
76561 | +2.523 |
Oracle | +2.400 |
acle | +2.379 |
Neg logit contributions | |
sanction | -6.728 |
Unsure | -6.515 |
hey | -6.395 |
cul | -6.379 |
sch | -6.322 |
Token | OT |
Token ID | 2394 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
Tea | +4.370 |
76561 | +3.347 |
Oracle | +3.265 |
abit | +3.218 |
Oracle | +3.116 |
Neg logit contributions | |
proble | -13.882 |
sanction | -13.726 |
princ | -13.253 |
condem | -12.974 |
explan | -12.939 |
Token | Agg |
Token ID | 19015 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Unsure | +11.577 |
Why | +11.103 |
CSI | +10.874 |
Unlock | +10.837 |
sch | +10.837 |
Neg logit contributions | |
Tea | -12.689 |
abit | -12.477 |
76561 | -12.183 |
acle | -11.614 |
ethy | -11.170 |
Token | ression |
Token ID | 2234 |
Feature activation | -9.00e+00 |
Pos logit contributions | |
sanction | +1.274 |
Unsure | +1.229 |
hey | +1.189 |
cul | +1.181 |
sch | +1.177 |
Neg logit contributions | |
Tea | -1.738 |
abit | -1.620 |
76561 | -1.620 |
acle | -1.553 |
Oracle | -1.531 |
Token | in |
Token ID | 287 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
sanction | +5.717 |
Unsure | +5.362 |
hey | +5.337 |
sch | +5.323 |
cul | +5.250 |
Neg logit contributions | |
Tea | -7.779 |
abit | -7.175 |
76561 | -7.110 |
acle | -6.951 |
Oracle | -6.663 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
sanction | +4.273 |
sch | +4.042 |
Unsure | +3.987 |
hey | +3.949 |
kinetic | +3.875 |
Neg logit contributions | |
Tea | -5.821 |
76561 | -5.414 |
abit | -5.364 |
acle | -5.169 |
Oracle | -5.039 |
Token | schools |
Token ID | 4266 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
sanction | +9.259 |
sch | +8.974 |
hey | +8.949 |
kinetic | +8.572 |
Unsure | +8.404 |
Neg logit contributions | |
Tea | -10.838 |
76561 | -10.032 |
abit | -9.862 |
acle | -9.474 |
Oracle | -9.299 |
Token | : |
Token ID | 25 |
Feature activation | -3.00e+01 |
Pos logit contributions | |
sanction | +4.734 |
hey | +4.484 |
Unsure | +4.443 |
sch | +4.431 |
cul | +4.369 |
Neg logit contributions | |
Tea | -5.688 |
76561 | -5.256 |
abit | -5.243 |
acle | -5.032 |
Oracle | -4.914 |
Token | Bull |
Token ID | 8266 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
Why | +16.986 |
Unlock | +16.644 |
sanction | +16.509 |
Unsure | +16.478 |
sch | +16.456 |
Neg logit contributions | |
Tea | -17.556 |
76561 | -15.860 |
abit | -15.832 |
Oracle | -14.916 |
acle | -14.900 |
Token | ies |
Token ID | 444 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
sanction | +2.868 |
Unsure | +2.743 |
hey | +2.664 |
sch | +2.632 |
cul | +2.618 |
Neg logit contributions | |
Tea | -4.952 |
76561 | -4.614 |
abit | -4.569 |
Oracle | -4.448 |
acle | -4.427 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e+01 |
Pos logit contributions | |
sanction | +8.028 |
Unsure | +7.801 |
sch | +7.681 |
hey | +7.676 |
cul | +7.475 |
Neg logit contributions | |
Tea | -11.122 |
76561 | -10.402 |
abit | -10.246 |
acle | -10.200 |
Oracle | -9.912 |
Token | whipping |
Token ID | 44637 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
sanction | +10.639 |
sch | +10.485 |
hey | +9.535 |
kinetic | +9.419 |
CSI | +9.299 |
Neg logit contributions | |
Tea | -13.091 |
abit | -12.206 |
76561 | -12.174 |
Oracle | -11.600 |
acle | -11.481 |
Token | boys |
Token ID | 6510 |
Feature activation | -8.39e+00 |
Pos logit contributions | |
sanction | +4.702 |
Unsure | +4.436 |
sch | +4.431 |
hey | +4.392 |
kinetic | +4.264 |
Neg logit contributions | |
Tea | -5.866 |
76561 | -5.615 |
abit | -5.463 |
acle | -5.239 |
Oracle | -5.080 |
Token | ance |
Token ID | 590 |
Feature activation | -8.70e+00 |
Pos logit contributions | |
sanction | +2.949 |
Unsure | +2.848 |
cul | +2.778 |
sch | +2.750 |
hey | +2.726 |
Neg logit contributions | |
Tea | -3.340 |
76561 | -3.106 |
abit | -3.024 |
Oracle | -2.912 |
acle | -2.890 |
Token | in |
Token ID | 287 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
sanction | +5.611 |
sch | +5.339 |
Unsure | +5.337 |
hey | +5.168 |
kinetic | +5.062 |
Neg logit contributions | |
Tea | -7.603 |
abit | -6.924 |
76561 | -6.921 |
acle | -6.669 |
Oracle | -6.497 |
Token | early |
Token ID | 1903 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
sanction | +4.615 |
sch | +4.406 |
Unsure | +4.227 |
hey | +4.212 |
kinetic | +4.131 |
Neg logit contributions | |
Tea | -6.694 |
76561 | -6.230 |
abit | -6.210 |
acle | -5.962 |
Oracle | -5.831 |
Token | adolescent |
Token ID | 28680 |
Feature activation | -8.72e+00 |
Pos logit contributions | |
sanction | +8.381 |
sch | +8.155 |
hey | +7.587 |
kinetic | +7.328 |
cul | +7.322 |
Neg logit contributions | |
Tea | -13.375 |
76561 | -12.845 |
abit | -12.574 |
acle | -11.909 |
Oracle | -11.754 |
Token | boys |
Token ID | 6510 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
sanction | +5.496 |
sch | +5.258 |
hey | +5.090 |
Unsure | +5.027 |
cul | +4.986 |
Neg logit contributions | |
Tea | -7.699 |
76561 | -7.233 |
abit | -7.217 |
acle | -6.989 |
Oracle | -6.808 |
Token | : |
Token ID | 25 |
Feature activation | -2.91e+01 |
Pos logit contributions | |
Tea | +1.363 |
abit | +1.273 |
76561 | +1.257 |
acle | +1.210 |
Oracle | +1.187 |
Neg logit contributions | |
sanction | -1.234 |
Unsure | -1.191 |
hey | -1.156 |
cul | -1.139 |
kinetic | -1.133 |
Token | Aff |
Token ID | 6708 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
Why | +16.533 |
Unsure | +16.515 |
sch | +16.363 |
sanction | +16.255 |
impact | +15.980 |
Neg logit contributions | |
Tea | -17.017 |
76561 | -15.525 |
abit | -15.406 |
acle | -14.947 |
Oracle | -14.779 |
Token | ili |
Token ID | 2403 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
sanction | +4.916 |
Unsure | +4.817 |
cul | +4.782 |
sch | +4.693 |
opoly | +4.652 |
Neg logit contributions | |
Tea | -4.870 |
76561 | -4.526 |
abit | -4.370 |
acle | -4.256 |
Oracle | -4.251 |
Token | ative |
Token ID | 876 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
Tea | +3.832 |
abit | +3.636 |
acle | +3.393 |
76561 | +3.345 |
Oracle | +3.184 |
Neg logit contributions | |
sanction | -5.449 |
Unsure | -5.341 |
hey | -5.218 |
CSI | -5.131 |
kinetic | -5.051 |
Token | and |
Token ID | 290 |
Feature activation | -1.97e+01 |
Pos logit contributions | |
sanction | +8.244 |
sch | +7.762 |
hey | +7.575 |
impact | +7.361 |
kinetic | +7.352 |
Neg logit contributions | |
Tea | -11.126 |
76561 | -10.441 |
abit | -10.194 |
acle | -9.830 |
Oracle | -9.605 |
Token | aggressive |
Token ID | 8361 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
sanction | +12.214 |
sch | +12.105 |
kinetic | +11.265 |
Unsure | +11.051 |
impact | +10.950 |
Neg logit contributions | |
Tea | -15.156 |
76561 | -14.019 |
abit | -13.130 |
Oracle | -12.881 |
ethy | -12.461 |
Token | - |
Token ID | 12 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
sanction | +1.951 |
Unsure | +1.857 |
sch | +1.817 |
hey | +1.813 |
cul | +1.791 |
Neg logit contributions | |
Tea | -2.364 |
76561 | -2.195 |
abit | -2.195 |
acle | -2.086 |
Oracle | -2.041 |
Token | beh |
Token ID | 20709 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
sanction | +3.954 |
Unsure | +3.773 |
cul | +3.758 |
sch | +3.725 |
win | +3.711 |
Neg logit contributions | |
Tea | -4.673 |
76561 | -4.384 |
abit | -4.325 |
acle | -4.161 |
Oracle | -4.063 |
Token | aving |
Token ID | 2703 |
Feature activation | -1.40e+01 |
Pos logit contributions | |
sanction | +0.165 |
Unsure | +0.159 |
hey | +0.154 |
cul | +0.153 |
sch | +0.152 |
Neg logit contributions | |
Tea | -0.223 |
abit | -0.208 |
76561 | -0.206 |
acle | -0.200 |
Oracle | -0.196 |
Token | , |
Token ID | 11 |
Feature activation | -7.93e+00 |
Pos logit contributions | |
sanction | +7.411 |
sch | +7.313 |
hey | +6.825 |
Unsure | +6.630 |
Koreans | +6.544 |
Neg logit contributions | |
Tea | -12.742 |
76561 | -12.377 |
abit | -11.907 |
acle | -11.408 |
Oracle | -11.220 |
Token | unhappy |
Token ID | 19283 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
sanction | +5.124 |
sch | +4.831 |
hey | +4.776 |
Unsure | +4.747 |
kinetic | +4.645 |
Neg logit contributions | |
Tea | -6.807 |
76561 | -6.527 |
abit | -6.380 |
acle | -6.031 |
Oracle | -5.943 |
Token | : |
Token ID | 25 |
Feature activation | -2.91e+01 |
Pos logit contributions | |
sanction | +3.062 |
Unsure | +2.883 |
sch | +2.880 |
hey | +2.838 |
cul | +2.778 |
Neg logit contributions | |
Tea | -4.577 |
76561 | -4.322 |
abit | -4.304 |
acle | -4.141 |
Oracle | -4.019 |
Token | The |
Token ID | 383 |
Feature activation | -2.30e+01 |
Pos logit contributions | |
Why | +16.948 |
Unsure | +16.407 |
Unlock | +16.340 |
sch | +16.200 |
sanction | +15.978 |
Neg logit contributions | |
Tea | -16.886 |
76561 | -16.030 |
abit | -15.563 |
acle | -14.803 |
Oracle | -14.404 |
Token | structure |
Token ID | 4645 |
Feature activation | -9.47e+00 |
Pos logit contributions | |
sch | +14.707 |
sanction | +14.702 |
impact | +14.702 |
hey | +14.463 |
kinetic | +13.796 |
Neg logit contributions | |
Tea | -14.602 |
76561 | -13.844 |
abit | -13.075 |
acle | -12.122 |
Oracle | -11.992 |
Token | of |
Token ID | 286 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
sanction | +5.704 |
sch | +5.321 |
hey | +5.319 |
Unsure | +5.201 |
cul | +5.182 |
Neg logit contributions | |
Tea | -8.306 |
76561 | -7.743 |
abit | -7.632 |
acle | -7.242 |
Oracle | -7.191 |
Token | adolescents |
Token ID | 25447 |
Feature activation | -8.34e+00 |
Pos logit contributions | |
sanction | +7.410 |
sch | +7.164 |
hey | +6.693 |
kinetic | +6.566 |
CSI | +6.529 |
Neg logit contributions | |
Tea | -9.773 |
76561 | -9.166 |
abit | -9.005 |
acle | -8.583 |
Oracle | -8.413 |
Token | � |
Token ID | 447 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
sanction | +4.709 |
sch | +4.477 |
cul | +4.395 |
Unsure | +4.389 |
hey | +4.331 |
Neg logit contributions | |
Tea | -7.794 |
abit | -7.254 |
76561 | -7.196 |
acle | -7.085 |
Oracle | -6.896 |
Token | ā |
Token ID | 10235 |
Feature activation | -8.41e+00 |
Pos logit contributions | |
sanction | +7.924 |
hey | +7.810 |
cul | +7.785 |
Unsure | +7.751 |
sch | +7.721 |
Neg logit contributions | |
Tea | -7.558 |
76561 | -7.214 |
abit | -6.740 |
Oracle | -6.548 |
Oracle | -6.512 |
Token | ne |
Token ID | 710 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
sanction | +5.391 |
hey | +5.236 |
Unsure | +5.218 |
sch | +5.174 |
cul | +5.165 |
Neg logit contributions | |
Tea | -6.865 |
76561 | -6.542 |
abit | -6.379 |
acle | -6.203 |
Oracle | -6.060 |
Token | o |
Token ID | 267 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
sanction | +6.200 |
hey | +6.115 |
sch | +6.108 |
Unsure | +6.103 |
cul | +5.894 |
Neg logit contributions | |
Tea | -8.787 |
76561 | -8.531 |
abit | -8.248 |
acle | -7.935 |
Oracle | -7.802 |
Token | Hal |
Token ID | 11023 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
sanction | +4.126 |
Unsure | +4.003 |
hey | +3.958 |
sch | +3.911 |
cul | +3.863 |
Neg logit contributions | |
Tea | -5.829 |
abit | -5.452 |
76561 | -5.437 |
acle | -5.251 |
Oracle | -5.083 |
Token | ep |
Token ID | 538 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Tea | +1.178 |
abit | +1.094 |
76561 | +1.061 |
acle | +1.036 |
Oracle | +1.004 |
Neg logit contributions | |
sanction | -1.386 |
Unsure | -1.336 |
hey | -1.301 |
cul | -1.284 |
kinetic | -1.283 |
Token | ā |
Token ID | 10235 |
Feature activation | -2.80e+01 |
Pos logit contributions | |
sanction | +1.667 |
Unsure | +1.627 |
hey | +1.585 |
cul | +1.575 |
sch | +1.564 |
Neg logit contributions | |
Tea | -1.434 |
76561 | -1.313 |
abit | -1.309 |
acle | -1.239 |
Oracle | -1.218 |
Token | k |
Token ID | 74 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
win | +17.482 |
cul | +17.434 |
Unsure | +16.927 |
kn | +16.672 |
sch | +16.605 |
Neg logit contributions | |
Tea | -13.939 |
76561 | -13.661 |
abit | -12.591 |
Oracle | -12.173 |
Archdemon | -12.009 |
Token | ī |
Token ID | 18962 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
Unsure | +8.884 |
cul | +8.870 |
sanction | +8.771 |
win | +8.769 |
hey | +8.734 |
Neg logit contributions | |
Tea | -8.775 |
76561 | -8.594 |
abit | -7.851 |
Oracle | -7.602 |
Oracle | -7.550 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
sanction | +5.370 |
Unsure | +5.189 |
hey | +5.182 |
sch | +5.181 |
cul | +5.097 |
Neg logit contributions | |
Tea | -7.801 |
76561 | -7.540 |
abit | -7.306 |
acle | -7.095 |
Oracle | -6.932 |
Token | a |
Token ID | 257 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
sanction | +5.817 |
Unsure | +5.677 |
hey | +5.654 |
sch | +5.611 |
kinetic | +5.343 |
Neg logit contributions | |
Tea | -9.403 |
76561 | -8.916 |
abit | -8.876 |
acle | -8.590 |
Oracle | -8.334 |
Token | k |
Token ID | 479 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
sanction | +3.276 |
Unsure | +3.138 |
hey | +3.114 |
sch | +3.086 |
cul | +3.008 |
Neg logit contributions | |
Tea | -5.879 |
76561 | -5.567 |
abit | -5.522 |
acle | -5.308 |
Oracle | -5.238 |
Token | field |
Token ID | 3245 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
Tea | +0.994 |
abit | +0.923 |
76561 | +0.905 |
acle | +0.883 |
Oracle | +0.863 |
Neg logit contributions | |
sanction | -0.896 |
Unsure | -0.872 |
hey | -0.839 |
cul | -0.827 |
sch | -0.826 |
Token | play |
Token ID | 711 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
sanction | +4.795 |
hey | +4.629 |
sch | +4.497 |
kinetic | +4.444 |
Unsure | +4.399 |
Neg logit contributions | |
Tea | -5.993 |
abit | -5.708 |
76561 | -5.632 |
acle | -5.360 |
Oracle | -5.182 |
Token | was |
Token ID | 373 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
sanction | +7.047 |
hey | +6.785 |
sch | +6.591 |
impact | +6.352 |
win | +6.333 |
Neg logit contributions | |
Tea | -10.867 |
abit | -10.153 |
76561 | -10.150 |
Oracle | -9.475 |
Oracle | -9.427 |
Token | the |
Token ID | 262 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
sanction | +1.290 |
Unsure | +1.231 |
hey | +1.211 |
sch | +1.189 |
kinetic | +1.181 |
Neg logit contributions | |
Tea | -1.556 |
abit | -1.452 |
76561 | -1.440 |
acle | -1.376 |
Oracle | -1.348 |
Token | only |
Token ID | 691 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
sanction | +2.105 |
Unsure | +1.956 |
hey | +1.946 |
sch | +1.897 |
kinetic | +1.873 |
Neg logit contributions | |
Tea | -3.437 |
abit | -3.298 |
76561 | -3.230 |
acle | -3.096 |
Oracle | -3.023 |
Token | factor |
Token ID | 5766 |
Feature activation | -2.79e+01 |
Pos logit contributions | |
sanction | +5.840 |
hey | +5.309 |
sch | +5.309 |
kinetic | +5.236 |
Unsure | +5.194 |
Neg logit contributions | |
Tea | -7.835 |
abit | -7.489 |
76561 | -7.311 |
Oracle | -6.777 |
acle | -6.743 |
Token | involved |
Token ID | 2950 |
Feature activation | -1.68e+01 |
Pos logit contributions | |
sanction | +14.610 |
impact | +13.548 |
hey | +13.320 |
relevant | +13.304 |
sch | +12.850 |
Neg logit contributions | |
Tea | -19.058 |
abit | -18.767 |
76561 | -17.831 |
ethy | -16.960 |
acle | -16.511 |
Token | , |
Token ID | 11 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
sanction | +9.385 |
hey | +8.730 |
sch | +8.452 |
win | +8.310 |
Unsure | +8.256 |
Neg logit contributions | |
Tea | -13.865 |
abit | -12.945 |
76561 | -12.923 |
acle | -12.189 |
ethy | -11.862 |
Token | he |
Token ID | 339 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
sanction | +3.757 |
hey | +3.562 |
Unsure | +3.499 |
sch | +3.393 |
cul | +3.350 |
Neg logit contributions | |
Tea | -5.649 |
abit | -5.252 |
76561 | -5.124 |
acle | -5.038 |
Oracle | -4.894 |
Token | � |
Token ID | 447 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
sanction | +3.458 |
Unsure | +3.305 |
hey | +3.281 |
sch | +3.226 |
cul | +3.208 |
Neg logit contributions | |
Tea | -5.002 |
abit | -4.636 |
76561 | -4.586 |
acle | -4.479 |
Oracle | -4.406 |
Token | � |
Token ID | 247 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
sanction | +2.873 |
Unsure | +2.815 |
hey | +2.701 |
cul | +2.616 |
sch | +2.607 |
Neg logit contributions | |
Tea | -5.033 |
abit | -4.777 |
76561 | -4.715 |
acle | -4.608 |
Oracle | -4.561 |
Token | other |
Token ID | 584 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
sanction | +2.934 |
sch | +2.642 |
Unsure | +2.564 |
hey | +2.540 |
relevant | +2.210 |
Neg logit contributions | |
Tea | -15.709 |
76561 | -15.492 |
abit | -14.999 |
Oracle | -14.129 |
acle | -14.087 |
Token | for |
Token ID | 329 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
sanction | +2.759 |
hey | +2.586 |
Unsure | +2.586 |
sch | +2.544 |
kinetic | +2.440 |
Neg logit contributions | |
Tea | -4.763 |
76561 | -4.576 |
abit | -4.536 |
acle | -4.324 |
Oracle | -4.184 |
Token | multi |
Token ID | 5021 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Tea | +2.580 |
abit | +2.375 |
acle | +2.295 |
76561 | +2.287 |
Oracle | +2.268 |
Neg logit contributions | |
sanction | -3.140 |
Unsure | -3.091 |
cul | -2.998 |
hey | -2.993 |
fw | -2.992 |
Token | - |
Token ID | 12 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Tea | +1.903 |
abit | +1.764 |
76561 | +1.717 |
acle | +1.700 |
Oracle | +1.671 |
Neg logit contributions | |
sanction | -1.910 |
Unsure | -1.870 |
hey | -1.803 |
cul | -1.800 |
proble | -1.786 |
Token | line |
Token ID | 1370 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
Tea | +1.382 |
abit | +1.280 |
76561 | +1.241 |
acle | +1.223 |
Oracle | +1.184 |
Neg logit contributions | |
sanction | -1.439 |
Unsure | -1.395 |
hey | -1.359 |
kinetic | -1.335 |
sch | -1.335 |
Token | ? |
Token ID | 30 |
Feature activation | -2.78e+01 |
Pos logit contributions | |
Unsure | +4.237 |
sanction | +4.185 |
hey | +4.106 |
sch | +3.819 |
kinetic | +3.782 |
Neg logit contributions | |
Tea | -13.275 |
76561 | -12.715 |
abit | -12.392 |
acle | -11.967 |
Oracle | -11.707 |
Token | in |
Token ID | 287 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
Why | +16.889 |
Unsure | +16.592 |
sanction | +16.285 |
hey | +16.156 |
Does | +15.486 |
Neg logit contributions | |
Tea | -16.383 |
76561 | -15.725 |
abit | -13.958 |
acle | -13.033 |
ña | -12.977 |
Token | what |
Token ID | 644 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
sanction | +9.636 |
cul | +9.017 |
sch | +9.009 |
Unsure | +8.974 |
hey | +8.927 |
Neg logit contributions | |
Tea | -11.283 |
76561 | -11.200 |
abit | -10.319 |
acle | -9.598 |
Oracle | -9.242 |
Token | context |
Token ID | 4732 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
sanction | +6.139 |
Unsure | +5.727 |
sch | +5.680 |
hey | +5.673 |
kinetic | +5.521 |
Neg logit contributions | |
Tea | -8.916 |
76561 | -8.791 |
abit | -8.496 |
acle | -8.001 |
ethy | -7.837 |
Token | are |
Token ID | 389 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
sanction | +2.929 |
Unsure | +2.777 |
hey | +2.715 |
sch | +2.668 |
kinetic | +2.630 |
Neg logit contributions | |
Tea | -4.854 |
76561 | -4.557 |
abit | -4.527 |
acle | -4.335 |
Oracle | -4.212 |
Token | blocks |
Token ID | 7021 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
sanction | +1.739 |
Unsure | +1.660 |
hey | +1.619 |
sch | +1.604 |
kinetic | +1.584 |
Neg logit contributions | |
Tea | -2.403 |
abit | -2.250 |
76561 | -2.239 |
acle | -2.137 |
Oracle | -2.075 |
Token | x |
Token ID | 2124 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
Unsure | +4.522 |
sch | +4.323 |
hey | +4.302 |
CSI | +4.177 |
sanction | +4.153 |
Neg logit contributions | |
Tea | -12.481 |
abit | -12.099 |
76561 | -11.947 |
acle | -11.478 |
ethy | -11.235 |
Token | . |
Token ID | 13 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
sanction | +2.431 |
Unsure | +2.410 |
hey | +2.328 |
sch | +2.285 |
win | +2.270 |
Neg logit contributions | |
Tea | -3.728 |
abit | -3.561 |
76561 | -3.537 |
acle | -3.366 |
Oracle | -3.294 |
Token | x |
Token ID | 87 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
Unsure | +3.412 |
win | +3.359 |
sanction | +3.255 |
cul | +3.250 |
hey | +3.203 |
Neg logit contributions | |
Tea | -6.812 |
abit | -6.516 |
76561 | -6.507 |
Oracle | -6.177 |
acle | -6.159 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e+01 |
Pos logit contributions | |
Unsure | +3.809 |
sanction | +3.718 |
win | +3.676 |
hey | +3.665 |
cul | +3.565 |
Neg logit contributions | |
Tea | -6.682 |
abit | -6.457 |
76561 | -6.432 |
acle | -6.022 |
Oracle | -5.938 |
Token | x |
Token ID | 87 |
Feature activation | -2.10e+01 |
Pos logit contributions | |
win | +8.777 |
gr | +7.950 |
cul | +7.756 |
Unsure | +7.624 |
fw | +7.554 |
Neg logit contributions | |
Tea | -17.943 |
��� | -17.861 |
76561 | -17.635 |
abit | -17.456 |
Archdemon | -16.959 |
Token | . |
Token ID | 13 |
Feature activation | -2.77e+01 |
Pos logit contributions | |
win | +7.621 |
gr | +7.047 |
Unsure | +7.018 |
� | +6.999 |
hey | +6.869 |
Neg logit contributions | |
76561 | -19.464 |
Tea | -19.336 |
��� | -19.110 |
abit | -18.996 |
ethy | -17.999 |
Token | 108 |
Token ID | 15711 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
win | +4.528 |
� | +3.973 |
cul | +3.862 |
hey | +3.272 |
sanction | +3.211 |
Neg logit contributions | |
76561 | -28.794 |
Tea | -28.415 |
abit | -27.810 |
ethy | -27.069 |
Archdemon | -26.912 |
Token | 10 |
Token ID | 838 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Unsure | +3.383 |
sanction | +3.301 |
hey | +3.131 |
sch | +3.100 |
CSI | +3.029 |
Neg logit contributions | |
Tea | -7.042 |
abit | -6.721 |
76561 | -6.607 |
acle | -6.360 |
ethy | -6.176 |
Token | 46 |
Token ID | 3510 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
sanction | +0.223 |
Unsure | +0.214 |
hey | +0.206 |
cul | +0.203 |
sch | +0.202 |
Neg logit contributions | |
Tea | -0.365 |
abit | -0.344 |
76561 | -0.340 |
acle | -0.331 |
Oracle | -0.325 |
Token | 358 |
Token ID | 31128 |
Feature activation | -9.82e+00 |
Pos logit contributions | |
sanction | +4.172 |
Unsure | +4.081 |
hey | +3.931 |
cul | +3.904 |
sch | +3.862 |
Neg logit contributions | |
Tea | -6.093 |
abit | -5.805 |
76561 | -5.532 |
acle | -5.504 |
Oracle | -5.367 |
Token | x |
Token ID | 2124 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Unsure | +3.937 |
sch | +3.775 |
hey | +3.771 |
sanction | +3.705 |
CSI | +3.648 |
Neg logit contributions | |
Tea | -10.386 |
abit | -10.113 |
76561 | -9.977 |
acle | -9.503 |
ethy | -9.309 |
Token | , |
Token ID | 11 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
Tea | +2.737 |
abit | +2.491 |
76561 | +2.476 |
acle | +2.429 |
Oracle | +2.383 |
Neg logit contributions | |
sanction | -2.550 |
proble | -2.483 |
Unsure | -2.434 |
kinetic | -2.360 |
cul | -2.347 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
sanction | +3.576 |
Unsure | +3.325 |
hey | +3.321 |
sch | +3.240 |
CSI | +3.203 |
Neg logit contributions | |
Tea | -5.213 |
abit | -4.933 |
76561 | -4.902 |
acle | -4.620 |
Oracle | -4.607 |
Token |
|
Token ID | 198 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
Tea | +2.004 |
abit | +1.842 |
76561 | +1.809 |
acle | +1.776 |
Oracle | +1.754 |
Neg logit contributions | |
sanction | -1.820 |
Unsure | -1.720 |
proble | -1.710 |
cul | -1.678 |
hey | -1.677 |
Token |
|
Token ID | 198 |
Feature activation | +7.96e+00 |
Pos logit contributions | |
Tea | +3.211 |
abit | +2.922 |
acle | +2.854 |
76561 | +2.854 |
Oracle | +2.817 |
Neg logit contributions | |
sanction | -3.240 |
proble | -3.187 |
Unsure | -3.034 |
kinetic | -3.001 |
cul | -2.972 |
Token | Subject |
Token ID | 19776 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
Tea | +5.696 |
abit | +4.985 |
76561 | +4.907 |
acle | +4.790 |
Oracle | +4.684 |
Neg logit contributions | |
sanction | -6.717 |
proble | -6.584 |
Unsure | -6.215 |
CSI | -6.149 |
kinetic | -6.137 |
Token | : |
Token ID | 25 |
Feature activation | -2.74e+01 |
Pos logit contributions | |
Unsure | +3.348 |
sanction | +3.307 |
hey | +3.238 |
win | +3.170 |
sch | +3.160 |
Neg logit contributions | |
Tea | -4.460 |
abit | -4.255 |
76561 | -4.192 |
acle | -3.979 |
Oracle | -3.938 |
Token | R |
Token ID | 371 |
Feature activation | -8.79e+00 |
Pos logit contributions | |
hey | +17.461 |
Unsure | +17.030 |
wow | +16.697 |
sch | +16.618 |
Why | +16.237 |
Neg logit contributions | |
Tea | -15.011 |
abit | -14.365 |
76561 | -14.291 |
Oracle | -13.863 |
acle | -13.199 |
Token | iff |
Token ID | 733 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
sanction | +6.372 |
Unsure | +6.160 |
hey | +6.086 |
sch | +6.044 |
cul | +6.005 |
Neg logit contributions | |
Tea | -6.575 |
76561 | -6.225 |
abit | -6.002 |
acle | -5.726 |
Oracle | -5.680 |
Token | Tra |
Token ID | 15721 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Tea | +0.042 |
abit | +0.040 |
76561 | +0.039 |
acle | +0.038 |
Oracle | +0.037 |
Neg logit contributions | |
sanction | -0.029 |
Unsure | -0.028 |
hey | -0.027 |
cul | -0.027 |
sch | -0.027 |
Token | x |
Token ID | 87 |
Feature activation | -1.65e+01 |
Pos logit contributions | |
sanction | +0.165 |
Unsure | +0.158 |
hey | +0.154 |
cul | +0.152 |
sch | +0.151 |
Neg logit contributions | |
Tea | -0.233 |
abit | -0.219 |
76561 | -0.216 |
acle | -0.210 |
Oracle | -0.206 |
Token | Actually |
Token ID | 18689 |
Feature activation | -9.94e+00 |
Pos logit contributions | |
hey | +10.919 |
Unsure | +10.632 |
sch | +10.440 |
sanction | +10.348 |
wow | +10.157 |
Neg logit contributions | |
Tea | -11.348 |
abit | -10.878 |
76561 | -10.840 |
Oracle | -10.401 |
acle | -10.087 |
Token | G |
Token ID | 38 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
Tea | +4.099 |
76561 | +3.648 |
abit | +3.636 |
acle | +3.551 |
Oracle | +3.512 |
Neg logit contributions | |
sanction | -3.511 |
proble | -3.284 |
Unsure | -3.246 |
cul | -3.208 |
opoly | -3.170 |
Token | ED |
Token ID | 1961 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Tea | +4.690 |
abit | +4.192 |
76561 | +4.141 |
Oracle | +3.990 |
acle | +3.924 |
Neg logit contributions | |
sanction | -7.507 |
proble | -7.320 |
cul | -6.968 |
opoly | -6.965 |
kinetic | -6.962 |
Token | NET |
Token ID | 30502 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
Tea | +2.631 |
abit | +2.451 |
76561 | +2.430 |
acle | +2.371 |
Oracle | +2.351 |
Neg logit contributions | |
sanction | -1.841 |
Unsure | -1.741 |
cul | -1.700 |
hey | -1.688 |
riction | -1.659 |
Token | CALL |
Token ID | 42815 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
sanction | +0.489 |
Unsure | +0.472 |
hey | +0.458 |
cul | +0.452 |
sch | +0.450 |
Neg logit contributions | |
Tea | -0.634 |
abit | -0.595 |
76561 | -0.587 |
acle | -0.569 |
Oracle | -0.557 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Tea | +0.451 |
abit | +0.426 |
76561 | +0.422 |
acle | +0.411 |
Oracle | +0.405 |
Neg logit contributions | |
sanction | -0.236 |
Unsure | -0.224 |
hey | -0.215 |
cul | -0.212 |
sch | -0.210 |
Token | : |
Token ID | 25 |
Feature activation | -2.69e+01 |
Pos logit contributions | |
Tea | +1.442 |
abit | +1.336 |
76561 | +1.316 |
acle | +1.274 |
Oracle | +1.252 |
Neg logit contributions | |
sanction | -1.463 |
Unsure | -1.413 |
hey | -1.371 |
cul | -1.363 |
sch | -1.346 |
Token | 05 |
Token ID | 8870 |
Feature activation | +7.64e+00 |
Pos logit contributions | |
CSI | +12.551 |
Unsure | +12.344 |
hey | +12.166 |
sch | +11.997 |
Unlock | +11.741 |
Neg logit contributions | |
Tea | -19.463 |
abit | -18.868 |
76561 | -17.967 |
acle | -16.605 |
ethy | -16.485 |
Token | 42 |
Token ID | 3682 |
Feature activation | +8.58e+00 |
Pos logit contributions | |
Tea | +5.597 |
abit | +4.909 |
76561 | +4.840 |
acle | +4.823 |
Oracle | +4.783 |
Neg logit contributions | |
sanction | -6.087 |
proble | -5.906 |
kinetic | -5.685 |
Unsure | -5.673 |
riction | -5.587 |
Token | z |
Token ID | 89 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
Tea | +4.487 |
abit | +4.053 |
acle | +3.785 |
76561 | +3.708 |
Oracle | +3.575 |
Neg logit contributions | |
sanction | -8.284 |
proble | -8.167 |
Unsure | -7.819 |
kinetic | -7.802 |
hey | -7.751 |
Token | SH |
Token ID | 6006 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
Tea | +0.673 |
abit | +0.630 |
76561 | +0.623 |
acle | +0.605 |
Oracle | +0.595 |
Neg logit contributions | |
sanction | -0.485 |
Unsure | -0.464 |
hey | -0.449 |
cul | -0.446 |
sch | -0.441 |
Token | AM |
Token ID | 2390 |
Feature activation | +8.55e+00 |
Pos logit contributions | |
Tea | +3.002 |
abit | +2.747 |
76561 | +2.674 |
acle | +2.578 |
Oracle | +2.565 |
Neg logit contributions | |
sanction | -3.380 |
Unsure | -3.244 |
cul | -3.161 |
hey | -3.148 |
kinetic | -3.133 |
Token | bullying |
Token ID | 20714 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
sanction | +4.166 |
sch | +3.908 |
Unsure | +3.841 |
hey | +3.807 |
kinetic | +3.765 |
Neg logit contributions | |
Tea | -5.501 |
abit | -5.124 |
76561 | -5.060 |
acle | -4.904 |
Oracle | -4.765 |
Token | behavior |
Token ID | 4069 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
sanction | +3.124 |
Unsure | +2.927 |
hey | +2.867 |
sch | +2.853 |
cul | +2.803 |
Neg logit contributions | |
Tea | -4.004 |
abit | -3.704 |
76561 | -3.668 |
acle | -3.611 |
Oracle | -3.475 |
Token | 1994 |
Token ID | 9162 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
sanction | +2.681 |
Unsure | +2.555 |
hey | +2.483 |
sch | +2.472 |
cul | +2.450 |
Neg logit contributions | |
Tea | -3.071 |
abit | -2.843 |
76561 | -2.783 |
acle | -2.741 |
Oracle | -2.647 |
Token | - |
Token ID | 12 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
sanction | +2.921 |
Unsure | +2.794 |
hey | +2.714 |
cul | +2.683 |
sch | +2.666 |
Neg logit contributions | |
Tea | -3.789 |
abit | -3.532 |
76561 | -3.472 |
acle | -3.381 |
Oracle | -3.287 |
Token | 2006 |
Token ID | 13330 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
sanction | +2.723 |
Unsure | +2.640 |
hey | +2.547 |
sch | +2.522 |
win | +2.516 |
Neg logit contributions | |
Tea | -4.220 |
abit | -4.047 |
76561 | -3.954 |
acle | -3.862 |
Oracle | -3.778 |
Token | : |
Token ID | 25 |
Feature activation | -2.67e+01 |
Pos logit contributions | |
sanction | +1.253 |
Unsure | +1.210 |
hey | +1.176 |
cul | +1.167 |
sch | +1.165 |
Neg logit contributions | |
Tea | -1.270 |
abit | -1.177 |
76561 | -1.161 |
acle | -1.126 |
Oracle | -1.095 |
Token | Find |
Token ID | 9938 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
Unsure | +15.265 |
Why | +15.002 |
impact | +14.764 |
sanction | +14.719 |
Unlock | +14.512 |
Neg logit contributions | |
Tea | -16.807 |
76561 | -15.492 |
abit | -15.125 |
acle | -14.652 |
ethy | -14.567 |
Token | ings |
Token ID | 654 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
sanction | +5.408 |
sch | +4.944 |
Unsure | +4.895 |
hey | +4.891 |
kinetic | +4.798 |
Neg logit contributions | |
Tea | -13.747 |
76561 | -13.121 |
abit | -12.732 |
acle | -12.430 |
Oracle | -12.315 |
Token | from |
Token ID | 422 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
sanction | +2.806 |
Unsure | +2.692 |
hey | +2.623 |
sch | +2.592 |
cul | +2.566 |
Neg logit contributions | |
Tea | -4.522 |
abit | -4.267 |
76561 | -4.230 |
acle | -4.090 |
Oracle | -4.002 |
Token | Europe |
Token ID | 2031 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
sanction | +7.287 |
sch | +6.976 |
Unsure | +6.780 |
CSI | +6.674 |
hey | +6.647 |
Neg logit contributions | |
Tea | -10.266 |
76561 | -9.478 |
abit | -9.348 |
acle | -9.017 |
Oracle | -8.943 |
Token | and |
Token ID | 290 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
sanction | +3.826 |
Unsure | +3.717 |
hey | +3.594 |
sch | +3.591 |
cul | +3.545 |
Neg logit contributions | |
Tea | -4.820 |
abit | -4.440 |
76561 | -4.375 |
acle | -4.241 |
Oracle | -4.123 |
Token | x |
Token ID | 2124 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Unsure | +3.521 |
sanction | +3.487 |
sch | +3.418 |
hey | +3.389 |
CSI | +3.282 |
Neg logit contributions | |
Tea | -8.484 |
abit | -8.146 |
76561 | -8.083 |
acle | -7.726 |
ethy | -7.529 |
Token | . |
Token ID | 13 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
sanction | +0.661 |
Unsure | +0.641 |
hey | +0.621 |
cul | +0.612 |
sch | +0.610 |
Neg logit contributions | |
Tea | -0.869 |
abit | -0.818 |
76561 | -0.809 |
acle | -0.781 |
Oracle | -0.765 |
Token | x |
Token ID | 87 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
sanction | +1.966 |
Unsure | +1.965 |
cul | +1.874 |
hey | +1.873 |
win | +1.872 |
Neg logit contributions | |
Tea | -3.385 |
abit | -3.212 |
76561 | -3.190 |
acle | -3.060 |
Oracle | -3.034 |
Token | . |
Token ID | 13 |
Feature activation | -9.36e+00 |
Pos logit contributions | |
Unsure | +3.848 |
sanction | +3.765 |
hey | +3.686 |
win | +3.680 |
sch | +3.582 |
Neg logit contributions | |
Tea | -6.729 |
abit | -6.529 |
76561 | -6.486 |
acle | -6.078 |
Oracle | -5.981 |
Token | x |
Token ID | 87 |
Feature activation | -2.07e+01 |
Pos logit contributions | |
win | +4.303 |
Unsure | +4.272 |
cul | +4.030 |
fw | +3.945 |
hey | +3.905 |
Neg logit contributions | |
Tea | -9.199 |
abit | -8.913 |
76561 | -8.820 |
Oracle | -8.482 |
acle | -8.399 |
Token | . |
Token ID | 13 |
Feature activation | -2.64e+01 |
Pos logit contributions | |
win | +7.396 |
Unsure | +7.097 |
gr | +6.305 |
fw | +6.277 |
hey | +6.237 |
Neg logit contributions | |
��� | -20.358 |
abit | -19.284 |
Tea | -18.871 |
fortun | -18.718 |
76561 | -18.636 |
Token | 128 |
Token ID | 12762 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
win | +6.085 |
sign | +5.311 |
Unsure | +5.141 |
cul | +5.006 |
sanction | +4.643 |
Neg logit contributions | |
��� | -26.254 |
abit | -25.624 |
Tea | -25.113 |
Oracle | -24.377 |
76561 | -24.105 |
Token | 9 |
Token ID | 860 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
sanction | +2.099 |
Unsure | +2.076 |
hey | +1.961 |
sch | +1.927 |
CSI | +1.903 |
Neg logit contributions | |
Tea | -4.151 |
abit | -3.961 |
76561 | -3.893 |
acle | -3.770 |
Oracle | -3.649 |
Token | 86 |
Token ID | 4521 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
sanction | +1.992 |
Unsure | +1.932 |
hey | +1.874 |
cul | +1.838 |
sch | +1.838 |
Neg logit contributions | |
Tea | -3.310 |
abit | -3.135 |
76561 | -3.045 |
acle | -2.998 |
Oracle | -2.940 |
Token | 104 |
Token ID | 13464 |
Feature activation | -8.70e+00 |
Pos logit contributions | |
Tea | +0.123 |
abit | +0.116 |
76561 | +0.114 |
acle | +0.111 |
Oracle | +0.109 |
Neg logit contributions | |
sanction | -0.082 |
Unsure | -0.079 |
hey | -0.076 |
cul | -0.075 |
sch | -0.075 |
Token | x |
Token ID | 2124 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Unsure | +3.687 |
sanction | +3.581 |
hey | +3.548 |
sch | +3.513 |
CSI | +3.376 |
Neg logit contributions | |
Tea | -9.147 |
76561 | -8.771 |
abit | -8.760 |
acle | -8.273 |
ethy | -8.091 |
Token | 4 |
Token ID | 19 |
Feature activation | -2.26e+01 |
Pos logit contributions | |
sanction | +1.961 |
Unsure | +1.881 |
hey | +1.831 |
cul | +1.813 |
sch | +1.790 |
Neg logit contributions | |
Tea | -2.780 |
76561 | -2.597 |
abit | -2.597 |
acle | -2.482 |
Oracle | -2.407 |
Token | { |
Token ID | 1391 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
Unsure | +9.437 |
sanction | +9.308 |
hey | +9.125 |
sch | +8.804 |
win | +8.791 |
Neg logit contributions | |
76561 | -19.272 |
Tea | -18.957 |
abit | -17.657 |
ethy | -16.472 |
acle | -16.359 |
Token | ( |
Token ID | 7 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Tea | +0.596 |
abit | +0.558 |
76561 | +0.551 |
acle | +0.537 |
Oracle | +0.527 |
Neg logit contributions | |
sanction | -0.393 |
Unsure | -0.375 |
hey | -0.363 |
cul | -0.358 |
sch | -0.356 |
Token | 341 |
Token ID | 33660 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
sanction | +1.474 |
Unsure | +1.425 |
hey | +1.383 |
cul | +1.363 |
sch | +1.358 |
Neg logit contributions | |
Tea | -2.079 |
abit | -1.967 |
76561 | -1.927 |
acle | -1.874 |
Oracle | -1.838 |
Token | s |
Token ID | 82 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
sanction | +1.844 |
Unsure | +1.776 |
hey | +1.727 |
cul | +1.700 |
sch | +1.700 |
Neg logit contributions | |
Tea | -2.577 |
abit | -2.417 |
76561 | -2.397 |
acle | -2.310 |
Oracle | -2.270 |
Token | )} |
Token ID | 38165 |
Feature activation | -2.64e+01 |
Pos logit contributions | |
Tea | +2.195 |
abit | +2.049 |
76561 | +2.032 |
acle | +1.981 |
Oracle | +1.950 |
Neg logit contributions | |
sanction | -1.559 |
Unsure | -1.482 |
hey | -1.424 |
cul | -1.418 |
proble | -1.413 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
Unsure | +12.607 |
sanction | +12.119 |
hey | +11.991 |
win | +11.959 |
cul | +11.761 |
Neg logit contributions | |
76561 | -20.018 |
Tea | -19.322 |
abit | -18.491 |
ethy | -16.108 |
salads | -16.079 |
Token | . |
Token ID | 13 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
Tea | +2.681 |
abit | +2.472 |
76561 | +2.411 |
acle | +2.383 |
Oracle | +2.350 |
Neg logit contributions | |
sanction | -2.476 |
proble | -2.352 |
Unsure | -2.352 |
hey | -2.293 |
cul | -2.290 |
Token | N |
Token ID | 399 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
sanction | +3.584 |
Unsure | +3.548 |
hey | +3.426 |
sch | +3.394 |
cul | +3.308 |
Neg logit contributions | |
Tea | -4.732 |
76561 | -4.527 |
abit | -4.415 |
acle | -4.175 |
Oracle | -4.006 |
Token | xd |
Token ID | 24954 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Tea | +4.143 |
abit | +3.877 |
acle | +3.734 |
76561 | +3.613 |
Oracle | +3.509 |
Neg logit contributions | |
sanction | -4.442 |
Unsure | -4.246 |
kinetic | -4.125 |
hey | -4.118 |
CSI | -4.105 |
Token | 4 |
Token ID | 19 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
Tea | +1.703 |
abit | +1.578 |
76561 | +1.530 |
acle | +1.505 |
Oracle | +1.480 |
Neg logit contributions | |
sanction | -1.773 |
Unsure | -1.716 |
hey | -1.669 |
cul | -1.653 |
kinetic | -1.646 |
Token | in |
Token ID | 287 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
Tea | +2.195 |
abit | +2.073 |
76561 | +2.025 |
acle | +1.993 |
Oracle | +1.957 |
Neg logit contributions | |
sanction | -1.566 |
Unsure | -1.516 |
hey | -1.457 |
cul | -1.445 |
CSI | -1.423 |
Token | their |
Token ID | 511 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
sanction | +5.838 |
sch | +5.563 |
Unsure | +5.544 |
hey | +5.534 |
cul | +5.408 |
Neg logit contributions | |
Tea | -8.922 |
abit | -8.340 |
76561 | -8.321 |
acle | -8.056 |
Oracle | -7.696 |
Token | infancy |
Token ID | 38120 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
Tea | +0.065 |
abit | +0.061 |
76561 | +0.061 |
acle | +0.059 |
Oracle | +0.058 |
Neg logit contributions | |
sanction | -0.043 |
Unsure | -0.041 |
hey | -0.040 |
cul | -0.039 |
sch | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
sanction | +3.270 |
Unsure | +3.084 |
hey | +3.029 |
sch | +3.015 |
cul | +3.010 |
Neg logit contributions | |
Tea | -4.021 |
76561 | -3.766 |
abit | -3.756 |
acle | -3.556 |
Oracle | -3.509 |
Token | such |
Token ID | 884 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
Tea | +0.371 |
abit | +0.347 |
76561 | +0.342 |
acle | +0.332 |
Oracle | +0.326 |
Neg logit contributions | |
sanction | -0.292 |
Unsure | -0.281 |
hey | -0.273 |
cul | -0.269 |
sch | -0.268 |
Token | as |
Token ID | 355 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
sanction | +0.054 |
Unsure | +0.052 |
hey | +0.050 |
cul | +0.050 |
sch | +0.049 |
Neg logit contributions | |
Tea | -0.089 |
abit | -0.083 |
76561 | -0.083 |
acle | -0.080 |
Oracle | -0.079 |
Token | robotics |
Token ID | 36359 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Tea | +13.434 |
abit | +13.208 |
Oracle | +12.800 |
acle | +12.522 |
76561 | +12.002 |
Neg logit contributions | |
Unsure | -10.686 |
sanction | -10.320 |
cul | -10.082 |
riction | -10.008 |
fw | -9.998 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
Tea | +1.990 |
abit | +1.853 |
76561 | +1.810 |
acle | +1.767 |
Oracle | +1.737 |
Neg logit contributions | |
sanction | -1.718 |
Unsure | -1.664 |
hey | -1.606 |
cul | -1.588 |
sch | -1.579 |
Token | artificial |
Token ID | 11666 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
Tea | +10.678 |
abit | +10.191 |
Oracle | +9.886 |
acle | +9.855 |
76561 | +9.640 |
Neg logit contributions | |
Unsure | -9.584 |
sanction | -9.073 |
riction | -8.959 |
malink | -8.742 |
fw | -8.724 |
Token | intelligence |
Token ID | 4430 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
Tea | +3.417 |
abit | +3.164 |
76561 | +2.998 |
acle | +2.972 |
Oracle | +2.947 |
Neg logit contributions | |
sanction | -3.733 |
Unsure | -3.720 |
hey | -3.508 |
cul | -3.495 |
fw | -3.476 |
Token | , |
Token ID | 11 |
Feature activation | +1.71e+01 |
Pos logit contributions | |
Tea | +3.991 |
abit | +3.725 |
acle | +3.579 |
76561 | +3.566 |
Oracle | +3.513 |
Neg logit contributions | |
sanction | -3.651 |
Unsure | -3.598 |
hey | -3.420 |
cul | -3.391 |
sch | -3.353 |
Token | So |
Token ID | 1406 |
Feature activation | +9.65e+00 |
Pos logit contributions | |
Tea | +6.049 |
Oracle | +5.588 |
acle | +5.519 |
76561 | +5.505 |
abit | +5.505 |
Neg logit contributions | |
sanction | -4.024 |
proble | -3.645 |
cul | -3.570 |
riction | -3.558 |
malink | -3.531 |
Token | , |
Token ID | 11 |
Feature activation | +8.79e+00 |
Pos logit contributions | |
Tea | +7.118 |
abit | +6.637 |
Oracle | +6.631 |
acle | +6.582 |
76561 | +6.454 |
Neg logit contributions | |
sanction | -6.722 |
Unsure | -6.635 |
malink | -6.357 |
opoly | -6.290 |
fw | -6.238 |
Token | Earth |
Token ID | 3668 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
Tea | +6.582 |
abit | +6.204 |
Oracle | +6.156 |
acle | +6.151 |
76561 | +6.092 |
Neg logit contributions | |
sanction | -6.072 |
Unsure | -5.941 |
malink | -5.672 |
riction | -5.657 |
opoly | -5.656 |
Token | 's |
Token ID | 338 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
Tea | +8.894 |
abit | +8.530 |
acle | +8.464 |
76561 | +8.184 |
Oracle | +8.076 |
Neg logit contributions | |
sanction | -9.728 |
Unsure | -9.451 |
malink | -9.338 |
fw | -9.068 |
opoly | -9.043 |
Token | orbit |
Token ID | 13066 |
Feature activation | +7.80e+00 |
Pos logit contributions | |
sanction | +2.011 |
Unsure | +1.909 |
hey | +1.879 |
kinetic | +1.876 |
sch | +1.855 |
Neg logit contributions | |
Tea | -2.894 |
abit | -2.706 |
76561 | -2.695 |
acle | -2.559 |
Oracle | -2.514 |
Token | is |
Token ID | 318 |
Feature activation | +2.35e+01 |
Pos logit contributions | |
Tea | +6.054 |
abit | +5.793 |
acle | +5.696 |
76561 | +5.628 |
Oracle | +5.459 |
Neg logit contributions | |
sanction | -5.373 |
Unsure | -5.255 |
malink | -4.987 |
hey | -4.969 |
opoly | -4.948 |
Token | the |
Token ID | 262 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
Oracle | +14.003 |
Tea | +13.675 |
acle | +13.432 |
abit | +13.137 |
76561 | +12.782 |
Neg logit contributions | |
opoly | -13.909 |
malink | -13.864 |
sanction | -13.658 |
Unsure | -13.560 |
fw | -12.929 |
Token | circumference |
Token ID | 38447 |
Feature activation | +7.61e+00 |
Pos logit contributions | |
Tea | +2.319 |
abit | +2.187 |
76561 | +2.153 |
acle | +2.122 |
Oracle | +2.090 |
Neg logit contributions | |
sanction | -1.476 |
Unsure | -1.423 |
hey | -1.353 |
cul | -1.348 |
sch | -1.331 |
Token | of |
Token ID | 286 |
Feature activation | +9.71e+00 |
Pos logit contributions | |
Tea | +5.335 |
abit | +5.081 |
acle | +4.927 |
76561 | +4.903 |
Oracle | +4.875 |
Neg logit contributions | |
sanction | -5.736 |
Unsure | -5.665 |
opoly | -5.394 |
malink | -5.377 |
hey | -5.375 |
Token | a |
Token ID | 257 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Tea | +6.842 |
abit | +6.472 |
Oracle | +6.355 |
acle | +6.295 |
76561 | +6.189 |
Neg logit contributions | |
Unsure | -7.060 |
sanction | -7.058 |
riction | -6.626 |
proble | -6.624 |
fw | -6.615 |
Token | circle |
Token ID | 9197 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
Tea | +1.186 |
abit | +1.116 |
76561 | +1.100 |
acle | +1.078 |
Oracle | +1.060 |
Neg logit contributions | |
sanction | -0.741 |
Unsure | -0.715 |
hey | -0.684 |
cul | -0.678 |
sch | -0.668 |
Token | this |
Token ID | 428 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
sanction | +2.927 |
Unsure | +2.815 |
hey | +2.775 |
sch | +2.750 |
CSI | +2.704 |
Neg logit contributions | |
Tea | -4.042 |
76561 | -3.808 |
abit | -3.787 |
acle | -3.586 |
Oracle | -3.487 |
Token | : |
Token ID | 25 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
sanction | +2.265 |
Unsure | +2.185 |
hey | +2.139 |
sch | +2.117 |
kinetic | +2.087 |
Neg logit contributions | |
Tea | -2.856 |
abit | -2.672 |
76561 | -2.667 |
acle | -2.533 |
Oracle | -2.461 |
Token |
|
Token ID | 198 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
sanction | +2.893 |
Unsure | +2.813 |
hey | +2.786 |
sch | +2.712 |
cul | +2.676 |
Neg logit contributions | |
Tea | -4.199 |
76561 | -3.961 |
abit | -3.929 |
acle | -3.729 |
Oracle | -3.646 |
Token |
|
Token ID | 198 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
sanction | +1.698 |
Unsure | +1.676 |
hey | +1.620 |
sch | +1.584 |
cul | +1.579 |
Neg logit contributions | |
Tea | -2.447 |
abit | -2.320 |
76561 | -2.302 |
acle | -2.194 |
Oracle | -2.149 |
Token | + |
Token ID | 10 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
Tea | +0.510 |
abit | +0.474 |
76561 | +0.466 |
acle | +0.452 |
Oracle | +0.442 |
Neg logit contributions | |
sanction | -0.471 |
Unsure | -0.455 |
hey | -0.441 |
cul | -0.436 |
sch | -0.435 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +2.28e+01 |
Pos logit contributions | |
Tea | +4.334 |
abit | +3.664 |
acle | +3.244 |
Oracle | +3.111 |
Oracle | +3.097 |
Neg logit contributions | |
proble | -14.898 |
sanction | -14.826 |
kinetic | -14.142 |
sch | -13.941 |
Unsure | -13.889 |
Token | --+ |
Token ID | 44785 |
Feature activation | -7.33e+00 |
Pos logit contributions | |
acle | +6.665 |
Tea | +6.393 |
abit | +6.178 |
76561 | +5.271 |
Oracle | +5.168 |
Neg logit contributions | |
proble | -24.075 |
sanction | -21.736 |
condem | -21.610 |
princ | -21.456 |
subur | -21.279 |
Token | | |
Token ID | 930 |
Feature activation | -9.41e+00 |
Pos logit contributions | |
sanction | +4.643 |
Unsure | +4.632 |
hey | +4.546 |
sch | +4.410 |
CSI | +4.345 |
Neg logit contributions | |
Tea | -6.228 |
abit | -5.879 |
76561 | -5.847 |
acle | -5.507 |
ethy | -5.304 |
Token | ... |
Token ID | 2644 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
sanction | +4.339 |
hey | +4.161 |
Unsure | +4.147 |
sch | +4.072 |
wow | +3.824 |
Neg logit contributions | |
Tea | -9.491 |
76561 | -9.098 |
abit | -8.865 |
acle | -8.494 |
Oracle | -8.308 |
Token | | |
Token ID | 930 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
sanction | +1.248 |
Unsure | +1.213 |
hey | +1.184 |
sch | +1.162 |
cul | +1.161 |
Neg logit contributions | |
Tea | -1.348 |
abit | -1.261 |
76561 | -1.246 |
acle | -1.195 |
Oracle | -1.165 |
Token | + |
Token ID | 1343 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
Tea | +0.634 |
abit | +0.591 |
76561 | +0.581 |
acle | +0.567 |
Oracle | +0.555 |
Neg logit contributions | |
sanction | -0.552 |
Unsure | -0.532 |
hey | -0.515 |
cul | -0.512 |
sch | -0.508 |
Token |
|
Token ID | 198 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
sanction | +1.780 |
Unsure | +1.758 |
hey | +1.698 |
sch | +1.662 |
cul | +1.650 |
Neg logit contributions | |
Tea | -2.572 |
abit | -2.447 |
76561 | -2.422 |
acle | -2.317 |
Oracle | -2.262 |
Token | La |
Token ID | 14772 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
Tea | +1.823 |
abit | +1.673 |
76561 | +1.662 |
acle | +1.611 |
Oracle | +1.575 |
Neg logit contributions | |
sanction | -1.307 |
Unsure | -1.246 |
hey | -1.206 |
kinetic | -1.186 |
sch | -1.185 |
Token | Rue |
Token ID | 45363 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
sanction | +0.390 |
Unsure | +0.376 |
hey | +0.362 |
cul | +0.357 |
sch | +0.355 |
Neg logit contributions | |
Tea | -0.599 |
abit | -0.563 |
76561 | -0.559 |
acle | -0.542 |
Oracle | -0.531 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
sanction | +0.860 |
Unsure | +0.823 |
hey | +0.803 |
sch | +0.793 |
cul | +0.790 |
Neg logit contributions | |
Tea | -1.021 |
abit | -0.952 |
76561 | -0.943 |
acle | -0.908 |
Oracle | -0.887 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
Tea | +0.898 |
abit | +0.835 |
76561 | +0.822 |
acle | +0.800 |
Oracle | +0.786 |
Neg logit contributions | |
sanction | -0.821 |
Unsure | -0.794 |
hey | -0.772 |
cul | -0.765 |
sch | -0.758 |
Token | longtime |
Token ID | 15076 |
Feature activation | +2.03e+01 |
Pos logit contributions | |
Tea | +9.341 |
Oracle | +8.724 |
acle | +8.661 |
abit | +8.633 |
76561 | +8.488 |
Neg logit contributions | |
Unsure | -7.907 |
fw | -7.654 |
sanction | -7.648 |
malink | -7.641 |
cul | -7.607 |
Token | Guatem |
Token ID | 28171 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Tea | +13.821 |
Oracle | +13.248 |
acle | +12.767 |
abit | +12.390 |
76561 | +12.088 |
Neg logit contributions | |
riction | -11.661 |
Unsure | -11.644 |
malink | -11.460 |
fw | -11.380 |
� | -11.288 |
Token | alan |
Token ID | 25786 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
Tea | +1.296 |
abit | +1.191 |
76561 | +1.156 |
acle | +1.120 |
Oracle | +1.092 |
Neg logit contributions | |
sanction | -1.736 |
Unsure | -1.687 |
hey | -1.644 |
cul | -1.627 |
sch | -1.621 |
Token | human |
Token ID | 1692 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
Tea | +10.706 |
Oracle | +9.660 |
abit | +9.462 |
76561 | +9.449 |
acle | +9.377 |
Neg logit contributions | |
Unsure | -9.876 |
riction | -9.558 |
malink | -9.541 |
fw | -9.519 |
sanction | -9.379 |
Token | rights |
Token ID | 2489 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
Tea | +5.253 |
abit | +4.682 |
acle | +4.443 |
76561 | +4.389 |
Oracle | +4.209 |
Neg logit contributions | |
Unsure | -11.250 |
sanction | -10.677 |
malink | -10.514 |
cul | -10.513 |
riction | -10.490 |
Token | activist |
Token ID | 11276 |
Feature activation | +9.37e+00 |
Pos logit contributions | |
Tea | +2.565 |
abit | +2.397 |
76561 | +2.347 |
acle | +2.295 |
Oracle | +2.270 |
Neg logit contributions | |
sanction | -2.406 |
Unsure | -2.380 |
cul | -2.274 |
hey | -2.250 |
riction | -2.226 |
Token | � |
Token ID | 447 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Tea | +6.992 |
abit | +6.479 |
acle | +6.368 |
Oracle | +6.353 |
76561 | +6.263 |
Neg logit contributions | |
Unsure | -5.853 |
sanction | -5.737 |
hey | -5.507 |
cul | -5.459 |
fw | -5.456 |
Token | � |
Token ID | 247 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
Tea | +1.510 |
abit | +1.415 |
76561 | +1.389 |
acle | +1.352 |
Oracle | +1.322 |
Neg logit contributions | |
sanction | -1.146 |
Unsure | -1.100 |
hey | -1.066 |
cul | -1.057 |
sch | -1.052 |
Token | its |
Token ID | 663 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
Tea | +5.017 |
abit | +4.670 |
76561 | +4.553 |
acle | +4.443 |
Oracle | +4.367 |
Neg logit contributions | |
sanction | -4.293 |
Unsure | -4.290 |
hey | -4.100 |
CSI | -4.025 |
sch | -4.019 |
Token | oil |
Token ID | 3056 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Tea | +1.922 |
abit | +1.787 |
76561 | +1.755 |
acle | +1.716 |
Oracle | +1.693 |
Neg logit contributions | |
sanction | -1.670 |
Unsure | -1.651 |
cul | -1.567 |
hey | -1.565 |
sch | -1.543 |
Token | production |
Token ID | 3227 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
sanction | +1.760 |
Unsure | +1.653 |
hey | +1.643 |
cul | +1.618 |
sch | +1.616 |
Neg logit contributions | |
Tea | -2.379 |
abit | -2.226 |
76561 | -2.202 |
acle | -2.138 |
Oracle | -2.088 |
Token | to |
Token ID | 284 |
Feature activation | +1.72e+01 |
Pos logit contributions | |
Tea | +2.391 |
abit | +2.249 |
76561 | +2.202 |
acle | +2.150 |
Oracle | +2.113 |
Neg logit contributions | |
sanction | -2.123 |
Unsure | -2.075 |
hey | -1.983 |
cul | -1.981 |
sch | -1.965 |
Token | � |
Token ID | 564 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
Tea | +12.910 |
abit | +12.023 |
acle | +11.844 |
76561 | +11.721 |
Oracle | +11.712 |
Neg logit contributions | |
Unsure | -9.603 |
riction | -9.059 |
fw | -8.938 |
malink | -8.879 |
proble | -8.860 |
Token | � |
Token ID | 246 |
Feature activation | +9.15e+00 |
Pos logit contributions | |
Tea | +5.505 |
abit | +5.131 |
76561 | +4.917 |
acle | +4.869 |
Oracle | +4.729 |
Neg logit contributions | |
sanction | -4.894 |
Unsure | -4.629 |
sch | -4.525 |
hey | -4.481 |
cul | -4.442 |
Token | pen |
Token ID | 3617 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
Tea | +8.025 |
abit | +7.466 |
76561 | +7.224 |
acle | +7.072 |
Oracle | +6.980 |
Neg logit contributions | |
sanction | -5.462 |
Unsure | -5.405 |
kinetic | -5.066 |
proble | -5.058 |
hey | -5.052 |
Token | al |
Token ID | 282 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Tea | +4.327 |
abit | +4.027 |
76561 | +3.916 |
acle | +3.882 |
Oracle | +3.751 |
Neg logit contributions | |
sanction | -4.871 |
Unsure | -4.755 |
hey | -4.630 |
CSI | -4.544 |
sch | -4.536 |
Token | ize |
Token ID | 1096 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Tea | +1.166 |
abit | +1.091 |
76561 | +1.070 |
acle | +1.044 |
Oracle | +1.025 |
Neg logit contributions | |
sanction | -0.949 |
Unsure | -0.920 |
hey | -0.892 |
sch | -0.877 |
cul | -0.876 |
Token | H |
Token ID | 367 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
Tea | +0.654 |
abit | +0.615 |
76561 | +0.605 |
acle | +0.591 |
Oracle | +0.581 |
Neg logit contributions | |
sanction | -0.463 |
Unsure | -0.446 |
hey | -0.431 |
cul | -0.426 |
sch | -0.422 |
Token | CCC |
Token ID | 46361 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
sanction | +2.604 |
Unsure | +2.520 |
cul | +2.506 |
hey | +2.496 |
sch | +2.454 |
Neg logit contributions | |
Tea | -2.786 |
76561 | -2.632 |
abit | -2.536 |
acle | -2.427 |
Oracle | -2.410 |
Token | , |
Token ID | 11 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
Tea | +3.883 |
abit | +3.608 |
76561 | +3.499 |
Oracle | +3.444 |
acle | +3.443 |
Neg logit contributions | |
sanction | -3.311 |
Unsure | -3.218 |
hey | -3.106 |
cul | -3.100 |
fw | -3.064 |
Token | if |
Token ID | 611 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
Tea | +3.926 |
abit | +3.719 |
Oracle | +3.599 |
76561 | +3.584 |
acle | +3.583 |
Neg logit contributions | |
sanction | -3.392 |
Unsure | -3.310 |
cul | -3.189 |
fw | -3.171 |
hey | -3.162 |
Token | approved |
Token ID | 6325 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
sanction | +1.925 |
Unsure | +1.751 |
hey | +1.740 |
sch | +1.717 |
kinetic | +1.678 |
Neg logit contributions | |
Tea | -4.143 |
76561 | -3.961 |
abit | -3.899 |
acle | -3.758 |
Oracle | -3.635 |
Token | by |
Token ID | 416 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
sanction | +2.491 |
Unsure | +2.341 |
hey | +2.307 |
sch | +2.266 |
kinetic | +2.254 |
Neg logit contributions | |
Tea | -3.281 |
76561 | -3.061 |
abit | -3.055 |
acle | -2.926 |
Oracle | -2.851 |
Token | college |
Token ID | 4152 |
Feature activation | -8.94e+00 |
Pos logit contributions | |
Tea | +1.389 |
abit | +1.305 |
76561 | +1.269 |
acle | +1.253 |
Oracle | +1.234 |
Neg logit contributions | |
sanction | -1.148 |
Unsure | -1.117 |
hey | -1.079 |
cul | -1.071 |
sch | -1.055 |
Token | officials |
Token ID | 2828 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
sanction | +4.553 |
hey | +4.131 |
sch | +4.085 |
Unsure | +3.977 |
kinetic | +3.914 |
Neg logit contributions | |
Tea | -8.911 |
76561 | -8.443 |
abit | -8.341 |
acle | -7.933 |
Oracle | -7.791 |
Token | , |
Token ID | 11 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
sanction | +1.197 |
Unsure | +1.143 |
hey | +1.119 |
sch | +1.098 |
cul | +1.096 |
Neg logit contributions | |
Tea | -1.552 |
abit | -1.450 |
76561 | -1.443 |
acle | -1.390 |
Oracle | -1.356 |
Token | would |
Token ID | 561 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Tea | +5.187 |
abit | +4.788 |
Oracle | +4.681 |
76561 | +4.643 |
acle | +4.571 |
Neg logit contributions | |
Unsure | -5.506 |
sanction | -5.448 |
fw | -5.321 |
riction | -5.306 |
cul | -5.275 |
Token | give |
Token ID | 1577 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
sanction | +0.386 |
Unsure | +0.370 |
hey | +0.359 |
cul | +0.354 |
sch | +0.354 |
Neg logit contributions | |
Tea | -0.487 |
abit | -0.455 |
76561 | -0.451 |
acle | -0.435 |
Oracle | -0.426 |
Token | to |
Token ID | 284 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Tea | +4.872 |
abit | +4.510 |
76561 | +4.341 |
acle | +4.246 |
Oracle | +4.222 |
Neg logit contributions | |
sanction | -5.235 |
Unsure | -5.214 |
hey | -5.032 |
opoly | -5.030 |
CSI | -5.014 |
Token | coordinate |
Token ID | 20435 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Tea | +2.418 |
abit | +2.290 |
76561 | +2.218 |
acle | +2.201 |
Oracle | +2.167 |
Neg logit contributions | |
sanction | -1.656 |
Unsure | -1.646 |
hey | -1.573 |
cul | -1.570 |
CSI | -1.550 |
Token | certain |
Token ID | 1728 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
Tea | +2.143 |
abit | +2.007 |
76561 | +1.962 |
acle | +1.917 |
Oracle | +1.888 |
Neg logit contributions | |
sanction | -1.754 |
Unsure | -1.728 |
hey | -1.656 |
cul | -1.648 |
opoly | -1.621 |
Token | measures |
Token ID | 5260 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Tea | +4.694 |
abit | +4.431 |
76561 | +4.314 |
acle | +4.218 |
Oracle | +4.184 |
Neg logit contributions | |
Unsure | -4.435 |
sanction | -4.339 |
cul | -4.212 |
opoly | -4.169 |
hey | -4.161 |
Token | they |
Token ID | 484 |
Feature activation | -6.92e+00 |
Pos logit contributions | |
Tea | +1.266 |
abit | +1.177 |
76561 | +1.153 |
acle | +1.119 |
Oracle | +1.097 |
Neg logit contributions | |
sanction | -1.258 |
Unsure | -1.223 |
hey | -1.188 |
cul | -1.178 |
sch | -1.170 |
Token | might |
Token ID | 1244 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
sanction | +4.426 |
Unsure | +4.051 |
sch | +3.899 |
hey | +3.842 |
cul | +3.824 |
Neg logit contributions | |
Tea | -6.298 |
76561 | -5.940 |
abit | -5.826 |
acle | -5.654 |
Oracle | -5.516 |
Token | take |
Token ID | 1011 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
sanction | +1.448 |
Unsure | +1.370 |
hey | +1.324 |
sch | +1.315 |
cul | +1.309 |
Neg logit contributions | |
Tea | -1.750 |
76561 | -1.623 |
abit | -1.613 |
acle | -1.550 |
Oracle | -1.513 |
Token | against |
Token ID | 1028 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Tea | +1.130 |
abit | +1.052 |
76561 | +1.030 |
acle | +0.998 |
Oracle | +0.979 |
Neg logit contributions | |
sanction | -1.181 |
Unsure | -1.151 |
hey | -1.118 |
cul | -1.109 |
sch | -1.102 |
Token | that |
Token ID | 326 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Tea | +1.634 |
abit | +1.523 |
76561 | +1.498 |
acle | +1.461 |
Oracle | +1.440 |
Neg logit contributions | |
sanction | -1.348 |
Unsure | -1.322 |
hey | -1.263 |
cul | -1.258 |
sch | -1.241 |
Token | hostile |
Token ID | 12524 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Tea | +0.300 |
abit | +0.280 |
76561 | +0.276 |
acle | +0.268 |
Oracle | +0.262 |
Neg logit contributions | |
sanction | -0.254 |
Unsure | -0.245 |
hey | -0.238 |
cul | -0.236 |
sch | -0.234 |
Token | country |
Token ID | 1499 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
Tea | +2.213 |
abit | +2.080 |
76561 | +2.038 |
acle | +2.012 |
Oracle | +1.985 |
Neg logit contributions | |
sanction | -1.665 |
Unsure | -1.630 |
cul | -1.562 |
hey | -1.561 |
fw | -1.538 |
Token | % |
Token ID | 4 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
sanction | +4.111 |
Unsure | +3.957 |
hey | +3.870 |
sch | +3.769 |
cul | +3.731 |
Neg logit contributions | |
Tea | -6.445 |
76561 | -6.072 |
abit | -6.042 |
acle | -5.780 |
Oracle | -5.519 |
Token | of |
Token ID | 286 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
sanction | +2.406 |
Unsure | +2.305 |
hey | +2.263 |
sch | +2.193 |
cul | +2.191 |
Neg logit contributions | |
Tea | -3.067 |
abit | -2.846 |
76561 | -2.834 |
acle | -2.712 |
Oracle | -2.629 |
Token | all |
Token ID | 477 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
sanction | +1.068 |
Unsure | +1.022 |
hey | +1.003 |
sch | +0.984 |
cul | +0.982 |
Neg logit contributions | |
Tea | -1.232 |
abit | -1.151 |
76561 | -1.140 |
acle | -1.094 |
Oracle | -1.062 |
Token | Android |
Token ID | 5565 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Tea | +0.051 |
abit | +0.047 |
76561 | +0.047 |
acle | +0.045 |
Oracle | +0.044 |
Neg logit contributions | |
sanction | -0.048 |
Unsure | -0.046 |
hey | -0.045 |
cul | -0.045 |
sch | -0.044 |
Token | apps |
Token ID | 6725 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
sanction | +0.788 |
Unsure | +0.760 |
hey | +0.743 |
cul | +0.733 |
sch | +0.732 |
Neg logit contributions | |
Tea | -0.802 |
abit | -0.745 |
76561 | -0.737 |
acle | -0.708 |
Oracle | -0.690 |
Token | scale |
Token ID | 5046 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
Tea | +0.956 |
abit | +0.895 |
76561 | +0.881 |
acle | +0.861 |
Oracle | +0.848 |
Neg logit contributions | |
sanction | -0.699 |
Unsure | -0.675 |
hey | -0.650 |
cul | -0.644 |
sch | -0.640 |
Token | almost |
Token ID | 2048 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Tea | +3.003 |
abit | +2.830 |
76561 | +2.715 |
acle | +2.701 |
Oracle | +2.690 |
Neg logit contributions | |
sanction | -2.578 |
Unsure | -2.510 |
hey | -2.416 |
cul | -2.395 |
riction | -2.395 |
Token | perfectly |
Token ID | 7138 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
sanction | +0.338 |
Unsure | +0.325 |
hey | +0.315 |
cul | +0.311 |
sch | +0.310 |
Neg logit contributions | |
Tea | -0.426 |
abit | -0.398 |
76561 | -0.394 |
acle | -0.381 |
Oracle | -0.373 |
Token | ," |
Token ID | 553 |
Feature activation | +9.75e+00 |
Pos logit contributions | |
Tea | +0.161 |
abit | +0.151 |
76561 | +0.149 |
acle | +0.144 |
Oracle | +0.141 |
Neg logit contributions | |
sanction | -0.132 |
Unsure | -0.127 |
hey | -0.124 |
cul | -0.122 |
sch | -0.122 |
Token | Ber |
Token ID | 4312 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Tea | +6.895 |
Oracle | +6.622 |
abit | +6.509 |
acle | +6.322 |
76561 | +6.133 |
Neg logit contributions | |
sanction | -7.095 |
Unsure | -6.922 |
cul | -6.664 |
riction | -6.632 |
kinetic | -6.607 |
Token | ne |
Token ID | 710 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
sanction | +0.656 |
Unsure | +0.633 |
hey | +0.611 |
cul | +0.607 |
sch | +0.600 |
Neg logit contributions | |
Tea | -1.042 |
abit | -0.979 |
76561 | -0.975 |
acle | -0.939 |
Oracle | -0.928 |
Token | him |
Token ID | 683 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
Tea | +0.250 |
abit | +0.233 |
76561 | +0.230 |
acle | +0.223 |
Oracle | +0.219 |
Neg logit contributions | |
sanction | -0.211 |
Unsure | -0.204 |
hey | -0.198 |
cul | -0.196 |
sch | -0.195 |
Token | to |
Token ID | 284 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Tea | +0.292 |
abit | +0.272 |
76561 | +0.268 |
acle | +0.259 |
Oracle | +0.254 |
Neg logit contributions | |
sanction | -0.273 |
Unsure | -0.264 |
hey | -0.256 |
cul | -0.254 |
sch | -0.252 |
Token | still |
Token ID | 991 |
Feature activation | -7.22e+00 |
Pos logit contributions | |
sanction | +1.573 |
Unsure | +1.493 |
hey | +1.466 |
sch | +1.448 |
cul | +1.429 |
Neg logit contributions | |
Tea | -2.079 |
76561 | -1.942 |
abit | -1.934 |
acle | -1.837 |
Oracle | -1.805 |
Token | find |
Token ID | 1064 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
sanction | +4.839 |
Unsure | +4.527 |
sch | +4.513 |
hey | +4.508 |
wow | +4.419 |
Neg logit contributions | |
Tea | -6.256 |
76561 | -5.966 |
abit | -5.703 |
Oracle | -5.376 |
acle | -5.279 |
Token | success |
Token ID | 1943 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
sanction | +1.944 |
hey | +1.821 |
Unsure | +1.807 |
sch | +1.780 |
kinetic | +1.771 |
Neg logit contributions | |
Tea | -2.740 |
abit | -2.585 |
76561 | -2.557 |
acle | -2.464 |
Oracle | -2.401 |
Token | against |
Token ID | 1028 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
sanction | +6.425 |
hey | +6.086 |
sch | +5.885 |
win | +5.728 |
Unsure | +5.718 |
Neg logit contributions | |
Tea | -9.294 |
76561 | -8.798 |
abit | -8.643 |
acle | -8.088 |
ethy | -7.966 |
Token | this |
Token ID | 428 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
Tea | +4.086 |
abit | +3.841 |
76561 | +3.708 |
acle | +3.705 |
Oracle | +3.695 |
Neg logit contributions | |
Unsure | -3.632 |
sanction | -3.612 |
cul | -3.451 |
opoly | -3.386 |
malink | -3.379 |
Token | defense |
Token ID | 3761 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
Tea | +6.387 |
abit | +5.898 |
acle | +5.874 |
Oracle | +5.865 |
76561 | +5.617 |
Neg logit contributions | |
Unsure | -6.102 |
sanction | -6.005 |
cul | -5.821 |
malink | -5.716 |
opoly | -5.705 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
sanction | +3.082 |
hey | +2.894 |
Unsure | +2.861 |
sch | +2.827 |
kinetic | +2.761 |
Neg logit contributions | |
Tea | -4.334 |
76561 | -4.073 |
abit | -4.047 |
acle | -3.829 |
Oracle | -3.743 |
Token | especially |
Token ID | 2592 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
sanction | +1.215 |
Unsure | +1.156 |
hey | +1.137 |
sch | +1.110 |
cul | +1.106 |
Neg logit contributions | |
Tea | -1.785 |
abit | -1.676 |
76561 | -1.654 |
acle | -1.602 |
Oracle | -1.569 |
Token | at |
Token ID | 379 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Tea | +1.172 |
abit | +1.091 |
76561 | +1.075 |
acle | +1.049 |
Oracle | +1.031 |
Neg logit contributions | |
sanction | -1.007 |
Unsure | -0.979 |
cul | -0.941 |
hey | -0.938 |
sch | -0.926 |
Token | from |
Token ID | 422 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
sanction | +0.685 |
Unsure | +0.653 |
hey | +0.635 |
sch | +0.625 |
cul | +0.623 |
Neg logit contributions | |
Tea | -1.011 |
abit | -0.952 |
76561 | -0.943 |
acle | -0.912 |
Oracle | -0.893 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Tea | +2.225 |
abit | +2.063 |
76561 | +2.033 |
acle | +1.988 |
Oracle | +1.959 |
Neg logit contributions | |
sanction | -1.779 |
Unsure | -1.726 |
hey | -1.660 |
cul | -1.656 |
kinetic | -1.625 |
Token | common |
Token ID | 2219 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
Tea | +0.959 |
abit | +0.897 |
76561 | +0.883 |
acle | +0.861 |
Oracle | +0.844 |
Neg logit contributions | |
sanction | -0.724 |
Unsure | -0.699 |
hey | -0.674 |
cul | -0.668 |
sch | -0.660 |
Token | problem |
Token ID | 1917 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
sanction | +2.888 |
Unsure | +2.716 |
sch | +2.679 |
hey | +2.669 |
cul | +2.612 |
Neg logit contributions | |
Tea | -4.259 |
abit | -4.034 |
76561 | -4.022 |
acle | -3.823 |
Oracle | -3.746 |
Token | . |
Token ID | 13 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
Tea | +1.533 |
abit | +1.431 |
76561 | +1.402 |
acle | +1.367 |
Oracle | +1.340 |
Neg logit contributions | |
sanction | -1.347 |
Unsure | -1.304 |
hey | -1.261 |
cul | -1.250 |
kinetic | -1.237 |
Token | They |
Token ID | 1119 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
Tea | +3.220 |
abit | +3.008 |
76561 | +2.980 |
acle | +2.906 |
Oracle | +2.870 |
Neg logit contributions | |
sanction | -1.785 |
Unsure | -1.661 |
hey | -1.613 |
cul | -1.602 |
kinetic | -1.589 |
Token | use |
Token ID | 779 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
Tea | +8.791 |
abit | +8.229 |
acle | +8.112 |
Oracle | +7.921 |
76561 | +7.621 |
Neg logit contributions | |
Unsure | -7.080 |
sanction | -6.970 |
riction | -6.891 |
opoly | -6.888 |
kinetic | -6.882 |
Token | heat |
Token ID | 4894 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
Tea | +8.189 |
abit | +7.564 |
acle | +7.468 |
76561 | +7.372 |
Oracle | +7.325 |
Neg logit contributions | |
sanction | -6.455 |
Unsure | -6.308 |
fw | -6.190 |
opoly | -6.004 |
win | -5.948 |
Token | . |
Token ID | 13 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
sanction | +0.396 |
Unsure | +0.381 |
hey | +0.370 |
cul | +0.366 |
sch | +0.365 |
Neg logit contributions | |
Tea | -0.471 |
abit | -0.441 |
76561 | -0.436 |
acle | -0.421 |
Oracle | -0.412 |
Token | Heat |
Token ID | 12308 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Tea | +0.921 |
abit | +0.867 |
76561 | +0.858 |
acle | +0.837 |
Oracle | +0.824 |
Neg logit contributions | |
sanction | -0.498 |
Unsure | -0.470 |
hey | -0.454 |
cul | -0.448 |
sch | -0.445 |
Token | will |
Token ID | 481 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
sanction | +1.247 |
Unsure | +1.200 |
hey | +1.165 |
sch | +1.150 |
cul | +1.150 |
Neg logit contributions | |
Tea | -1.703 |
abit | -1.603 |
76561 | -1.594 |
acle | -1.534 |
Oracle | -1.503 |
Token | o |
Token ID | 267 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
sanction | +4.501 |
Unsure | +4.340 |
hey | +4.326 |
sch | +4.287 |
cul | +4.234 |
Neg logit contributions | |
Tea | -6.390 |
76561 | -6.129 |
abit | -5.975 |
acle | -5.764 |
Oracle | -5.667 |
Token | Kau |
Token ID | 28148 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
sanction | +3.565 |
Unsure | +3.435 |
hey | +3.395 |
sch | +3.351 |
cul | +3.329 |
Neg logit contributions | |
Tea | -5.209 |
abit | -4.875 |
76561 | -4.864 |
acle | -4.694 |
Oracle | -4.563 |
Token | a |
Token ID | 64 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
sanction | +1.213 |
Unsure | +1.175 |
hey | +1.151 |
cul | +1.142 |
sch | +1.136 |
Neg logit contributions | |
Tea | -1.133 |
76561 | -1.044 |
abit | -1.041 |
acle | -0.992 |
Oracle | -0.976 |
Token | � |
Token ID | 134 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
sch | +9.455 |
hey | +9.231 |
cul | +9.033 |
sanction | +9.003 |
Unsure | +8.985 |
Neg logit contributions | |
Tea | -15.973 |
76561 | -15.603 |
abit | -14.813 |
acle | -14.595 |
Oracle | -14.349 |
Token | � |
Token ID | 119 |
Feature activation | -9.29e+00 |
Pos logit contributions | |
sanction | +0.889 |
Unsure | +0.848 |
hey | +0.805 |
cul | +0.791 |
sch | +0.778 |
Neg logit contributions | |
Tea | -2.068 |
abit | -1.959 |
76561 | -1.944 |
acle | -1.889 |
Oracle | -1.867 |
Token | i |
Token ID | 72 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
sanction | +6.002 |
cul | +5.923 |
Unsure | +5.762 |
hey | +5.739 |
win | +5.659 |
Neg logit contributions | |
Tea | -7.368 |
76561 | -7.172 |
abit | -6.833 |
Oracle | -6.636 |
acle | -6.531 |
Token | , |
Token ID | 11 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
sanction | +6.931 |
hey | +6.764 |
Unsure | +6.763 |
sch | +6.717 |
cul | +6.466 |
Neg logit contributions | |
Tea | -10.138 |
76561 | -9.946 |
abit | -9.480 |
acle | -9.091 |
Oracle | -8.984 |
Token | a |
Token ID | 257 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
sanction | +6.734 |
Unsure | +6.593 |
hey | +6.585 |
sch | +6.523 |
cul | +6.251 |
Neg logit contributions | |
Tea | -10.309 |
76561 | -9.858 |
abit | -9.763 |
acle | -9.353 |
Oracle | -9.144 |
Token | p |
Token ID | 279 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
sanction | +3.727 |
Unsure | +3.566 |
hey | +3.554 |
sch | +3.522 |
cul | +3.422 |
Neg logit contributions | |
Tea | -6.466 |
76561 | -6.119 |
abit | -6.067 |
acle | -5.809 |
Oracle | -5.745 |
Token | ē |
Token ID | 27092 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
sanction | +1.621 |
Unsure | +1.579 |
hey | +1.542 |
cul | +1.532 |
sch | +1.517 |
Neg logit contributions | |
Tea | -1.628 |
76561 | -1.507 |
abit | -1.500 |
acle | -1.424 |
Oracle | -1.407 |
Token | l |
Token ID | 75 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
sanction | +3.415 |
Unsure | +3.295 |
hey | +3.268 |
cul | +3.234 |
sch | +3.234 |
Neg logit contributions | |
Tea | -4.434 |
abit | -4.146 |
76561 | -4.139 |
acle | -3.927 |
Oracle | -3.878 |
Token | services |
Token ID | 2594 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
sanction | +3.334 |
Unsure | +3.141 |
hey | +3.107 |
sch | +3.071 |
kinetic | +3.019 |
Neg logit contributions | |
Tea | -4.054 |
76561 | -3.839 |
abit | -3.796 |
acle | -3.575 |
Oracle | -3.455 |
Token | to |
Token ID | 284 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
sanction | +2.911 |
Unsure | +2.732 |
hey | +2.677 |
sch | +2.616 |
cul | +2.603 |
Neg logit contributions | |
Tea | -4.491 |
76561 | -4.334 |
abit | -4.243 |
acle | -4.082 |
Oracle | -3.891 |
Token | include |
Token ID | 2291 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
sanction | +0.965 |
Unsure | +0.914 |
hey | +0.891 |
sch | +0.876 |
cul | +0.874 |
Neg logit contributions | |
Tea | -1.318 |
76561 | -1.232 |
abit | -1.229 |
acle | -1.178 |
Oracle | -1.148 |
Token | on |
Token ID | 319 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
sanction | +4.182 |
Unsure | +3.951 |
hey | +3.866 |
sch | +3.823 |
cul | +3.772 |
Neg logit contributions | |
Tea | -5.224 |
76561 | -5.022 |
abit | -4.852 |
acle | -4.626 |
ethy | -4.455 |
Token | their |
Token ID | 511 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
sanction | +3.632 |
Unsure | +3.419 |
hey | +3.389 |
sch | +3.326 |
cul | +3.290 |
Neg logit contributions | |
Tea | -4.890 |
76561 | -4.674 |
abit | -4.584 |
acle | -4.319 |
Oracle | -4.164 |
Token | Android |
Token ID | 5565 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
Tea | +0.386 |
abit | +0.360 |
76561 | +0.353 |
acle | +0.343 |
Oracle | +0.337 |
Neg logit contributions | |
sanction | -0.365 |
Unsure | -0.354 |
hey | -0.343 |
cul | -0.340 |
sch | -0.338 |
Token | phones |
Token ID | 9512 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
sanction | +2.741 |
Unsure | +2.619 |
hey | +2.580 |
sch | +2.545 |
cul | +2.538 |
Neg logit contributions | |
Tea | -3.162 |
76561 | -2.988 |
abit | -2.936 |
acle | -2.791 |
Oracle | -2.698 |
Token | . |
Token ID | 13 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
sanction | +3.249 |
Unsure | +3.104 |
hey | +3.045 |
cul | +2.997 |
sch | +2.987 |
Neg logit contributions | |
Tea | -3.796 |
76561 | -3.571 |
abit | -3.522 |
acle | -3.362 |
Oracle | -3.233 |
Token | We |
Token ID | 775 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Tea | +3.399 |
abit | +3.103 |
76561 | +3.094 |
Oracle | +3.088 |
acle | +3.056 |
Neg logit contributions | |
sanction | -2.363 |
cul | -2.189 |
kinetic | -2.184 |
Unsure | -2.169 |
hey | -2.161 |
Token | do |
Token ID | 466 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
Tea | +0.880 |
abit | +0.824 |
76561 | +0.804 |
acle | +0.788 |
Oracle | +0.774 |
Neg logit contributions | |
sanction | -0.721 |
Unsure | -0.700 |
hey | -0.679 |
cul | -0.672 |
sch | -0.666 |
Token | not |
Token ID | 407 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Tea | +5.922 |
abit | +5.459 |
Oracle | +5.194 |
acle | +5.180 |
76561 | +4.949 |
Neg logit contributions | |
Unsure | -6.245 |
sanction | -6.114 |
hey | -6.054 |
CSI | -6.044 |
win | -5.971 |
Token | never |
Token ID | 1239 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
sanction | +4.486 |
Unsure | +4.280 |
sch | +4.259 |
hey | +4.245 |
kinetic | +4.141 |
Neg logit contributions | |
Tea | -5.931 |
76561 | -5.639 |
abit | -5.582 |
acle | -5.282 |
Oracle | -5.069 |
Token | inspired |
Token ID | 7867 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
sanction | +7.963 |
sch | +7.693 |
hey | +7.374 |
CSI | +7.283 |
kinetic | +7.269 |
Neg logit contributions | |
Tea | -13.390 |
76561 | -13.178 |
abit | -12.742 |
ethy | -11.715 |
acle | -11.628 |
Token | to |
Token ID | 284 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
sanction | +2.815 |
Unsure | +2.703 |
hey | +2.669 |
sch | +2.631 |
cul | +2.620 |
Neg logit contributions | |
Tea | -2.723 |
76561 | -2.529 |
abit | -2.522 |
acle | -2.417 |
Oracle | -2.332 |
Token | make |
Token ID | 787 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
sanction | +1.258 |
Unsure | +1.202 |
hey | +1.177 |
sch | +1.159 |
cul | +1.156 |
Neg logit contributions | |
Tea | -1.641 |
abit | -1.536 |
76561 | -1.531 |
acle | -1.468 |
Oracle | -1.431 |
Token | myself |
Token ID | 3589 |
Feature activation | -9.61e+00 |
Pos logit contributions | |
sanction | +4.375 |
hey | +4.271 |
sch | +4.239 |
kinetic | +4.181 |
Unsure | +4.074 |
Neg logit contributions | |
Tea | -6.764 |
76561 | -6.406 |
abit | -6.402 |
acle | -6.011 |
Oracle | -5.872 |
Token | look |
Token ID | 804 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
sanction | +5.284 |
sch | +5.151 |
hey | +5.143 |
Unsure | +5.120 |
cul | +5.073 |
Neg logit contributions | |
Tea | -8.668 |
76561 | -8.513 |
abit | -8.334 |
acle | -7.688 |
Oracle | -7.619 |
Token | like |
Token ID | 588 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
sch | +6.960 |
hey | +6.917 |
sanction | +6.910 |
kinetic | +6.754 |
wow | +6.612 |
Neg logit contributions | |
Tea | -11.913 |
76561 | -11.505 |
abit | -11.383 |
acle | -10.364 |
Oracle | -10.159 |
Token | a |
Token ID | 257 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
sanction | +4.731 |
hey | +4.699 |
sch | +4.588 |
CSI | +4.495 |
kinetic | +4.493 |
Neg logit contributions | |
Tea | -7.157 |
76561 | -6.734 |
abit | -6.707 |
acle | -6.283 |
Oracle | -6.145 |
Token | doll |
Token ID | 3654 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
sanction | +2.218 |
Unsure | +2.109 |
hey | +2.095 |
sch | +2.082 |
kinetic | +2.051 |
Neg logit contributions | |
Tea | -3.098 |
abit | -2.903 |
76561 | -2.873 |
acle | -2.739 |
Oracle | -2.690 |
Token | . |
Token ID | 13 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
Tea | +5.279 |
abit | +5.028 |
acle | +4.808 |
76561 | +4.806 |
Oracle | +4.697 |
Neg logit contributions | |
sanction | -4.961 |
Unsure | -4.812 |
cul | -4.565 |
CSI | -4.559 |
riction | -4.547 |
Token | To |
Token ID | 1675 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
Tea | +4.142 |
76561 | +3.822 |
abit | +3.813 |
Oracle | +3.757 |
acle | +3.736 |
Neg logit contributions | |
sanction | -2.512 |
kinetic | -2.244 |
cul | -2.236 |
riction | -2.218 |
Unsure | -2.211 |
Token | off |
Token ID | 572 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
sanction | +3.203 |
Unsure | +3.041 |
sch | +3.002 |
hey | +2.992 |
cul | +2.943 |
Neg logit contributions | |
Tea | -4.295 |
abit | -4.046 |
76561 | -4.011 |
acle | -3.869 |
Oracle | -3.762 |
Token | with |
Token ID | 351 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
sanction | +6.319 |
Unsure | +6.141 |
sch | +6.091 |
hey | +5.984 |
cul | +5.857 |
Neg logit contributions | |
Tea | -9.570 |
abit | -9.074 |
76561 | -9.050 |
acle | -8.594 |
ethy | -8.362 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
sanction | +2.790 |
Unsure | +2.640 |
hey | +2.621 |
sch | +2.567 |
cul | +2.542 |
Neg logit contributions | |
Tea | -4.798 |
abit | -4.546 |
76561 | -4.493 |
acle | -4.370 |
Oracle | -4.239 |
Token | Are |
Token ID | 4231 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
sanction | +0.593 |
Unsure | +0.579 |
hey | +0.556 |
cul | +0.544 |
sch | +0.544 |
Neg logit contributions | |
Tea | -0.964 |
abit | -0.914 |
76561 | -0.900 |
acle | -0.874 |
Oracle | -0.853 |
Token | your |
Token ID | 534 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Tea | +0.480 |
abit | +0.446 |
76561 | +0.440 |
acle | +0.427 |
Oracle | +0.418 |
Neg logit contributions | |
sanction | -0.444 |
Unsure | -0.429 |
hey | -0.416 |
cul | -0.413 |
sch | -0.410 |
Token | kids |
Token ID | 3988 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Tea | +0.353 |
abit | +0.330 |
76561 | +0.325 |
acle | +0.315 |
Oracle | +0.309 |
Neg logit contributions | |
sanction | -0.292 |
Unsure | -0.281 |
hey | -0.272 |
cul | -0.270 |
sch | -0.268 |
Token | too |
Token ID | 1165 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
sanction | +2.099 |
Unsure | +2.023 |
hey | +1.973 |
sch | +1.960 |
cul | +1.928 |
Neg logit contributions | |
Tea | -2.793 |
abit | -2.637 |
76561 | -2.610 |
acle | -2.515 |
Oracle | -2.436 |
Token | young |
Token ID | 1862 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
sanction | +0.755 |
Unsure | +0.727 |
hey | +0.705 |
sch | +0.698 |
cul | +0.695 |
Neg logit contributions | |
Tea | -1.037 |
abit | -0.977 |
76561 | -0.968 |
acle | -0.932 |
Oracle | -0.912 |
Token | to |
Token ID | 284 |
Feature activation | -8.12e+00 |
Pos logit contributions | |
sanction | +1.674 |
Unsure | +1.610 |
hey | +1.574 |
sch | +1.556 |
cul | +1.551 |
Neg logit contributions | |
Tea | -2.113 |
abit | -1.983 |
76561 | -1.956 |
acle | -1.905 |
Oracle | -1.852 |
Token | get |
Token ID | 651 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
sanction | +4.833 |
Unsure | +4.501 |
sch | +4.476 |
hey | +4.449 |
cul | +4.341 |
Neg logit contributions | |
Tea | -7.483 |
76561 | -7.173 |
abit | -6.893 |
Oracle | -6.614 |
acle | -6.604 |
Token | into |
Token ID | 656 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
sanction | +4.290 |
Unsure | +4.085 |
sch | +4.083 |
hey | +4.013 |
kinetic | +3.982 |
Neg logit contributions | |
Tea | -6.725 |
76561 | -6.420 |
abit | -6.311 |
acle | -6.058 |
Oracle | -5.928 |
Token | them |
Token ID | 606 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
sanction | +4.440 |
Unsure | +4.140 |
hey | +4.079 |
sch | +4.069 |
kinetic | +3.946 |
Neg logit contributions | |
Tea | -6.652 |
abit | -6.293 |
76561 | -6.271 |
acle | -6.032 |
Oracle | -5.853 |
Token | in |
Token ID | 287 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
sanction | +1.880 |
Unsure | +1.785 |
hey | +1.754 |
sch | +1.732 |
cul | +1.720 |
Neg logit contributions | |
Tea | -2.311 |
abit | -2.146 |
76561 | -2.138 |
acle | -2.057 |
Oracle | -2.008 |
Token | celebration |
Token ID | 14395 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
Tea | +5.701 |
abit | +5.325 |
acle | +5.214 |
Oracle | +5.192 |
76561 | +5.111 |
Neg logit contributions | |
Unsure | -4.529 |
sanction | -4.389 |
cul | -4.294 |
opoly | -4.279 |
riction | -4.262 |
Token | of |
Token ID | 286 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
sanction | +2.181 |
Unsure | +2.072 |
hey | +2.034 |
sch | +2.001 |
cul | +1.982 |
Neg logit contributions | |
Tea | -2.802 |
abit | -2.625 |
76561 | -2.592 |
acle | -2.515 |
Oracle | -2.449 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Tea | +0.410 |
abit | +0.384 |
76561 | +0.379 |
acle | +0.369 |
Oracle | +0.362 |
Neg logit contributions | |
sanction | -0.297 |
Unsure | -0.287 |
hey | -0.277 |
cul | -0.274 |
sch | -0.271 |
Token | 25 |
Token ID | 1679 |
Feature activation | -9.97e+00 |
Pos logit contributions | |
sanction | +0.956 |
Unsure | +0.905 |
hey | +0.891 |
sch | +0.875 |
cul | +0.865 |
Neg logit contributions | |
Tea | -1.411 |
abit | -1.327 |
76561 | -1.314 |
acle | -1.271 |
Oracle | -1.240 |
Token | th |
Token ID | 400 |
Feature activation | -7.87e+00 |
Pos logit contributions | |
sanction | +5.115 |
hey | +4.780 |
Unsure | +4.708 |
sch | +4.702 |
win | +4.592 |
Neg logit contributions | |
Tea | -9.543 |
abit | -9.137 |
76561 | -9.096 |
acle | -8.706 |
Oracle | -8.437 |
Token | anniversary |
Token ID | 11162 |
Feature activation | -8.21e+00 |
Pos logit contributions | |
sanction | +3.371 |
Unsure | +3.012 |
hey | +2.995 |
sch | +2.923 |
win | +2.797 |
Neg logit contributions | |
Tea | -8.463 |
abit | -8.108 |
76561 | -8.034 |
acle | -7.809 |
Oracle | -7.587 |
Token | of |
Token ID | 286 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
sanction | +5.015 |
hey | +4.688 |
sch | +4.641 |
Unsure | +4.628 |
win | +4.479 |
Neg logit contributions | |
Tea | -7.281 |
abit | -6.801 |
76561 | -6.797 |
acle | -6.527 |
Oracle | -6.328 |
Token | their |
Token ID | 511 |
Feature activation | -6.89e+00 |
Pos logit contributions | |
sanction | +4.507 |
hey | +4.138 |
sch | +4.115 |
Unsure | +4.065 |
CSI | +3.984 |
Neg logit contributions | |
Tea | -6.541 |
abit | -6.119 |
76561 | -6.075 |
acle | -5.827 |
Oracle | -5.707 |
Token | first |
Token ID | 717 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
sanction | +4.129 |
hey | +3.925 |
sch | +3.815 |
Unsure | +3.681 |
kinetic | +3.663 |
Neg logit contributions | |
Tea | -6.343 |
76561 | -5.996 |
abit | -5.976 |
acle | -5.647 |
Oracle | -5.531 |
Token | in |
Token ID | 287 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
sanction | +1.682 |
Unsure | +1.612 |
hey | +1.580 |
cul | +1.554 |
sch | +1.554 |
Neg logit contributions | |
Tea | -2.203 |
abit | -2.066 |
76561 | -2.054 |
acle | -1.971 |
Oracle | -1.922 |
Token | Melbourne |
Token ID | 14819 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Tea | +2.594 |
abit | +2.383 |
acle | +2.324 |
76561 | +2.313 |
Oracle | +2.304 |
Neg logit contributions | |
sanction | -2.650 |
Unsure | -2.611 |
cul | -2.502 |
hey | -2.496 |
opoly | -2.479 |
Token | on |
Token ID | 319 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Tea | +1.380 |
abit | +1.291 |
76561 | +1.267 |
acle | +1.236 |
Oracle | +1.220 |
Neg logit contributions | |
sanction | -1.129 |
Unsure | -1.091 |
hey | -1.052 |
cul | -1.044 |
sch | -1.034 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Tea | +0.665 |
abit | +0.623 |
76561 | +0.614 |
acle | +0.599 |
Oracle | +0.590 |
Neg logit contributions | |
sanction | -0.472 |
Unsure | -0.454 |
hey | -0.439 |
cul | -0.434 |
sch | -0.431 |
Token | , |
Token ID | 11 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
sanction | +0.110 |
Unsure | +0.106 |
hey | +0.103 |
cul | +0.102 |
sch | +0.101 |
Neg logit contributions | |
Tea | -0.141 |
abit | -0.132 |
76561 | -0.130 |
acle | -0.126 |
Oracle | -0.123 |
Token | V |
Token ID | 569 |
Feature activation | -2.32e+01 |
Pos logit contributions | |
Tea | +3.891 |
abit | +3.638 |
76561 | +3.606 |
acle | +3.531 |
Oracle | +3.524 |
Neg logit contributions | |
sanction | -3.131 |
Unsure | -3.026 |
hey | -2.894 |
sch | -2.865 |
cul | -2.864 |
Token | ese |
Token ID | 2771 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
Unsure | +7.568 |
cul | +7.267 |
win | +7.182 |
hey | +6.728 |
sch | +6.393 |
Neg logit contributions | |
76561 | -21.432 |
Tea | -21.180 |
Oracle | -20.384 |
Oracle | -19.857 |
��� | -19.610 |
Token | y |
Token ID | 88 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
sanction | +0.738 |
Unsure | +0.718 |
hey | +0.701 |
cul | +0.695 |
sch | +0.692 |
Neg logit contributions | |
Tea | -0.640 |
abit | -0.590 |
76561 | -0.584 |
acle | -0.558 |
Oracle | -0.547 |
Token | – |
Token ID | 784 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
sanction | +6.319 |
sch | +5.972 |
hey | +5.970 |
Unsure | +5.811 |
kinetic | +5.703 |
Neg logit contributions | |
Tea | -8.326 |
76561 | -7.918 |
abit | -7.766 |
acle | -7.294 |
Oracle | -7.092 |
Token | who |
Token ID | 508 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
sanction | +0.908 |
Unsure | +0.874 |
hey | +0.854 |
cul | +0.841 |
sch | +0.837 |
Neg logit contributions | |
Tea | -1.077 |
abit | -1.007 |
76561 | -0.994 |
acle | -0.960 |
Oracle | -0.935 |
Token | heads |
Token ID | 6665 |
Feature activation | +7.60e+00 |
Pos logit contributions | |
sanction | +2.704 |
hey | +2.538 |
Unsure | +2.527 |
sch | +2.499 |
cul | +2.445 |
Neg logit contributions | |
Tea | -3.764 |
abit | -3.564 |
76561 | -3.540 |
acle | -3.365 |
Oracle | -3.257 |
Token | email |
Token ID | 3053 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
sanction | +2.967 |
Unsure | +2.812 |
hey | +2.757 |
sch | +2.730 |
cul | +2.698 |
Neg logit contributions | |
Tea | -4.686 |
abit | -4.387 |
76561 | -4.374 |
acle | -4.190 |
Oracle | -4.092 |
Token | below |
Token ID | 2174 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
sanction | +3.083 |
Unsure | +2.977 |
hey | +2.937 |
sch | +2.924 |
kinetic | +2.865 |
Neg logit contributions | |
Tea | -3.594 |
abit | -3.312 |
76561 | -3.278 |
acle | -3.154 |
Oracle | -3.097 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e-03 |
Pos logit contributions | |
Tea | +0.004 |
abit | +0.004 |
76561 | +0.004 |
acle | +0.004 |
Oracle | +0.003 |
Neg logit contributions | |
sanction | -0.003 |
Unsure | -0.003 |
hey | -0.003 |
cul | -0.003 |
sch | -0.003 |
Token | : |
Token ID | 1058 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
Tea | +0.002 |
abit | +0.002 |
76561 | +0.002 |
acle | +0.002 |
Oracle | +0.002 |
Neg logit contributions | |
sanction | -0.001 |
Unsure | -0.001 |
hey | -0.001 |
cul | -0.001 |
sch | -0.001 |
Token | To |
Token ID | 1675 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
sanction | +6.802 |
hey | +6.764 |
Unsure | +6.750 |
cul | +6.579 |
win | +6.463 |
Neg logit contributions | |
Tea | -8.319 |
abit | -8.083 |
76561 | -7.849 |
acle | -7.568 |
Oracle | -7.283 |
Token | prove |
Token ID | 5879 |
Feature activation | -2.22e+01 |
Pos logit contributions | |
Tea | +4.966 |
abit | +4.583 |
acle | +4.381 |
76561 | +4.379 |
Oracle | +4.357 |
Neg logit contributions | |
sanction | -4.723 |
Unsure | -4.721 |
riction | -4.465 |
cul | -4.461 |
kinetic | -4.449 |
Token | just |
Token ID | 655 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
hey | +10.058 |
gr | +9.152 |
wow | +8.683 |
sch | +8.654 |
sanction | +8.621 |
Neg logit contributions | |
76561 | -19.867 |
Tea | -18.839 |
abit | -18.688 |
byss | -17.594 |
ethy | -17.422 |
Token | how |
Token ID | 703 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
sanction | +2.718 |
hey | +2.549 |
Unsure | +2.520 |
sch | +2.449 |
cul | +2.401 |
Neg logit contributions | |
Tea | -7.781 |
abit | -7.392 |
76561 | -7.325 |
acle | -7.056 |
Oracle | -6.915 |
Token | easy |
Token ID | 2562 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
Tea | +3.164 |
abit | +2.914 |
acle | +2.781 |
Oracle | +2.722 |
76561 | +2.649 |
Neg logit contributions | |
sanction | -5.120 |
Unsure | -4.958 |
cul | -4.834 |
CSI | -4.774 |
hey | -4.766 |
Token | it |
Token ID | 340 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Tea | +7.531 |
abit | +7.032 |
76561 | +6.846 |
Oracle | +6.592 |
acle | +6.588 |
Neg logit contributions | |
proble | -11.929 |
sanction | -11.492 |
Unsure | -11.327 |
cul | -11.222 |
opoly | -11.172 |
Token | is |
Token ID | 318 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Tea | +0.310 |
abit | +0.291 |
76561 | +0.287 |
acle | +0.280 |
Oracle | +0.275 |
Neg logit contributions | |
sanction | -0.211 |
Unsure | -0.202 |
hey | -0.196 |
cul | -0.193 |
sch | -0.192 |
Token | s |
Token ID | 82 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
sch | +11.072 |
sanction | +10.973 |
Unsure | +10.833 |
cul | +10.478 |
CSI | +10.258 |
Neg logit contributions | |
Tea | -12.248 |
abit | -11.459 |
acle | -11.344 |
76561 | -11.044 |
Oracle | -10.912 |
Token | Self |
Token ID | 12189 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
sanction | +6.773 |
Unsure | +6.719 |
sch | +6.678 |
hey | +6.509 |
cul | +6.431 |
Neg logit contributions | |
Tea | -9.144 |
76561 | -8.522 |
abit | -8.427 |
acle | -8.203 |
Oracle | -7.994 |
Token | - |
Token ID | 12 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
sanction | +1.615 |
Unsure | +1.560 |
hey | +1.506 |
cul | +1.494 |
sch | +1.490 |
Neg logit contributions | |
Tea | -2.010 |
abit | -1.875 |
76561 | -1.846 |
acle | -1.788 |
Oracle | -1.747 |
Token | concept |
Token ID | 43169 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
sanction | +2.708 |
Unsure | +2.604 |
hey | +2.517 |
cul | +2.515 |
sch | +2.489 |
Neg logit contributions | |
Tea | -3.356 |
abit | -3.159 |
76561 | -3.113 |
acle | -3.052 |
Oracle | -2.975 |
Token | Scale |
Token ID | 21589 |
Feature activation | -9.22e+00 |
Pos logit contributions | |
sanction | +3.613 |
Unsure | +3.534 |
sch | +3.433 |
cul | +3.388 |
hey | +3.378 |
Neg logit contributions | |
Tea | -4.949 |
abit | -4.599 |
76561 | -4.491 |
acle | -4.347 |
Oracle | -4.263 |
Token | : |
Token ID | 25 |
Feature activation | -2.58e+01 |
Pos logit contributions | |
sanction | +5.639 |
Unsure | +5.529 |
sch | +5.445 |
cul | +5.352 |
hey | +5.262 |
Neg logit contributions | |
Tea | -7.977 |
abit | -7.453 |
76561 | -7.241 |
acle | -7.175 |
Oracle | -6.963 |
Token | Second |
Token ID | 5498 |
Feature activation | -9.41e+00 |
Pos logit contributions | |
Unsure | +14.754 |
sch | +14.305 |
Unlock | +14.163 |
sanction | +14.128 |
Why | +14.101 |
Neg logit contributions | |
Tea | -16.459 |
abit | -15.291 |
76561 | -15.064 |
acle | -14.689 |
Oracle | -14.487 |
Token | edition |
Token ID | 8313 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
sanction | +5.642 |
Unsure | +5.390 |
sch | +5.232 |
hey | +5.063 |
kinetic | +5.049 |
Neg logit contributions | |
Tea | -8.494 |
abit | -8.090 |
76561 | -8.052 |
acle | -7.464 |
Oracle | -7.422 |
Token | . |
Token ID | 13 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
sanction | +4.500 |
Unsure | +4.267 |
sch | +4.178 |
cul | +4.169 |
hey | +4.155 |
Neg logit contributions | |
Tea | -6.727 |
abit | -6.315 |
76561 | -6.298 |
acle | -5.954 |
Oracle | -5.813 |
Token | Los |
Token ID | 5401 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
Tea | +0.438 |
abit | +0.407 |
76561 | +0.402 |
acle | +0.390 |
Oracle | +0.383 |
Neg logit contributions | |
sanction | -0.397 |
Unsure | -0.382 |
hey | -0.371 |
cul | -0.368 |
sch | -0.365 |
Token | Angeles |
Token ID | 5652 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Tea | +3.155 |
abit | +2.947 |
acle | +2.809 |
76561 | +2.757 |
Oracle | +2.744 |
Neg logit contributions | |
sanction | -4.128 |
Unsure | -3.980 |
hey | -3.902 |
kinetic | -3.897 |
CSI | -3.838 |
Token | . |
Token ID | 13 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
sanction | +2.873 |
Unsure | +2.774 |
hey | +2.725 |
sch | +2.693 |
cul | +2.685 |
Neg logit contributions | |
Tea | -3.960 |
76561 | -3.761 |
abit | -3.636 |
acle | -3.501 |
Oracle | -3.461 |
Token | J |
Token ID | 449 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
sanction | +0.473 |
Unsure | +0.456 |
hey | +0.439 |
sch | +0.431 |
cul | +0.431 |
Neg logit contributions | |
Tea | -0.816 |
abit | -0.771 |
76561 | -0.764 |
acle | -0.740 |
Oracle | -0.724 |
Token | . |
Token ID | 13 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
sanction | +1.707 |
Unsure | +1.652 |
hey | +1.612 |
sch | +1.590 |
cul | +1.588 |
Neg logit contributions | |
Tea | -2.154 |
76561 | -2.021 |
abit | -1.998 |
acle | -1.919 |
Oracle | -1.886 |
Token | ( |
Token ID | 357 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
sanction | +1.226 |
Unsure | +1.197 |
hey | +1.150 |
sch | +1.133 |
cul | +1.124 |
Neg logit contributions | |
Tea | -2.296 |
abit | -2.179 |
76561 | -2.172 |
acle | -2.083 |
Oracle | -2.033 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
sanction | +0.315 |
Unsure | +0.303 |
hey | +0.294 |
cul | +0.290 |
sch | +0.289 |
Neg logit contributions | |
Tea | -0.442 |
abit | -0.415 |
76561 | -0.410 |
acle | -0.398 |
Oracle | -0.390 |
Token | ). |
Token ID | 6739 |
Feature activation | -2.20e+01 |
Pos logit contributions | |
sanction | +0.184 |
Unsure | +0.178 |
hey | +0.174 |
cul | +0.172 |
sch | +0.171 |
Neg logit contributions | |
Tea | -0.155 |
abit | -0.143 |
76561 | -0.140 |
acle | -0.135 |
Oracle | -0.132 |
Token | Cl |
Token ID | 1012 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
Unsure | +13.484 |
Why | +12.986 |
Unlock | +12.568 |
sch | +12.563 |
Impact | +12.375 |
Neg logit contributions | |
Tea | -14.527 |
abit | -14.446 |
76561 | -14.093 |
acle | -13.561 |
Oracle | -12.945 |
Token | ueless |
Token ID | 38835 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
sanction | +3.727 |
Unsure | +3.569 |
cul | +3.550 |
hey | +3.511 |
sch | +3.500 |
Neg logit contributions | |
Tea | -4.186 |
76561 | -3.925 |
abit | -3.801 |
Oracle | -3.699 |
acle | -3.646 |
Token | or |
Token ID | 393 |
Feature activation | -8.21e+00 |
Pos logit contributions | |
sanction | +6.219 |
sch | +6.087 |
Unsure | +5.972 |
hey | +5.848 |
cul | +5.618 |
Neg logit contributions | |
Tea | -8.586 |
76561 | -8.147 |
abit | -8.019 |
acle | -7.653 |
Oracle | -7.505 |
Token | powerful |
Token ID | 3665 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
sanction | +5.480 |
Unsure | +5.371 |
sch | +5.275 |
hey | +5.220 |
cul | +5.068 |
Neg logit contributions | |
Tea | -6.708 |
76561 | -6.359 |
abit | -6.327 |
Oracle | -5.869 |
Oracle | -5.832 |
Token | ? |
Token ID | 30 |
Feature activation | -2.50e+01 |
Pos logit contributions | |
sanction | +4.599 |
sch | +4.346 |
Unsure | +4.310 |
hey | +4.223 |
kinetic | +4.099 |
Neg logit contributions | |
Tea | -6.983 |
76561 | -6.573 |
abit | -6.568 |
acle | -6.245 |
Oracle | -6.066 |
Token | of |
Token ID | 286 |
Feature activation | -1.71e+01 |
Pos logit contributions | |
sanction | +4.232 |
hey | +3.999 |
Unsure | +3.968 |
cul | +3.940 |
sch | +3.928 |
Neg logit contributions | |
Tea | -5.960 |
76561 | -5.648 |
abit | -5.597 |
acle | -5.313 |
Oracle | -5.170 |
Token | Millenn |
Token ID | 19007 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
Why | +10.057 |
Unlock | +10.038 |
Unsure | +9.916 |
sanction | +9.902 |
sch | +9.885 |
Neg logit contributions | |
Tea | -12.498 |
76561 | -12.235 |
abit | -11.639 |
acle | -11.153 |
Oracle | -11.005 |
Token | ial |
Token ID | 498 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
cul | +4.627 |
opoly | +4.558 |
sanction | +4.470 |
Unsure | +4.435 |
sch | +4.365 |
Neg logit contributions | |
Tea | -11.269 |
76561 | -11.134 |
Oracle | -10.437 |
abit | -10.367 |
Oracle | -10.218 |
Token | Moment |
Token ID | 29278 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Unsure | +6.922 |
sanction | +6.821 |
sch | +6.711 |
cul | +6.649 |
CSI | +6.567 |
Neg logit contributions | |
Tea | -8.536 |
76561 | -8.331 |
abit | -8.085 |
acle | -7.882 |
Oracle | -7.504 |
Token | um |
Token ID | 388 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
Tea | +1.921 |
abit | +1.789 |
76561 | +1.740 |
acle | +1.710 |
Oracle | +1.666 |
Neg logit contributions | |
sanction | -2.010 |
Unsure | -1.934 |
hey | -1.889 |
cul | -1.867 |
sch | -1.857 |
Token | : |
Token ID | 25 |
Feature activation | -2.19e+01 |
Pos logit contributions | |
sanction | +4.219 |
Unsure | +4.210 |
sch | +4.025 |
cul | +4.012 |
hey | +4.003 |
Neg logit contributions | |
Tea | -5.610 |
76561 | -5.269 |
abit | -5.268 |
acle | -5.027 |
Oracle | -4.842 |
Token | How |
Token ID | 1374 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
Why | +13.030 |
Unlock | +12.764 |
Unsure | +12.482 |
Challenge | +11.827 |
sch | +11.719 |
Neg logit contributions | |
Tea | -14.740 |
76561 | -14.642 |
abit | -14.443 |
acle | -13.501 |
ethy | -13.317 |
Token | A |
Token ID | 317 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
sanction | +0.055 |
Unsure | +0.053 |
hey | +0.051 |
cul | +0.050 |
sch | +0.050 |
Neg logit contributions | |
Tea | -0.080 |
abit | -0.075 |
76561 | -0.074 |
acle | -0.072 |
Oracle | -0.071 |
Token | New |
Token ID | 968 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Tea | +0.323 |
abit | +0.303 |
76561 | +0.298 |
acle | +0.290 |
Oracle | +0.285 |
Neg logit contributions | |
sanction | -0.247 |
Unsure | -0.237 |
hey | -0.230 |
cul | -0.227 |
sch | -0.226 |
Token | Generation |
Token ID | 16588 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
Tea | +1.116 |
abit | +1.042 |
76561 | +1.015 |
acle | +0.998 |
Oracle | +0.983 |
Neg logit contributions | |
sanction | -0.926 |
Unsure | -0.884 |
hey | -0.860 |
cul | -0.849 |
kinetic | -0.844 |
Token | Is |
Token ID | 1148 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
Unsure | +2.403 |
sanction | +2.357 |
sch | +2.229 |
hey | +2.224 |
cul | +2.213 |
Neg logit contributions | |
Tea | -4.773 |
abit | -4.517 |
76561 | -4.507 |
acle | -4.332 |
Oracle | -4.224 |