Token | , |
Token ID | 11 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
declass | +1.722 |
lobb | +1.658 |
� | +1.627 |
":[" | +1.562 |
Kubrick | +1.539 |
Neg logit contributions | |
Metatron | -1.718 |
Sac | -1.671 |
Syl | -1.605 |
Es | -1.565 |
Alphabet | -1.489 |
Token | � |
Token ID | 447 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
Metatron | +0.163 |
Sac | +0.158 |
Syl | +0.153 |
Es | +0.148 |
Alphabet | +0.142 |
Neg logit contributions | |
declass | -0.162 |
lobb | -0.155 |
� | -0.153 |
":[" | -0.146 |
bryce | -0.145 |
Token | � |
Token ID | 251 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
Metatron | +0.008 |
Sac | +0.008 |
Syl | +0.008 |
Es | +0.008 |
Alphabet | +0.007 |
Neg logit contributions | |
declass | -0.007 |
lobb | -0.006 |
� | -0.006 |
":[" | -0.006 |
bryce | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
declass | +0.529 |
lobb | +0.510 |
� | +0.503 |
":[" | +0.481 |
bryce | +0.478 |
Neg logit contributions | |
Metatron | -0.475 |
Sac | -0.459 |
Syl | -0.442 |
Es | -0.427 |
Alphabet | -0.409 |
Token | Mer |
Token ID | 4638 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Metatron | +0.029 |
Sac | +0.028 |
Syl | +0.027 |
Es | +0.026 |
Alphabet | +0.025 |
Neg logit contributions | |
declass | -0.029 |
lobb | -0.028 |
� | -0.028 |
":[" | -0.026 |
bryce | -0.026 |
Token | r |
Token ID | 81 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
Metatron | +0.850 |
Sac | +0.821 |
Syl | +0.793 |
Es | +0.764 |
Alphabet | +0.729 |
Neg logit contributions | |
declass | -1.042 |
lobb | -1.006 |
� | -0.989 |
":[" | -0.952 |
Kubrick | -0.941 |
Token | ion |
Token ID | 295 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Metatron | +5.799 |
Syl | +5.435 |
Sac | +5.375 |
Es | +5.075 |
alia | +4.778 |
Neg logit contributions | |
declass | -9.384 |
lobb | -9.134 |
":[" | -8.981 |
� | -8.942 |
�� | -8.852 |
Token | Stock |
Token ID | 10500 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Metatron | +1.486 |
Sac | +1.437 |
Syl | +1.397 |
Es | +1.351 |
Alphabet | +1.293 |
Neg logit contributions | |
declass | -1.524 |
lobb | -1.463 |
� | -1.437 |
":[" | -1.382 |
bryce | -1.374 |
Token | bro |
Token ID | 7957 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
Metatron | +1.442 |
Sac | +1.391 |
Syl | +1.348 |
Es | +1.307 |
Alphabet | +1.253 |
Neg logit contributions | |
declass | -1.498 |
lobb | -1.437 |
� | -1.421 |
":[" | -1.359 |
bryce | -1.352 |
Token | kers |
Token ID | 15949 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Metatron | +0.652 |
Sac | +0.630 |
Syl | +0.607 |
Es | +0.587 |
Alphabet | +0.558 |
Neg logit contributions | |
declass | -0.757 |
lobb | -0.727 |
� | -0.723 |
":[" | -0.688 |
bryce | -0.686 |
Token | chief |
Token ID | 4039 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
Metatron | +1.088 |
Sac | +1.051 |
Syl | +1.017 |
Es | +0.984 |
Alphabet | +0.944 |
Neg logit contributions | |
declass | -1.205 |
lobb | -1.157 |
� | -1.143 |
bryce | -1.095 |
":[" | -1.092 |
Token | u |
Token ID | 84 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
Metatron | +1.768 |
Sac | +1.729 |
Syl | +1.672 |
Es | +1.618 |
alia | +1.556 |
Neg logit contributions | |
declass | -1.854 |
lobb | -1.810 |
� | -1.766 |
":[" | -1.685 |
Kubrick | -1.683 |
Token | D |
Token ID | 360 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
Metatron | +2.173 |
Sac | +2.130 |
Syl | +2.082 |
Es | +1.999 |
Alphabet | +1.892 |
Neg logit contributions | |
declass | -2.517 |
lobb | -2.425 |
� | -2.371 |
bryce | -2.294 |
":[" | -2.290 |
Token | arya |
Token ID | 43898 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Metatron | +0.459 |
Sac | +0.441 |
Syl | +0.424 |
Es | +0.408 |
Alphabet | +0.389 |
Neg logit contributions | |
declass | -0.605 |
lobb | -0.585 |
� | -0.577 |
":[" | -0.555 |
bryce | -0.552 |
Token | and |
Token ID | 290 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Metatron | +0.948 |
Sac | +0.919 |
Syl | +0.890 |
Es | +0.857 |
Alphabet | +0.819 |
Neg logit contributions | |
declass | -1.091 |
lobb | -1.053 |
� | -1.035 |
bryce | -0.993 |
":[" | -0.993 |
Token | Sy |
Token ID | 1632 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
declass | +1.719 |
lobb | +1.655 |
� | +1.630 |
":[" | +1.548 |
Kubrick | +1.546 |
Neg logit contributions | |
Metatron | -1.639 |
Sac | -1.596 |
Syl | -1.515 |
Es | -1.485 |
Alphabet | -1.426 |
Token | r |
Token ID | 81 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
declass | +0.241 |
lobb | +0.233 |
� | +0.230 |
":[" | +0.221 |
bryce | +0.220 |
Neg logit contributions | |
Metatron | -0.187 |
Sac | -0.180 |
Syl | -0.173 |
Es | -0.167 |
Alphabet | -0.159 |
Token | D |
Token ID | 360 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Metatron | +7.329 |
Syl | +7.214 |
Sac | +7.154 |
alia | +6.773 |
Es | +6.722 |
Neg logit contributions | |
declass | -7.573 |
lobb | -7.283 |
� | -7.035 |
�� | -6.891 |
FAC | -6.857 |
Token | arya |
Token ID | 43898 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Metatron | +1.170 |
Sac | +1.128 |
Syl | +1.056 |
Es | +0.997 |
Alphabet | +0.924 |
Neg logit contributions | |
declass | -2.745 |
lobb | -2.665 |
� | -2.642 |
Kubrick | -2.549 |
bryce | -2.544 |
Token | rivers |
Token ID | 18180 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Metatron | +1.044 |
Sac | +1.010 |
Syl | +0.978 |
Es | +0.945 |
Alphabet | +0.896 |
Neg logit contributions | |
declass | -1.221 |
lobb | -1.175 |
� | -1.156 |
bryce | -1.112 |
":[" | -1.112 |
Token | . |
Token ID | 13 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Metatron | +1.163 |
Sac | +1.127 |
Syl | +1.087 |
Es | +1.051 |
Alphabet | +0.998 |
Neg logit contributions | |
declass | -1.358 |
lobb | -1.307 |
� | -1.286 |
":[" | -1.240 |
bryce | -1.237 |
Token | The |
Token ID | 383 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
declass | +0.369 |
lobb | +0.356 |
� | +0.351 |
":[" | +0.336 |
bryce | +0.334 |
Neg logit contributions | |
Metatron | -0.320 |
Sac | -0.310 |
Syl | -0.298 |
Es | -0.288 |
Alphabet | -0.276 |
Token | Reading |
Token ID | 36120 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
Metatron | +2.134 |
Sac | +2.084 |
Syl | +1.949 |
Es | +1.905 |
Alphabet | +1.768 |
Neg logit contributions | |
declass | -3.546 |
lobb | -3.455 |
� | -3.392 |
Kubrick | -3.242 |
":[" | -3.241 |
Token | 55 |
Token ID | 5996 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
declass | +2.137 |
lobb | +2.033 |
� | +1.994 |
":[" | +1.889 |
bryce | +1.878 |
Neg logit contributions | |
Metatron | -2.825 |
Sac | -2.759 |
Syl | -2.668 |
Es | -2.606 |
Alphabet | -2.509 |
Token | 80 |
Token ID | 1795 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
declass | +0.792 |
lobb | +0.744 |
� | +0.741 |
":[" | +0.713 |
FAC | +0.698 |
Neg logit contributions | |
Metatron | -1.125 |
Sac | -1.072 |
Syl | -1.049 |
Es | -1.010 |
Alphabet | -0.996 |
Token | 953 |
Token ID | 49649 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Metatron | +1.415 |
Sac | +1.323 |
Syl | +1.209 |
Es | +1.159 |
Alphabet | +1.046 |
Neg logit contributions | |
declass | -3.983 |
lobb | -3.865 |
� | -3.832 |
Kubrick | -3.699 |
FAC | -3.697 |
Token | 16 |
Token ID | 1467 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
Metatron | +2.018 |
Sac | +1.956 |
Syl | +1.895 |
Es | +1.830 |
Alphabet | +1.762 |
Neg logit contributions | |
declass | -1.892 |
lobb | -1.829 |
� | -1.802 |
bryce | -1.711 |
":[" | -1.704 |
Token | 27 |
Token ID | 1983 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Metatron | +2.547 |
Sac | +2.504 |
Syl | +2.383 |
Es | +2.308 |
Alphabet | +2.187 |
Neg logit contributions | |
declass | -3.530 |
lobb | -3.445 |
� | -3.387 |
bryce | -3.222 |
":[" | -3.197 |
Token | 145 |
Token ID | 18781 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Sac | +2.662 |
Metatron | +2.269 |
Syl | +2.033 |
Es | +2.006 |
2020 | +1.946 |
Neg logit contributions | |
lobb | -12.265 |
declass | -12.259 |
� | -11.977 |
�� | -11.919 |
Kubrick | -11.523 |
Token | Flat |
Token ID | 21939 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
Metatron | +1.379 |
Sac | +1.312 |
Syl | +1.280 |
Es | +1.216 |
Alphabet | +1.171 |
Neg logit contributions | |
declass | -1.887 |
lobb | -1.839 |
� | -1.808 |
bryce | -1.745 |
":[" | -1.732 |
Token | buff |
Token ID | 36873 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
declass | +0.047 |
lobb | +0.045 |
� | +0.043 |
":[" | +0.042 |
bryce | +0.042 |
Neg logit contributions | |
Metatron | -0.054 |
Sac | -0.052 |
Syl | -0.051 |
Es | -0.049 |
Alphabet | -0.048 |
Token | ers |
Token ID | 364 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Metatron | +1.133 |
Sac | +1.104 |
Syl | +1.073 |
Es | +1.047 |
Alphabet | +1.012 |
Neg logit contributions | |
declass | -0.728 |
lobb | -0.692 |
� | -0.677 |
":[" | -0.638 |
bryce | -0.634 |
Token | Reading |
Token ID | 36120 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Metatron | +1.159 |
Sac | +1.103 |
Syl | +1.068 |
Es | +1.013 |
Alphabet | +0.974 |
Neg logit contributions | |
declass | -1.703 |
lobb | -1.642 |
� | -1.628 |
":[" | -1.578 |
bryce | -1.567 |
Token | President |
Token ID | 1992 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Metatron | +1.275 |
Sac | +1.228 |
Syl | +1.194 |
Es | +1.149 |
Alphabet | +1.116 |
Neg logit contributions | |
declass | -1.276 |
lobb | -1.231 |
� | -1.229 |
":[" | -1.168 |
bryce | -1.166 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
Metatron | +1.125 |
Sac | +1.083 |
Syl | +1.048 |
Es | +1.012 |
Alphabet | +0.970 |
Neg logit contributions | |
declass | -1.279 |
lobb | -1.235 |
� | -1.217 |
":[" | -1.165 |
bryce | -1.161 |
Token | Donald |
Token ID | 3759 |
Feature activation | +7.91e+00 |
Pos logit contributions | |
Metatron | +1.787 |
Sac | +1.723 |
Syl | +1.666 |
Es | +1.618 |
Alphabet | +1.562 |
Neg logit contributions | |
declass | -1.874 |
lobb | -1.812 |
� | -1.793 |
":[" | -1.727 |
bryce | -1.709 |
Token | John |
Token ID | 1757 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
Metatron | +3.709 |
Sac | +3.608 |
Syl | +3.448 |
Es | +3.298 |
Alphabet | +3.115 |
Neg logit contributions | |
declass | -7.863 |
� | -7.501 |
lobb | -7.456 |
bryce | -7.234 |
�� | -7.176 |
Token | Trump |
Token ID | 1301 |
Feature activation | +6.51e+00 |
Pos logit contributions | |
Metatron | +3.083 |
Sac | +2.962 |
Syl | +2.800 |
Es | +2.646 |
Alphabet | +2.536 |
Neg logit contributions | |
declass | -6.262 |
lobb | -6.086 |
� | -6.019 |
bryce | -5.853 |
":[" | -5.785 |
Token | House |
Token ID | 18102 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
Sac | +3.620 |
Metatron | +3.469 |
Es | +3.369 |
Syl | +3.163 |
2020 | +3.041 |
Neg logit contributions | |
declass | -5.919 |
lobb | -5.819 |
� | -5.766 |
":[" | -5.472 |
�� | -5.417 |
Token | committee |
Token ID | 5583 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Sac | +5.478 |
Metatron | +5.328 |
Es | +4.971 |
Syl | +4.936 |
Alphabet | +4.833 |
Neg logit contributions | |
� | -9.224 |
declass | -9.075 |
�� | -8.990 |
lobb | -8.945 |
":[" | -8.891 |
Token | believes |
Token ID | 5804 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Metatron | +2.730 |
Sac | +2.622 |
Syl | +2.490 |
Es | +2.330 |
Alphabet | +2.225 |
Neg logit contributions | |
declass | -5.124 |
� | -5.097 |
lobb | -5.041 |
":[" | -4.929 |
bryce | -4.854 |
Token | it |
Token ID | 340 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Metatron | +1.259 |
Sac | +1.204 |
Syl | +1.183 |
Es | +1.119 |
Alphabet | +1.073 |
Neg logit contributions | |
declass | -1.603 |
� | -1.567 |
lobb | -1.555 |
bryce | -1.504 |
":[" | -1.501 |
Token | has |
Token ID | 468 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
Metatron | +1.048 |
Sac | +1.016 |
Syl | +0.980 |
Es | +0.950 |
Alphabet | +0.911 |
Neg logit contributions | |
declass | -1.074 |
lobb | -1.033 |
� | -1.015 |
":[" | -0.971 |
bryce | -0.966 |
Token | evidence |
Token ID | 2370 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
Metatron | +1.626 |
Sac | +1.541 |
Syl | +1.470 |
Es | +1.374 |
Alphabet | +1.300 |
Neg logit contributions | |
declass | -3.096 |
lobb | -3.043 |
� | -3.025 |
":[" | -2.925 |
bryce | -2.914 |
Token | ra |
Token ID | 430 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
Metatron | +1.772 |
Sac | +1.702 |
Syl | +1.643 |
Es | +1.576 |
Alphabet | +1.508 |
Neg logit contributions | |
declass | -2.314 |
lobb | -2.244 |
� | -2.212 |
bryce | -2.123 |
":[" | -2.113 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Metatron | +2.114 |
Sac | +2.038 |
Syl | +1.983 |
Es | +1.909 |
Alphabet | +1.841 |
Neg logit contributions | |
declass | -2.214 |
lobb | -2.127 |
� | -2.082 |
bryce | -2.007 |
":[" | -1.995 |
Token | God |
Token ID | 1793 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
Metatron | +1.020 |
Sac | +0.985 |
Syl | +0.952 |
Es | +0.917 |
Alphabet | +0.879 |
Neg logit contributions | |
declass | -1.109 |
lobb | -1.069 |
� | -1.049 |
bryce | -1.006 |
":[" | -1.006 |
Token | of |
Token ID | 286 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Metatron | +2.335 |
Sac | +2.239 |
Syl | +2.173 |
Es | +2.075 |
Alphabet | +1.981 |
Neg logit contributions | |
declass | -2.962 |
lobb | -2.873 |
� | -2.794 |
":[" | -2.715 |
bryce | -2.694 |
Token | Har |
Token ID | 2113 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
Metatron | +1.518 |
Sac | +1.465 |
Syl | +1.420 |
Es | +1.364 |
Alphabet | +1.312 |
Neg logit contributions | |
declass | -1.618 |
lobb | -1.557 |
� | -1.530 |
bryce | -1.471 |
":[" | -1.467 |
Token | v |
Token ID | 85 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
Metatron | +2.550 |
Sac | +2.494 |
Syl | +2.400 |
Es | +2.296 |
Alphabet | +2.216 |
Neg logit contributions | |
declass | -3.205 |
lobb | -3.082 |
� | -3.036 |
":[" | -2.907 |
bryce | -2.897 |
Token | ests |
Token ID | 3558 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Metatron | +5.601 |
Sac | +5.401 |
Syl | +5.208 |
Es | +5.171 |
alia | +4.853 |
Neg logit contributions | |
declass | -8.929 |
� | -8.599 |
lobb | -8.474 |
FAC | -8.250 |
bryce | -8.195 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Metatron | +1.844 |
Sac | +1.785 |
Syl | +1.727 |
Es | +1.667 |
Alphabet | +1.602 |
Neg logit contributions | |
declass | -1.921 |
lobb | -1.839 |
� | -1.799 |
bryce | -1.734 |
Kubrick | -1.723 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Metatron | +0.841 |
Sac | +0.813 |
Syl | +0.787 |
Es | +0.763 |
Alphabet | +0.734 |
Neg logit contributions | |
declass | -0.773 |
lobb | -0.740 |
� | -0.727 |
":[" | -0.698 |
bryce | -0.690 |
Token | Hot |
Token ID | 21352 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Metatron | +0.102 |
Sac | +0.098 |
Syl | +0.095 |
Es | +0.090 |
Alphabet | +0.087 |
Neg logit contributions | |
declass | -0.133 |
lobb | -0.129 |
� | -0.127 |
":[" | -0.123 |
bryce | -0.122 |
Token | Soup |
Token ID | 34011 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Metatron | +1.022 |
Sac | +0.987 |
Syl | +0.942 |
Es | +0.901 |
Alphabet | +0.859 |
Neg logit contributions | |
declass | -1.551 |
lobb | -1.503 |
� | -1.480 |
bryce | -1.429 |
":[" | -1.425 |
Token | ( |
Token ID | 357 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Metatron | +0.011 |
Sac | +0.011 |
Syl | +0.010 |
Es | +0.010 |
Alphabet | +0.010 |
Neg logit contributions | |
declass | -0.012 |
lobb | -0.011 |
� | -0.011 |
":[" | -0.011 |
bryce | -0.011 |
Token | can |
Token ID | 5171 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Metatron | +1.118 |
Sac | +1.087 |
Syl | +1.045 |
Es | +1.019 |
Alphabet | +0.974 |
Neg logit contributions | |
declass | -1.119 |
lobb | -1.075 |
� | -1.058 |
":[" | -1.005 |
bryce | -1.004 |
Token | be |
Token ID | 307 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
declass | +1.599 |
lobb | +1.513 |
� | +1.493 |
":[" | +1.438 |
Kubrick | +1.400 |
Neg logit contributions | |
Metatron | -1.806 |
Sac | -1.749 |
Syl | -1.686 |
Es | -1.640 |
Alphabet | -1.572 |
Token | empty |
Token ID | 6565 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
declass | +2.486 |
lobb | +2.383 |
� | +2.324 |
":[" | +2.248 |
FAC | +2.208 |
Neg logit contributions | |
Metatron | -2.626 |
Sac | -2.578 |
Syl | -2.446 |
Es | -2.389 |
Alphabet | -2.275 |
Token | ) |
Token ID | 8 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
declass | +1.627 |
lobb | +1.580 |
� | +1.551 |
":[" | +1.479 |
FAC | +1.457 |
Neg logit contributions | |
Metatron | -1.605 |
Sac | -1.562 |
Syl | -1.499 |
Es | -1.449 |
Alphabet | -1.384 |
Token | Example |
Token ID | 17934 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
declass | +1.679 |
lobb | +1.618 |
� | +1.579 |
":[" | +1.529 |
FAC | +1.507 |
Neg logit contributions | |
Metatron | -1.605 |
Sac | -1.567 |
Syl | -1.491 |
Es | -1.454 |
Alphabet | -1.383 |
Token | : |
Token ID | 25 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
Metatron | +6.022 |
Syl | +5.632 |
Sac | +5.583 |
Es | +5.390 |
Alphabet | +5.141 |
Neg logit contributions | |
declass | -8.052 |
lobb | -7.766 |
� | -7.711 |
bryce | -7.658 |
Kubrick | -7.459 |
Token | vi |
Token ID | 25357 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Metatron | +2.981 |
Sac | +2.855 |
Syl | +2.796 |
Es | +2.705 |
Alphabet | +2.577 |
Neg logit contributions | |
declass | -3.346 |
lobb | -3.215 |
� | -3.180 |
bryce | -3.084 |
Kubrick | -3.042 |
Token | : |
Token ID | 25 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Metatron | +2.046 |
Sac | +1.987 |
Syl | +1.919 |
Es | +1.860 |
Alphabet | +1.769 |
Neg logit contributions | |
declass | -2.382 |
lobb | -2.289 |
� | -2.254 |
bryce | -2.192 |
Kubrick | -2.166 |
Token | no |
Token ID | 3919 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
Metatron | +1.340 |
Sac | +1.299 |
Syl | +1.254 |
Es | +1.224 |
Alphabet | +1.166 |
Neg logit contributions | |
declass | -1.371 |
lobb | -1.316 |
� | -1.292 |
bryce | -1.237 |
Kubrick | -1.233 |
Token | ai |
Token ID | 1872 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Metatron | +0.511 |
Sac | +0.495 |
Syl | +0.477 |
Es | +0.463 |
Alphabet | +0.444 |
Neg logit contributions | |
declass | -0.531 |
lobb | -0.511 |
� | -0.502 |
":[" | -0.479 |
bryce | -0.478 |
Token | Donald |
Token ID | 3759 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
declass | +0.112 |
lobb | +0.107 |
� | +0.105 |
":[" | +0.100 |
Kubrick | +0.100 |
Neg logit contributions | |
Metatron | -0.128 |
Sac | -0.125 |
Syl | -0.120 |
Es | -0.117 |
Alphabet | -0.112 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Metatron | +1.477 |
Sac | +1.407 |
Syl | +1.352 |
Es | +1.282 |
Alphabet | +1.214 |
Neg logit contributions | |
declass | -2.693 |
lobb | -2.611 |
� | -2.577 |
":[" | -2.482 |
bryce | -2.480 |
Token | Donald |
Token ID | 3759 |
Feature activation | +8.31e+00 |
Pos logit contributions | |
Metatron | +1.743 |
Sac | +1.674 |
Syl | +1.637 |
Es | +1.579 |
Alphabet | +1.522 |
Neg logit contributions | |
declass | -1.678 |
lobb | -1.610 |
� | -1.594 |
":[" | -1.522 |
bryce | -1.522 |
Token | John |
Token ID | 1757 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
Metatron | +3.949 |
Sac | +3.826 |
Syl | +3.617 |
Es | +3.491 |
Alphabet | +3.324 |
Neg logit contributions | |
declass | -8.195 |
� | -7.865 |
lobb | -7.834 |
�� | -7.518 |
bryce | -7.508 |
Token | Trump |
Token ID | 1301 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
Metatron | +3.096 |
Sac | +3.016 |
Syl | +2.850 |
Es | +2.695 |
Alphabet | +2.593 |
Neg logit contributions | |
declass | -6.974 |
lobb | -6.759 |
� | -6.729 |
bryce | -6.529 |
�� | -6.445 |
Token | House |
Token ID | 18102 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Sac | +3.213 |
Metatron | +3.132 |
Es | +2.964 |
Syl | +2.855 |
2020 | +2.696 |
Neg logit contributions | |
declass | -5.458 |
lobb | -5.341 |
� | -5.264 |
":[" | -5.016 |
bryce | -4.976 |
Token | committee |
Token ID | 5583 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Sac | +5.407 |
Metatron | +5.191 |
Es | +4.897 |
Syl | +4.872 |
2020 | +4.775 |
Neg logit contributions | |
declass | -8.729 |
� | -8.646 |
":[" | -8.512 |
lobb | -8.508 |
�� | -8.494 |
Token | believes |
Token ID | 5804 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Metatron | +1.686 |
Sac | +1.617 |
Syl | +1.541 |
Es | +1.476 |
Alphabet | +1.393 |
Neg logit contributions | |
declass | -2.827 |
lobb | -2.740 |
� | -2.704 |
":[" | -2.608 |
bryce | -2.599 |
Token | it |
Token ID | 340 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Metatron | +0.789 |
Sac | +0.742 |
Syl | +0.714 |
Es | +0.660 |
Alphabet | +0.620 |
Neg logit contributions | |
declass | -1.793 |
lobb | -1.755 |
� | -1.747 |
bryce | -1.703 |
":[" | -1.694 |
Token | has |
Token ID | 468 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
Metatron | +1.007 |
Sac | +0.975 |
Syl | +0.941 |
Es | +0.911 |
Alphabet | +0.874 |
Neg logit contributions | |
declass | -1.036 |
lobb | -0.997 |
� | -0.981 |
":[" | -0.938 |
bryce | -0.933 |
Token | evidence |
Token ID | 2370 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
Metatron | +1.770 |
Sac | +1.675 |
Syl | +1.601 |
Es | +1.489 |
Alphabet | +1.423 |
Neg logit contributions | |
declass | -3.276 |
lobb | -3.230 |
� | -3.205 |
":[" | -3.107 |
bryce | -3.103 |
Token | import |
Token ID | 1330 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
Metatron | +0.509 |
Sac | +0.496 |
Syl | +0.482 |
Es | +0.472 |
Alphabet | +0.454 |
Neg logit contributions | |
declass | -0.289 |
lobb | -0.268 |
� | -0.260 |
":[" | -0.247 |
FAC | -0.244 |
Token | n |
Token ID | 299 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
Metatron | +1.927 |
Sac | +1.818 |
Syl | +1.768 |
Es | +1.660 |
Alphabet | +1.655 |
Neg logit contributions | |
declass | -2.881 |
lobb | -2.819 |
� | -2.805 |
bryce | -2.708 |
":[" | -2.691 |
Token | umpy |
Token ID | 32152 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
declass | +1.640 |
lobb | +1.527 |
":[" | +1.402 |
� | +1.391 |
bryce | +1.382 |
Neg logit contributions | |
Metatron | -4.515 |
Sac | -4.374 |
Syl | -4.291 |
Es | -4.245 |
Alphabet | -4.058 |
Token | as |
Token ID | 355 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Metatron | +0.033 |
Sac | +0.031 |
Syl | +0.031 |
Es | +0.030 |
Alphabet | +0.029 |
Neg logit contributions | |
declass | -0.024 |
lobb | -0.022 |
� | -0.022 |
":[" | -0.021 |
bryce | -0.021 |
Token | np |
Token ID | 45941 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
declass | +0.071 |
lobb | +0.066 |
� | +0.062 |
":[" | +0.059 |
Kubrick | +0.059 |
Neg logit contributions | |
Metatron | -0.156 |
Sac | -0.154 |
Syl | -0.149 |
Es | -0.147 |
Alphabet | -0.141 |
Token | import |
Token ID | 1330 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Metatron | +1.244 |
Sac | +1.214 |
Syl | +1.176 |
Es | +1.154 |
Alphabet | +1.110 |
Neg logit contributions | |
declass | -0.727 |
lobb | -0.680 |
� | -0.658 |
":[" | -0.622 |
FAC | -0.619 |
Token | arg |
Token ID | 1822 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
Metatron | +4.377 |
Sac | +3.957 |
Alphabet | +3.843 |
Syl | +3.816 |
te | +3.652 |
Neg logit contributions | |
declass | -9.475 |
� | -9.404 |
bryce | -9.315 |
lobb | -9.241 |
�� | -9.056 |
Token | parse |
Token ID | 29572 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
declass | +3.137 |
lobb | +2.904 |
bryce | +2.866 |
":[" | +2.792 |
� | +2.791 |
Neg logit contributions | |
Metatron | -4.248 |
Sac | -4.024 |
Syl | -4.018 |
Es | -3.837 |
Alphabet | -3.737 |
Token | import |
Token ID | 1330 |
Feature activation | +9.55e+00 |
Pos logit contributions | |
declass | +0.933 |
lobb | +0.830 |
� | +0.779 |
FAC | +0.764 |
Kubrick | +0.754 |
Neg logit contributions | |
Metatron | -1.836 |
Sac | -1.789 |
Syl | -1.735 |
Es | -1.700 |
Alphabet | -1.630 |
Token | im |
Token ID | 545 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Metatron | +4.104 |
Sac | +3.828 |
Syl | +3.694 |
te | +3.452 |
Alphabet | +3.400 |
Neg logit contributions | |
� | -9.406 |
lobb | -9.147 |
declass | -9.138 |
�� | -9.080 |
bryce | -8.998 |
Token | utils |
Token ID | 26791 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
declass | +1.779 |
lobb | +1.718 |
� | +1.680 |
":[" | +1.637 |
bryce | +1.618 |
Neg logit contributions | |
Metatron | -1.531 |
Sac | -1.453 |
Syl | -1.410 |
Es | -1.335 |
Alphabet | -1.309 |
Token | Continue |
Token ID | 10054 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
Metatron | +0.145 |
Sac | +0.139 |
Syl | +0.133 |
Es | +0.129 |
Alphabet | +0.122 |
Neg logit contributions | |
declass | -0.188 |
lobb | -0.182 |
� | -0.179 |
":[" | -0.172 |
Kubrick | -0.171 |
Token | reading |
Token ID | 3555 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
Metatron | +1.406 |
Sac | +1.349 |
Syl | +1.287 |
Es | +1.234 |
Alphabet | +1.167 |
Neg logit contributions | |
declass | -2.286 |
lobb | -2.215 |
� | -2.185 |
":[" | -2.107 |
bryce | -2.100 |
Token | the |
Token ID | 262 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
declass | +2.416 |
lobb | +2.321 |
� | +2.243 |
":[" | +2.191 |
Kubrick | +2.178 |
Neg logit contributions | |
Metatron | -3.319 |
Sac | -3.227 |
Syl | -3.092 |
Es | -3.065 |
inventoryQuantity | -2.929 |
Token | main |
Token ID | 1388 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
declass | +2.510 |
lobb | +2.418 |
� | +2.185 |
foreground | +2.165 |
Kubrick | +2.147 |
Neg logit contributions | |
Metatron | -5.096 |
Sac | -4.991 |
Es | -4.830 |
Syl | -4.822 |
inventoryQuantity | -4.669 |
Token | story |
Token ID | 1621 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
declass | +1.109 |
lobb | +1.047 |
� | +0.949 |
Kubrick | +0.940 |
":[" | +0.938 |
Neg logit contributions | |
Metatron | -2.317 |
Sac | -2.248 |
Syl | -2.194 |
Es | -2.174 |
inventoryQuantity | -2.073 |
Token | Please |
Token ID | 4222 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Metatron | +1.503 |
Sac | +1.445 |
Syl | +1.381 |
Es | +1.326 |
Alphabet | +1.259 |
Neg logit contributions | |
declass | -2.283 |
lobb | -2.210 |
� | -2.180 |
":[" | -2.100 |
bryce | -2.094 |
Token | verify |
Token ID | 11767 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
Metatron | +6.924 |
Sac | +6.806 |
Syl | +6.461 |
Es | +6.323 |
Alphabet | +6.062 |
Neg logit contributions | |
declass | -7.367 |
� | -7.254 |
lobb | -7.191 |
bryce | -6.958 |
":[" | -6.848 |
Token | you |
Token ID | 345 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
declass | +2.644 |
lobb | +2.530 |
� | +2.451 |
":[" | +2.395 |
Ghostbusters | +2.353 |
Neg logit contributions | |
Metatron | -2.587 |
Sac | -2.536 |
Syl | -2.432 |
Es | -2.347 |
Alphabet | -2.263 |
Token | 're |
Token ID | 821 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Metatron | +0.535 |
Sac | +0.519 |
Syl | +0.498 |
Es | +0.486 |
Alphabet | +0.464 |
Neg logit contributions | |
declass | -0.543 |
lobb | -0.523 |
� | -0.516 |
bryce | -0.488 |
Kubrick | -0.488 |
Token | not |
Token ID | 407 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Metatron | +1.696 |
Sac | +1.652 |
Syl | +1.610 |
Es | +1.560 |
Alphabet | +1.513 |
Neg logit contributions | |
declass | -1.201 |
lobb | -1.154 |
� | -1.140 |
bryce | -1.071 |
":[" | -1.062 |
Token | a |
Token ID | 257 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
declass | +0.087 |
lobb | +0.083 |
� | +0.082 |
":[" | +0.078 |
bryce | +0.078 |
Neg logit contributions | |
Metatron | -0.089 |
Sac | -0.086 |
Syl | -0.083 |
Es | -0.081 |
Alphabet | -0.077 |
Token | Donald |
Token ID | 3759 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Metatron | +1.069 |
Sac | +1.033 |
Syl | +0.999 |
Es | +0.965 |
Alphabet | +0.928 |
Neg logit contributions | |
declass | -1.128 |
lobb | -1.087 |
� | -1.073 |
":[" | -1.025 |
bryce | -1.022 |
Token | Trump |
Token ID | 1301 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
Metatron | +0.947 |
Sac | +0.904 |
Syl | +0.870 |
Es | +0.825 |
Alphabet | +0.782 |
Neg logit contributions | |
declass | -1.726 |
lobb | -1.672 |
� | -1.653 |
":[" | -1.594 |
bryce | -1.591 |
Token | Donald |
Token ID | 3759 |
Feature activation | +7.59e+00 |
Pos logit contributions | |
Metatron | +2.283 |
Sac | +2.208 |
Syl | +2.151 |
Es | +2.075 |
Alphabet | +1.991 |
Neg logit contributions | |
declass | -2.653 |
lobb | -2.560 |
� | -2.516 |
":[" | -2.453 |
Kubrick | -2.421 |
Token | John |
Token ID | 1757 |
Feature activation | +7.12e+00 |
Pos logit contributions | |
Metatron | +3.675 |
Sac | +3.583 |
Syl | +3.384 |
Es | +3.269 |
Alphabet | +3.112 |
Neg logit contributions | |
declass | -7.425 |
� | -7.136 |
lobb | -7.107 |
�� | -6.753 |
":[" | -6.751 |
Token | Trump |
Token ID | 1301 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
Metatron | +3.217 |
Sac | +3.130 |
Syl | +2.973 |
Es | +2.773 |
Alphabet | +2.678 |
Neg logit contributions | |
declass | -7.086 |
lobb | -6.878 |
� | -6.800 |
bryce | -6.632 |
":[" | -6.544 |
Token | House |
Token ID | 18102 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Sac | +3.485 |
Metatron | +3.390 |
Es | +3.232 |
Syl | +3.084 |
2020 | +2.948 |
Neg logit contributions | |
declass | -5.896 |
lobb | -5.784 |
� | -5.726 |
":[" | -5.451 |
bryce | -5.392 |
Token | committee |
Token ID | 5583 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
Sac | +5.376 |
Metatron | +5.096 |
Es | +4.853 |
Syl | +4.791 |
2020 | +4.768 |
Neg logit contributions | |
declass | -8.678 |
� | -8.674 |
lobb | -8.572 |
�� | -8.526 |
":[" | -8.478 |
Token | believes |
Token ID | 5804 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Metatron | +2.048 |
Sac | +1.978 |
Syl | +1.877 |
Es | +1.781 |
Alphabet | +1.686 |
Neg logit contributions | |
declass | -3.664 |
� | -3.582 |
lobb | -3.573 |
":[" | -3.460 |
bryce | -3.427 |
Token | it |
Token ID | 340 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Metatron | +0.655 |
Sac | +0.628 |
Syl | +0.612 |
Es | +0.580 |
Alphabet | +0.556 |
Neg logit contributions | |
declass | -0.894 |
lobb | -0.869 |
� | -0.868 |
bryce | -0.841 |
":[" | -0.837 |
Token | has |
Token ID | 468 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
Metatron | +1.026 |
Sac | +0.991 |
Syl | +0.958 |
Es | +0.925 |
Alphabet | +0.883 |
Neg logit contributions | |
declass | -1.039 |
lobb | -1.002 |
� | -0.995 |
":[" | -0.947 |
bryce | -0.942 |
Token | evidence |
Token ID | 2370 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
Metatron | +1.685 |
Sac | +1.597 |
Syl | +1.518 |
Es | +1.420 |
Alphabet | +1.351 |
Neg logit contributions | |
declass | -3.155 |
lobb | -3.102 |
� | -3.097 |
":[" | -2.988 |
bryce | -2.981 |
Token | Continue |
Token ID | 10054 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Metatron | +0.660 |
Sac | +0.636 |
Syl | +0.610 |
Es | +0.587 |
Alphabet | +0.559 |
Neg logit contributions | |
declass | -0.913 |
lobb | -0.884 |
� | -0.870 |
":[" | -0.837 |
bryce | -0.835 |
Token | reading |
Token ID | 3555 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Metatron | +1.147 |
Sac | +1.103 |
Syl | +1.050 |
Es | +1.010 |
Alphabet | +0.952 |
Neg logit contributions | |
declass | -1.826 |
lobb | -1.772 |
� | -1.743 |
":[" | -1.683 |
bryce | -1.676 |
Token | the |
Token ID | 262 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
declass | +1.651 |
lobb | +1.585 |
� | +1.538 |
":[" | +1.478 |
Kubrick | +1.469 |
Neg logit contributions | |
Metatron | -2.039 |
Sac | -1.982 |
Syl | -1.906 |
Es | -1.877 |
Alphabet | -1.778 |
Token | main |
Token ID | 1388 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
declass | +1.054 |
lobb | +1.001 |
� | +0.966 |
":[" | +0.914 |
Kubrick | +0.913 |
Neg logit contributions | |
Metatron | -1.770 |
Sac | -1.724 |
Syl | -1.668 |
Es | -1.649 |
Alphabet | -1.561 |
Token | story |
Token ID | 1621 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
declass | +1.007 |
lobb | +0.951 |
� | +0.890 |
Kubrick | +0.855 |
":[" | +0.849 |
Neg logit contributions | |
Metatron | -1.984 |
Sac | -1.926 |
Syl | -1.875 |
Es | -1.853 |
inventoryQuantity | -1.763 |
Token | Please |
Token ID | 4222 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
Metatron | +1.241 |
Sac | +1.193 |
Syl | +1.139 |
Es | +1.094 |
Alphabet | +1.039 |
Neg logit contributions | |
declass | -1.888 |
lobb | -1.827 |
� | -1.803 |
":[" | -1.737 |
bryce | -1.732 |
Token | verify |
Token ID | 11767 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Metatron | +6.829 |
Sac | +6.726 |
Syl | +6.401 |
Es | +6.239 |
Alphabet | +6.000 |
Neg logit contributions | |
declass | -7.428 |
� | -7.292 |
lobb | -7.229 |
bryce | -7.003 |
":[" | -6.902 |
Token | you |
Token ID | 345 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
declass | +2.375 |
lobb | +2.277 |
� | +2.204 |
":[" | +2.153 |
Kubrick | +2.112 |
Neg logit contributions | |
Metatron | -2.296 |
Sac | -2.239 |
Syl | -2.149 |
Es | -2.077 |
Alphabet | -1.999 |
Token | 're |
Token ID | 821 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Metatron | +0.412 |
Sac | +0.401 |
Syl | +0.384 |
Es | +0.375 |
Alphabet | +0.357 |
Neg logit contributions | |
declass | -0.421 |
lobb | -0.406 |
� | -0.401 |
Kubrick | -0.379 |
bryce | -0.379 |
Token | not |
Token ID | 407 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Metatron | +1.754 |
Sac | +1.713 |
Syl | +1.668 |
Es | +1.615 |
Alphabet | +1.568 |
Neg logit contributions | |
declass | -1.252 |
lobb | -1.207 |
� | -1.194 |
bryce | -1.120 |
":[" | -1.108 |
Token | a |
Token ID | 257 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Metatron | +0.135 |
Sac | +0.131 |
Syl | +0.126 |
Es | +0.122 |
Alphabet | +0.117 |
Neg logit contributions | |
declass | -0.134 |
lobb | -0.128 |
� | -0.126 |
":[" | -0.121 |
bryce | -0.120 |
Token | Continue |
Token ID | 10054 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Metatron | +0.352 |
Sac | +0.339 |
Syl | +0.325 |
Es | +0.314 |
Alphabet | +0.298 |
Neg logit contributions | |
declass | -0.470 |
lobb | -0.454 |
� | -0.448 |
":[" | -0.431 |
bryce | -0.428 |
Token | reading |
Token ID | 3555 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
Metatron | +1.513 |
Sac | +1.448 |
Syl | +1.383 |
Es | +1.323 |
Alphabet | +1.253 |
Neg logit contributions | |
declass | -2.500 |
lobb | -2.421 |
� | -2.396 |
":[" | -2.306 |
bryce | -2.299 |
Token | the |
Token ID | 262 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
declass | +2.393 |
lobb | +2.291 |
� | +2.200 |
":[" | +2.163 |
Kubrick | +2.150 |
Neg logit contributions | |
Metatron | -3.268 |
Sac | -3.181 |
Syl | -3.052 |
Es | -3.021 |
inventoryQuantity | -2.881 |
Token | main |
Token ID | 1388 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
declass | +2.613 |
lobb | +2.506 |
foreground | +2.237 |
� | +2.218 |
Kubrick | +2.214 |
Neg logit contributions | |
Metatron | -5.275 |
Sac | -5.168 |
Syl | -5.006 |
Es | -5.004 |
inventoryQuantity | -4.837 |
Token | story |
Token ID | 1621 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
declass | +0.972 |
lobb | +0.921 |
� | +0.835 |
Kubrick | +0.822 |
":[" | +0.821 |
Neg logit contributions | |
Metatron | -1.995 |
Sac | -1.940 |
Syl | -1.893 |
Es | -1.872 |
inventoryQuantity | -1.783 |
Token | Please |
Token ID | 4222 |
Feature activation | +9.92e+00 |
Pos logit contributions | |
Metatron | +1.382 |
Sac | +1.328 |
Syl | +1.271 |
Es | +1.221 |
Alphabet | +1.157 |
Neg logit contributions | |
declass | -2.070 |
lobb | -2.005 |
� | -1.976 |
":[" | -1.903 |
bryce | -1.895 |
Token | verify |
Token ID | 11767 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
Metatron | +6.790 |
Sac | +6.687 |
Syl | +6.317 |
Es | +6.196 |
Alphabet | +5.970 |
Neg logit contributions | |
declass | -7.267 |
� | -7.177 |
lobb | -7.105 |
bryce | -6.887 |
":[" | -6.779 |
Token | you |
Token ID | 345 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
declass | +2.626 |
lobb | +2.514 |
� | +2.417 |
":[" | +2.376 |
Ghostbusters | +2.332 |
Neg logit contributions | |
Metatron | -2.572 |
Sac | -2.514 |
Syl | -2.416 |
Es | -2.336 |
Alphabet | -2.244 |
Token | 're |
Token ID | 821 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Metatron | +0.217 |
Sac | +0.211 |
Syl | +0.203 |
Es | +0.197 |
Alphabet | +0.189 |
Neg logit contributions | |
declass | -0.212 |
lobb | -0.204 |
� | -0.201 |
":[" | -0.191 |
bryce | -0.191 |
Token | not |
Token ID | 407 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
Metatron | +1.609 |
Sac | +1.567 |
Syl | +1.526 |
Es | +1.479 |
Alphabet | +1.435 |
Neg logit contributions | |
declass | -1.132 |
lobb | -1.090 |
� | -1.078 |
bryce | -1.010 |
":[" | -1.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Metatron | +0.041 |
Sac | +0.040 |
Syl | +0.038 |
Es | +0.037 |
Alphabet | +0.036 |
Neg logit contributions | |
declass | -0.040 |
lobb | -0.039 |
� | -0.038 |
":[" | -0.036 |
bryce | -0.036 |
Token | ERA |
Token ID | 18802 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
Metatron | +1.718 |
Sac | +1.636 |
Syl | +1.559 |
Es | +1.508 |
Alphabet | +1.431 |
Neg logit contributions | |
declass | -2.935 |
lobb | -2.829 |
� | -2.801 |
bryce | -2.700 |
":[" | -2.694 |
Token | in |
Token ID | 287 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Metatron | +0.009 |
Sac | +0.009 |
Syl | +0.008 |
Es | +0.008 |
Alphabet | +0.008 |
Neg logit contributions | |
declass | -0.011 |
lobb | -0.010 |
� | -0.010 |
":[" | -0.010 |
bryce | -0.010 |
Token | 54 |
Token ID | 7175 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
declass | +1.635 |
lobb | +1.564 |
� | +1.531 |
FAC | +1.476 |
":[" | +1.472 |
Neg logit contributions | |
Metatron | -1.629 |
Sac | -1.585 |
Syl | -1.517 |
Es | -1.489 |
alia | -1.412 |
Token | 1 |
Token ID | 352 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
Metatron | +2.759 |
Sac | +2.700 |
Syl | +2.621 |
Es | +2.510 |
Alphabet | +2.395 |
Neg logit contributions | |
declass | -3.710 |
lobb | -3.555 |
� | -3.536 |
bryce | -3.431 |
":[" | -3.377 |
Token | / |
Token ID | 14 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
Metatron | +3.872 |
Sac | +3.830 |
Syl | +3.657 |
Es | +3.631 |
Alphabet | +3.400 |
Neg logit contributions | |
declass | -4.319 |
lobb | -4.187 |
� | -4.110 |
�� | -3.912 |
bryce | -3.910 |
Token | 3 |
Token ID | 18 |
Feature activation | +9.91e+00 |
Pos logit contributions | |
Metatron | +1.849 |
Sac | +1.819 |
Es | +1.704 |
Syl | +1.696 |
2020 | +1.566 |
Neg logit contributions | |
declass | -2.675 |
lobb | -2.577 |
� | -2.517 |
Kubrick | -2.422 |
":[" | -2.411 |
Token | IP |
Token ID | 6101 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Metatron | +4.527 |
Sac | +4.342 |
Syl | +4.207 |
Es | +4.038 |
Alphabet | +3.867 |
Neg logit contributions | |
declass | -9.492 |
� | -9.073 |
lobb | -9.023 |
�� | -8.984 |
bryce | -8.929 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Metatron | +1.608 |
Sac | +1.577 |
Syl | +1.512 |
Es | +1.469 |
Alphabet | +1.395 |
Neg logit contributions | |
declass | -1.932 |
lobb | -1.866 |
� | -1.840 |
bryce | -1.772 |
Kubrick | -1.769 |
Token |
|
Token ID | 198 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Metatron | +1.109 |
Sac | +1.076 |
Syl | +1.040 |
Es | +1.009 |
Alphabet | +0.969 |
Neg logit contributions | |
declass | -1.055 |
lobb | -1.014 |
� | -0.996 |
":[" | -0.951 |
bryce | -0.946 |
Token | Nick |
Token ID | 23609 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Metatron | +0.312 |
Sac | +0.303 |
Syl | +0.289 |
Es | +0.281 |
Alphabet | +0.266 |
Neg logit contributions | |
declass | -0.395 |
lobb | -0.382 |
� | -0.375 |
":[" | -0.359 |
bryce | -0.358 |
Token | Vincent |
Token ID | 18653 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
declass | +2.022 |
lobb | +1.952 |
� | +1.919 |
":[" | +1.839 |
Kubrick | +1.829 |
Neg logit contributions | |
Metatron | -1.814 |
Sac | -1.760 |
Syl | -1.688 |
Es | -1.642 |
Alphabet | -1.566 |
Token | both |
Token ID | 1111 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Metatron | +1.534 |
Sac | +1.483 |
Syl | +1.447 |
Es | +1.395 |
Alphabet | +1.348 |
Neg logit contributions | |
declass | -1.305 |
lobb | -1.248 |
� | -1.238 |
bryce | -1.181 |
":[" | -1.169 |
Token | died |
Token ID | 3724 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Metatron | +1.443 |
Sac | +1.390 |
Syl | +1.351 |
Es | +1.303 |
Alphabet | +1.251 |
Neg logit contributions | |
declass | -1.504 |
lobb | -1.440 |
� | -1.435 |
bryce | -1.368 |
":[" | -1.361 |
Token | of |
Token ID | 286 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
declass | +1.537 |
lobb | +1.474 |
� | +1.443 |
":[" | +1.380 |
Kubrick | +1.365 |
Neg logit contributions | |
Metatron | -1.574 |
Sac | -1.523 |
Syl | -1.463 |
Es | -1.418 |
Alphabet | -1.368 |
Token | cerebral |
Token ID | 31169 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
Metatron | +0.762 |
Sac | +0.742 |
Syl | +0.724 |
Es | +0.702 |
Alphabet | +0.673 |
Neg logit contributions | |
declass | -0.622 |
lobb | -0.589 |
� | -0.584 |
bryce | -0.560 |
":[" | -0.556 |
Token | ha |
Token ID | 387 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Metatron | +6.419 |
Sac | +6.370 |
Syl | +6.319 |
Es | +6.121 |
te | +6.032 |
Neg logit contributions | |
declass | -2.889 |
� | -2.752 |
lobb | -2.746 |
�� | -2.710 |
bryce | -2.676 |
Token | em |
Token ID | 368 |
Feature activation | +9.87e+00 |
Pos logit contributions | |
Metatron | +2.058 |
Sac | +2.049 |
Syl | +1.970 |
Es | +1.933 |
Alphabet | +1.848 |
Neg logit contributions | |
declass | -1.917 |
lobb | -1.864 |
� | -1.840 |
bryce | -1.742 |
":[" | -1.738 |
Token | or |
Token ID | 273 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
Sac | +6.048 |
Metatron | +5.921 |
Syl | +5.796 |
alia | +5.781 |
Es | +5.626 |
Neg logit contributions | |
declass | -7.677 |
lobb | -7.643 |
bryce | -7.231 |
� | -7.184 |
Kubrick | -7.094 |
Token | rh |
Token ID | 17179 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Metatron | +1.019 |
Sac | +0.965 |
Syl | +0.821 |
Es | +0.701 |
alia | +0.622 |
Neg logit contributions | |
declass | -6.411 |
� | -6.373 |
lobb | -6.332 |
":[" | -6.080 |
Ghostbusters | -6.043 |
Token | age |
Token ID | 496 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
Metatron | +2.168 |
Sac | +2.135 |
Syl | +2.036 |
Es | +1.968 |
Alphabet | +1.884 |
Neg logit contributions | |
declass | -2.815 |
lobb | -2.733 |
� | -2.696 |
bryce | -2.571 |
":[" | -2.566 |
Token | ," |
Token ID | 553 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
Metatron | +1.695 |
Sac | +1.642 |
Syl | +1.591 |
Es | +1.535 |
Alphabet | +1.458 |
Neg logit contributions | |
declass | -1.996 |
lobb | -1.931 |
� | -1.909 |
bryce | -1.835 |
":[" | -1.816 |
Token | said |
Token ID | 531 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
Metatron | +2.664 |
Sac | +2.604 |
Syl | +2.551 |
Es | +2.411 |
Alphabet | +2.326 |
Neg logit contributions | |
declass | -2.908 |
� | -2.811 |
lobb | -2.798 |
bryce | -2.703 |
":[" | -2.657 |
Token | IT |
Token ID | 2043 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
Metatron | +1.350 |
Sac | +1.314 |
Syl | +1.263 |
Es | +1.233 |
Alphabet | +1.174 |
Neg logit contributions | |
declass | -1.385 |
lobb | -1.332 |
� | -1.313 |
":[" | -1.250 |
bryce | -1.243 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Metatron | +2.977 |
Sac | +2.894 |
Syl | +2.806 |
Es | +2.744 |
Alphabet | +2.596 |
Neg logit contributions | |
declass | -3.049 |
lobb | -2.901 |
� | -2.887 |
":[" | -2.757 |
bryce | -2.750 |
Token | Lor |
Token ID | 26068 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Metatron | +1.417 |
Sac | +1.366 |
Syl | +1.329 |
Es | +1.282 |
Alphabet | +1.233 |
Neg logit contributions | |
declass | -1.441 |
lobb | -1.385 |
� | -1.368 |
":[" | -1.308 |
bryce | -1.302 |
Token | can |
Token ID | 5171 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Metatron | +3.430 |
Sac | +3.308 |
Syl | +3.243 |
Es | +3.061 |
alia | +2.958 |
Neg logit contributions | |
declass | -4.499 |
lobb | -4.369 |
� | -4.365 |
":[" | -4.199 |
FAC | -4.100 |
Token | Sir |
Token ID | 7361 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
Metatron | +0.752 |
Sac | +0.728 |
Syl | +0.703 |
Es | +0.680 |
Alphabet | +0.651 |
Neg logit contributions | |
declass | -0.809 |
lobb | -0.778 |
� | -0.766 |
":[" | -0.734 |
bryce | -0.730 |
Token | r |
Token ID | 81 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
Metatron | +3.107 |
Sac | +2.990 |
Syl | +2.940 |
Es | +2.819 |
Alphabet | +2.701 |
Neg logit contributions | |
declass | -3.225 |
lobb | -3.091 |
� | -3.073 |
":[" | -2.936 |
FAC | -2.872 |
Token | , |
Token ID | 11 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Metatron | +6.091 |
Sac | +5.913 |
Syl | +5.800 |
Es | +5.576 |
alia | +5.328 |
Neg logit contributions | |
declass | -7.568 |
� | -7.314 |
lobb | -7.235 |
�� | -7.145 |
":[" | -7.113 |
Token | says |
Token ID | 1139 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Metatron | +1.728 |
Sac | +1.662 |
Syl | +1.606 |
Es | +1.546 |
Alphabet | +1.478 |
Neg logit contributions | |
declass | -2.181 |
lobb | -2.100 |
� | -2.085 |
":[" | -2.004 |
bryce | -1.996 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Metatron | +0.125 |
Sac | +0.121 |
Syl | +0.116 |
Es | +0.112 |
Alphabet | +0.107 |
Neg logit contributions | |
declass | -0.135 |
lobb | -0.131 |
� | -0.127 |
":[" | -0.122 |
FAC | -0.121 |
Token | cost |
Token ID | 1575 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
Metatron | +1.026 |
Sac | +0.995 |
Syl | +0.967 |
Es | +0.939 |
Alphabet | +0.906 |
Neg logit contributions | |
declass | -0.883 |
lobb | -0.844 |
� | -0.838 |
":[" | -0.796 |
bryce | -0.792 |
Token | of |
Token ID | 286 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
Metatron | +1.959 |
Sac | +1.913 |
Syl | +1.822 |
Es | +1.773 |
Alphabet | +1.691 |
Neg logit contributions | |
declass | -2.427 |
lobb | -2.325 |
� | -2.323 |
":[" | -2.238 |
bryce | -2.209 |
Token | / |
Token ID | 14 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Metatron | +1.151 |
Sac | +1.111 |
Syl | +1.083 |
Es | +1.044 |
Alphabet | +1.008 |
Neg logit contributions | |
declass | -1.125 |
lobb | -1.082 |
� | -1.052 |
bryce | -1.019 |
":[" | -1.010 |
Token | any |
Token ID | 1092 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
declass | +0.947 |
lobb | +0.909 |
� | +0.901 |
":[" | +0.855 |
bryce | +0.848 |
Neg logit contributions | |
Metatron | -1.061 |
Sac | -1.026 |
Syl | -0.995 |
Es | -0.961 |
Alphabet | -0.931 |
Token | Mode |
Token ID | 10363 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
declass | +0.662 |
lobb | +0.640 |
� | +0.632 |
":[" | +0.606 |
bryce | +0.602 |
Neg logit contributions | |
Metatron | -0.513 |
Sac | -0.495 |
Syl | -0.475 |
Es | -0.458 |
Alphabet | -0.436 |
Token | : |
Token ID | 25 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Metatron | +1.823 |
Sac | +1.766 |
Syl | +1.691 |
Es | +1.633 |
Alphabet | +1.554 |
Neg logit contributions | |
declass | -2.428 |
lobb | -2.349 |
� | -2.312 |
bryce | -2.222 |
":[" | -2.206 |
Token | Man |
Token ID | 5124 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
declass | +1.434 |
lobb | +1.378 |
� | +1.365 |
":[" | +1.298 |
FAC | +1.277 |
Neg logit contributions | |
Metatron | -1.721 |
Sac | -1.659 |
Syl | -1.618 |
Es | -1.559 |
Alphabet | -1.515 |
Token | aged |
Token ID | 1886 |
Feature activation | +9.68e+00 |
Pos logit contributions | |
declass | +0.289 |
lobb | +0.274 |
� | +0.266 |
":[" | +0.253 |
bryce | +0.247 |
Neg logit contributions | |
Metatron | -0.526 |
Sac | -0.512 |
Syl | -0.500 |
Es | -0.487 |
Alphabet | -0.472 |
Token | Access |
Token ID | 8798 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Metatron | +5.927 |
Sac | +5.735 |
Syl | +5.666 |
Es | +5.308 |
Alphabet | +5.238 |
Neg logit contributions | |
declass | -7.869 |
lobb | -7.673 |
�� | -7.616 |
� | -7.578 |
bryce | -7.564 |
Token | Point |
Token ID | 6252 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Metatron | +1.101 |
Sac | +1.060 |
Syl | +1.018 |
Es | +0.976 |
Alphabet | +0.932 |
Neg logit contributions | |
declass | -1.561 |
lobb | -1.511 |
� | -1.488 |
bryce | -1.429 |
":[" | -1.428 |
Token | : |
Token ID | 25 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Metatron | +1.169 |
Sac | +1.126 |
Syl | +1.082 |
Es | +1.045 |
Alphabet | +0.997 |
Neg logit contributions | |
declass | -1.457 |
lobb | -1.406 |
� | -1.386 |
":[" | -1.334 |
bryce | -1.325 |
Token | Not |
Token ID | 1892 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Metatron | +0.986 |
Sac | +0.957 |
Syl | +0.933 |
Es | +0.905 |
Alphabet | +0.875 |
Neg logit contributions | |
declass | -0.729 |
lobb | -0.696 |
� | -0.677 |
bryce | -0.647 |
":[" | -0.642 |
Token | - |
Token ID | 12 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Metatron | +1.254 |
Sac | +1.212 |
Syl | +1.169 |
Es | +1.128 |
Alphabet | +1.080 |
Neg logit contributions | |
declass | -1.458 |
lobb | -1.406 |
� | -1.382 |
":[" | -1.323 |
bryce | -1.322 |
Token | Reading |
Token ID | 36120 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
Metatron | +2.229 |
Sac | +2.201 |
Syl | +2.025 |
Es | +2.012 |
2020 | +1.833 |
Neg logit contributions | |
declass | -4.023 |
lobb | -3.946 |
� | -3.851 |
Kubrick | -3.694 |
":[" | -3.670 |
Token | 55 |
Token ID | 5996 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
declass | +2.390 |
lobb | +2.253 |
� | +2.209 |
":[" | +2.099 |
FAC | +2.096 |
Neg logit contributions | |
Metatron | -3.135 |
Sac | -3.074 |
Syl | -2.950 |
Es | -2.902 |
Alphabet | -2.784 |
Token | 80 |
Token ID | 1795 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
declass | +0.999 |
lobb | +0.938 |
� | +0.933 |
":[" | +0.899 |
FAC | +0.880 |
Neg logit contributions | |
Metatron | -1.430 |
Sac | -1.362 |
Syl | -1.333 |
Es | -1.283 |
Alphabet | -1.266 |
Token | 953 |
Token ID | 49649 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
Metatron | +1.243 |
Sac | +1.165 |
Syl | +1.072 |
Es | +1.024 |
Alphabet | +0.930 |
Neg logit contributions | |
declass | -3.397 |
lobb | -3.299 |
� | -3.268 |
Kubrick | -3.151 |
FAC | -3.150 |
Token | 16 |
Token ID | 1467 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
Metatron | +1.887 |
Sac | +1.825 |
Syl | +1.776 |
Es | +1.704 |
Alphabet | +1.634 |
Neg logit contributions | |
declass | -1.861 |
lobb | -1.820 |
� | -1.788 |
bryce | -1.710 |
":[" | -1.691 |
Token | 27 |
Token ID | 1983 |
Feature activation | +9.66e+00 |
Pos logit contributions | |
Metatron | +2.309 |
Sac | +2.259 |
Syl | +2.158 |
Es | +2.085 |
Alphabet | +1.979 |
Neg logit contributions | |
declass | -3.120 |
lobb | -3.038 |
� | -2.985 |
bryce | -2.846 |
":[" | -2.832 |
Token | 145 |
Token ID | 18781 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Sac | +2.588 |
Metatron | +2.333 |
Syl | +2.078 |
Es | +2.009 |
2020 | +1.907 |
Neg logit contributions | |
declass | -11.189 |
lobb | -11.149 |
� | -10.885 |
�� | -10.745 |
Kubrick | -10.501 |
Token | Flat |
Token ID | 21939 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Metatron | +1.416 |
Sac | +1.346 |
Syl | +1.320 |
Es | +1.251 |
Alphabet | +1.206 |
Neg logit contributions | |
declass | -1.879 |
lobb | -1.833 |
� | -1.797 |
bryce | -1.738 |
":[" | -1.724 |
Token | buff |
Token ID | 36873 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
declass | +0.069 |
lobb | +0.066 |
� | +0.065 |
":[" | +0.063 |
bryce | +0.062 |
Neg logit contributions | |
Metatron | -0.080 |
Sac | -0.077 |
Syl | -0.075 |
Es | -0.072 |
Alphabet | -0.070 |
Token | ers |
Token ID | 364 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Metatron | +1.297 |
Sac | +1.266 |
Syl | +1.229 |
Es | +1.200 |
Alphabet | +1.159 |
Neg logit contributions | |
declass | -0.843 |
lobb | -0.802 |
� | -0.786 |
":[" | -0.738 |
bryce | -0.735 |
Token | Reading |
Token ID | 36120 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Metatron | +1.125 |
Sac | +1.066 |
Syl | +1.040 |
Es | +0.980 |
Alphabet | +0.950 |
Neg logit contributions | |
declass | -1.603 |
lobb | -1.539 |
� | -1.529 |
":[" | -1.490 |
bryce | -1.477 |
Token | short |
Token ID | 1790 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
declass | +0.070 |
lobb | +0.068 |
� | +0.066 |
":[" | +0.063 |
bryce | +0.063 |
Neg logit contributions | |
Metatron | -0.081 |
Sac | -0.079 |
Syl | -0.077 |
Es | -0.074 |
Alphabet | -0.071 |
Token | limit |
Token ID | 4179 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
Metatron | +1.180 |
Sac | +1.152 |
Syl | +1.118 |
Es | +1.088 |
Alphabet | +1.051 |
Neg logit contributions | |
declass | -0.850 |
lobb | -0.812 |
� | -0.801 |
bryce | -0.755 |
":[" | -0.751 |
Token | : |
Token ID | 25 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
declass | +0.598 |
lobb | +0.569 |
� | +0.564 |
":[" | +0.558 |
Kubrick | +0.543 |
Neg logit contributions | |
Metatron | -0.554 |
Sac | -0.525 |
Syl | -0.511 |
Es | -0.489 |
Alphabet | -0.472 |
Token | 7 |
Token ID | 22 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
declass | +1.241 |
lobb | +1.186 |
� | +1.174 |
":[" | +1.118 |
bryce | +1.107 |
Neg logit contributions | |
Metatron | -1.486 |
Sac | -1.436 |
Syl | -1.395 |
Es | -1.347 |
Alphabet | -1.305 |
Token | R |
Token ID | 371 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
Metatron | +2.925 |
Sac | +2.717 |
Syl | +2.662 |
Es | +2.425 |
Alphabet | +2.395 |
Neg logit contributions | |
declass | -5.779 |
lobb | -5.629 |
bryce | -5.537 |
� | -5.520 |
":[" | -5.361 |
Token | TS |
Token ID | 4694 |
Feature activation | +9.63e+00 |
Pos logit contributions | |
Metatron | +3.530 |
Sac | +3.503 |
Syl | +3.330 |
Es | +3.302 |
2020 | +3.131 |
Neg logit contributions | |
declass | -3.390 |
lobb | -3.291 |
� | -3.194 |
Kubrick | -3.026 |
bryce | -3.021 |
Token | thr |
Token ID | 5636 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
Metatron | +4.774 |
Sac | +4.628 |
Syl | +4.544 |
Es | +4.254 |
te | +4.112 |
Neg logit contributions | |
declass | -8.637 |
� | -8.628 |
lobb | -8.352 |
�� | -8.252 |
bryce | -8.211 |
Token | : |
Token ID | 25 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
Metatron | +3.436 |
Sac | +3.416 |
Syl | +3.209 |
Es | +3.128 |
Alphabet | +2.937 |
Neg logit contributions | |
declass | -5.259 |
lobb | -5.122 |
� | -5.038 |
bryce | -4.849 |
�� | -4.817 |
Token | off |
Token ID | 2364 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
Metatron | +2.157 |
Sac | +2.100 |
Syl | +1.973 |
Es | +1.915 |
Alphabet | +1.780 |
Neg logit contributions | |
declass | -4.010 |
lobb | -3.905 |
� | -3.854 |
bryce | -3.707 |
Kubrick | -3.687 |
Token | Frag |
Token ID | 24229 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
Metatron | +1.863 |
Sac | +1.804 |
Syl | +1.754 |
Es | +1.642 |
Alphabet | +1.613 |
Neg logit contributions | |
declass | -2.677 |
lobb | -2.614 |
� | -2.547 |
bryce | -2.501 |
Kubrick | -2.458 |
Token | ment |
Token ID | 434 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
Metatron | +3.191 |
Sac | +3.169 |
Syl | +2.967 |
Es | +2.830 |
alia | +2.681 |
Neg logit contributions | |
declass | -5.840 |
� | -5.767 |
lobb | -5.745 |
Kubrick | -5.408 |
FAC | -5.391 |
Token | garbage |
Token ID | 15413 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
declass | +1.393 |
lobb | +1.351 |
� | +1.286 |
":[" | +1.244 |
FAC | +1.238 |
Neg logit contributions | |
Metatron | -1.490 |
Sac | -1.449 |
Syl | -1.376 |
Es | -1.349 |
Alphabet | -1.299 |
Token | and |
Token ID | 290 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
declass | +0.447 |
lobb | +0.432 |
� | +0.417 |
":[" | +0.401 |
bryce | +0.398 |
Neg logit contributions | |
Metatron | -0.451 |
Sac | -0.436 |
Syl | -0.417 |
Es | -0.406 |
Alphabet | -0.391 |
Token | diver |
Token ID | 12312 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
declass | +1.749 |
lobb | +1.681 |
� | +1.600 |
bryce | +1.540 |
Kubrick | +1.539 |
Neg logit contributions | |
Metatron | -2.079 |
Sac | -2.019 |
Syl | -1.934 |
Es | -1.894 |
Alphabet | -1.823 |
Token | ting |
Token ID | 889 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
declass | +0.293 |
lobb | +0.283 |
� | +0.278 |
":[" | +0.268 |
bryce | +0.267 |
Neg logit contributions | |
Metatron | -0.227 |
Sac | -0.218 |
Syl | -0.209 |
Es | -0.202 |
Alphabet | -0.193 |
Token | the |
Token ID | 262 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Metatron | +0.706 |
Sac | +0.685 |
Syl | +0.665 |
Es | +0.642 |
Alphabet | +0.614 |
Neg logit contributions | |
declass | -0.696 |
lobb | -0.668 |
� | -0.660 |
":[" | -0.629 |
bryce | -0.627 |
Token | creek |
Token ID | 39459 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
Metatron | +1.800 |
Sac | +1.745 |
Syl | +1.696 |
Es | +1.608 |
Alphabet | +1.515 |
Neg logit contributions | |
declass | -2.498 |
lobb | -2.416 |
� | -2.409 |
":[" | -2.303 |
bryce | -2.298 |
Token | water |
Token ID | 1660 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Metatron | +5.620 |
Sac | +5.569 |
Syl | +5.457 |
te | +5.171 |
Es | +5.157 |
Neg logit contributions | |
declass | -7.631 |
� | -7.518 |
lobb | -7.381 |
bryce | -7.176 |
":[" | -7.037 |
Token | so |
Token ID | 523 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Metatron | +0.904 |
Sac | +0.876 |
Syl | +0.845 |
Es | +0.817 |
Alphabet | +0.782 |
Neg logit contributions | |
declass | -0.991 |
lobb | -0.954 |
� | -0.942 |
":[" | -0.900 |
bryce | -0.899 |
Token | as |
Token ID | 355 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
declass | +1.163 |
lobb | +1.118 |
� | +1.097 |
":[" | +1.046 |
bryce | +1.041 |
Neg logit contributions | |
Metatron | -1.256 |
Sac | -1.218 |
Syl | -1.176 |
Es | -1.142 |
Alphabet | -1.098 |
Token | to |
Token ID | 284 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
declass | +1.233 |
lobb | +1.188 |
� | +1.168 |
":[" | +1.119 |
bryce | +1.113 |
Neg logit contributions | |
Metatron | -1.138 |
Sac | -1.101 |
Syl | -1.060 |
Es | -1.027 |
Alphabet | -0.984 |
Token | facilitate |
Token ID | 15570 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
declass | +1.405 |
lobb | +1.340 |
� | +1.296 |
":[" | +1.257 |
beaut | +1.247 |
Neg logit contributions | |
Metatron | -1.412 |
Sac | -1.356 |
Syl | -1.295 |
Es | -1.277 |
Alphabet | -1.225 |
Token | Continue |
Token ID | 10054 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Metatron | +0.439 |
Sac | +0.423 |
Syl | +0.406 |
Es | +0.392 |
Alphabet | +0.372 |
Neg logit contributions | |
declass | -0.576 |
lobb | -0.556 |
� | -0.549 |
":[" | -0.528 |
bryce | -0.524 |
Token | reading |
Token ID | 3555 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
Metatron | +0.749 |
Sac | +0.727 |
Syl | +0.687 |
Es | +0.668 |
Alphabet | +0.625 |
Neg logit contributions | |
declass | -1.126 |
lobb | -1.095 |
� | -1.067 |
":[" | -1.034 |
Kubrick | -1.032 |
Token | the |
Token ID | 262 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
declass | +1.766 |
lobb | +1.693 |
� | +1.643 |
":[" | +1.585 |
Kubrick | +1.576 |
Neg logit contributions | |
Metatron | -2.242 |
Sac | -2.182 |
Syl | -2.096 |
Es | -2.069 |
2020 | -1.957 |
Token | main |
Token ID | 1388 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
declass | +1.265 |
lobb | +1.203 |
� | +1.155 |
":[" | +1.097 |
Kubrick | +1.094 |
Neg logit contributions | |
Metatron | -2.185 |
Sac | -2.134 |
Syl | -2.060 |
Es | -2.042 |
inventoryQuantity | -1.930 |
Token | story |
Token ID | 1621 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
declass | +1.025 |
lobb | +0.967 |
� | +0.897 |
Kubrick | +0.870 |
":[" | +0.857 |
Neg logit contributions | |
Metatron | -2.083 |
Sac | -2.027 |
Syl | -1.971 |
Es | -1.954 |
inventoryQuantity | -1.861 |
Token | Please |
Token ID | 4222 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
Metatron | +1.147 |
Sac | +1.102 |
Syl | +1.058 |
Es | +1.018 |
Alphabet | +0.958 |
Neg logit contributions | |
declass | -1.671 |
lobb | -1.620 |
� | -1.594 |
":[" | -1.535 |
Kubrick | -1.526 |
Token | verify |
Token ID | 11767 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
Metatron | +6.661 |
Sac | +6.562 |
Syl | +6.235 |
Es | +6.091 |
Alphabet | +5.889 |
Neg logit contributions | |
declass | -7.013 |
� | -6.894 |
lobb | -6.858 |
bryce | -6.596 |
":[" | -6.498 |
Token | you |
Token ID | 345 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
declass | +2.616 |
lobb | +2.505 |
� | +2.403 |
":[" | +2.363 |
Ghostbusters | +2.320 |
Neg logit contributions | |
Metatron | -2.603 |
Sac | -2.544 |
Syl | -2.446 |
Es | -2.366 |
Alphabet | -2.268 |
Token | 're |
Token ID | 821 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
declass | +0.101 |
lobb | +0.098 |
� | +0.096 |
":[" | +0.091 |
bryce | +0.091 |
Neg logit contributions | |
Metatron | -0.106 |
Sac | -0.103 |
Syl | -0.099 |
Es | -0.096 |
Alphabet | -0.093 |
Token | not |
Token ID | 407 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Metatron | +1.119 |
Sac | +1.092 |
Syl | +1.062 |
Es | +1.032 |
Alphabet | +1.000 |
Neg logit contributions | |
declass | -0.765 |
lobb | -0.735 |
� | -0.725 |
bryce | -0.679 |
":[" | -0.676 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
declass | +0.369 |
lobb | +0.355 |
� | +0.345 |
":[" | +0.333 |
bryce | +0.330 |
Neg logit contributions | |
Metatron | -0.384 |
Sac | -0.371 |
Syl | -0.359 |
Es | -0.349 |
Alphabet | -0.334 |
Token | apt |
Token ID | 2373 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
Metatron | +0.468 |
Sac | +0.459 |
Syl | +0.447 |
Es | +0.438 |
Alphabet | +0.426 |
Neg logit contributions | |
declass | -0.181 |
lobb | -0.168 |
� | -0.163 |
":[" | -0.149 |
bryce | -0.148 |
Token | or |
Token ID | 273 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Metatron | +0.597 |
Sac | +0.577 |
Syl | +0.561 |
Es | +0.545 |
Alphabet | +0.525 |
Neg logit contributions | |
declass | -0.465 |
lobb | -0.444 |
� | -0.428 |
":[" | -0.416 |
Kubrick | -0.409 |
Token | is |
Token ID | 318 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
declass | +1.021 |
lobb | +0.995 |
� | +0.961 |
FAC | +0.921 |
":[" | +0.920 |
Neg logit contributions | |
Metatron | -1.034 |
Sac | -0.999 |
Syl | -0.959 |
Es | -0.933 |
Alphabet | -0.893 |
Token | 6 |
Token ID | 718 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
declass | +0.893 |
lobb | +0.855 |
� | +0.832 |
Kubrick | +0.797 |
":[" | +0.795 |
Neg logit contributions | |
Metatron | -0.948 |
Sac | -0.921 |
Syl | -0.885 |
Es | -0.864 |
Alphabet | -0.824 |
Token | inches |
Token ID | 8331 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
declass | +3.376 |
lobb | +3.250 |
� | +3.170 |
":[" | +3.051 |
FAC | +3.039 |
Neg logit contributions | |
Metatron | -3.304 |
Sac | -3.193 |
Syl | -3.052 |
Es | -2.942 |
Alphabet | -2.824 |
Token | wider |
Token ID | 10595 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
declass | +3.913 |
lobb | +3.729 |
� | +3.556 |
Kubrick | +3.456 |
beaut | +3.388 |
Neg logit contributions | |
Metatron | -5.314 |
Sac | -5.220 |
Syl | -4.935 |
Es | -4.855 |
inventoryQuantity | -4.697 |
Token | than |
Token ID | 621 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
declass | +5.642 |
lobb | +5.330 |
� | +5.084 |
":[" | +4.958 |
beaut | +4.849 |
Neg logit contributions | |
Metatron | -9.129 |
Sac | -8.955 |
Syl | -8.566 |
Es | -8.430 |
inventoryQuantity | -8.056 |
Token | the |
Token ID | 262 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
declass | +2.774 |
lobb | +2.676 |
� | +2.573 |
Kubrick | +2.483 |
Ghostbusters | +2.468 |
Neg logit contributions | |
Metatron | -3.255 |
Sac | -3.179 |
Syl | -3.033 |
Es | -2.985 |
Alphabet | -2.815 |
Token | standard |
Token ID | 3210 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
declass | +2.264 |
lobb | +2.193 |
� | +2.110 |
Ghostbusters | +2.041 |
Kubrick | +2.038 |
Neg logit contributions | |
Metatron | -2.245 |
Sac | -2.190 |
Syl | -2.084 |
Es | -2.043 |
Alphabet | -1.925 |
Token | F |
Token ID | 376 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
declass | +2.969 |
lobb | +2.866 |
� | +2.689 |
Ghostbusters | +2.679 |
FAC | +2.665 |
Neg logit contributions | |
Metatron | -3.674 |
Sac | -3.615 |
Syl | -3.416 |
Es | -3.380 |
inventoryQuantity | -3.253 |
Token | - |
Token ID | 12 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
declass | +2.763 |
lobb | +2.653 |
� | +2.590 |
":[" | +2.519 |
Kubrick | +2.479 |
Neg logit contributions | |
Metatron | -2.702 |
Sac | -2.586 |
Syl | -2.486 |
Es | -2.379 |
Alphabet | -2.330 |
Token | The |
Token ID | 383 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Metatron | +0.512 |
Sac | +0.495 |
Syl | +0.479 |
Es | +0.463 |
Alphabet | +0.444 |
Neg logit contributions | |
declass | -0.540 |
lobb | -0.520 |
� | -0.508 |
bryce | -0.488 |
":[" | -0.487 |
Token | opening |
Token ID | 4756 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
declass | +0.919 |
lobb | +0.879 |
� | +0.861 |
":[" | +0.816 |
bryce | +0.810 |
Neg logit contributions | |
Metatron | -1.215 |
Sac | -1.183 |
Syl | -1.145 |
Es | -1.116 |
Alphabet | -1.076 |
Token | movie |
Token ID | 3807 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
declass | +1.958 |
lobb | +1.870 |
� | +1.809 |
":[" | +1.688 |
Kubrick | +1.656 |
Neg logit contributions | |
Metatron | -4.169 |
Sac | -4.085 |
Syl | -3.961 |
Es | -3.887 |
Alphabet | -3.761 |
Token | depicts |
Token ID | 28539 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
declass | +4.287 |
lobb | +4.239 |
� | +4.106 |
":[" | +3.964 |
Kubrick | +3.907 |
Neg logit contributions | |
Metatron | -4.397 |
Sac | -4.282 |
Syl | -4.083 |
Es | -3.993 |
inventoryQuantity | -3.813 |
Token | Hats |
Token ID | 37934 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
declass | +1.035 |
lobb | +0.996 |
� | +0.979 |
":[" | +0.934 |
bryce | +0.927 |
Neg logit contributions | |
Metatron | -1.072 |
Sac | -1.042 |
Syl | -1.004 |
Es | -0.976 |
Alphabet | -0.937 |
Token | une |
Token ID | 1726 |
Feature activation | -9.61e+00 |
Pos logit contributions | |
declass | +5.194 |
lobb | +4.930 |
� | +4.916 |
":[" | +4.830 |
bryce | +4.800 |
Neg logit contributions | |
Metatron | -2.471 |
Sac | -2.259 |
Syl | -2.189 |
Es | -2.045 |
Alphabet | -1.950 |
Token | Mik |
Token ID | 17722 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
declass | +4.925 |
� | +4.702 |
lobb | +4.671 |
":[" | +4.273 |
FAC | +4.263 |
Neg logit contributions | |
Metatron | -8.414 |
Sac | -8.313 |
Syl | -7.927 |
Es | -7.883 |
inventoryQuantity | -7.704 |
Token | u |
Token ID | 84 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
declass | +4.101 |
lobb | +3.878 |
":[" | +3.821 |
bryce | +3.801 |
� | +3.771 |
Neg logit contributions | |
Metatron | -3.835 |
Sac | -3.631 |
Syl | -3.497 |
Es | -3.390 |
Alphabet | -3.283 |
Token | � |
Token ID | 447 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
declass | +3.782 |
lobb | +3.650 |
� | +3.632 |
":[" | +3.430 |
Kubrick | +3.407 |
Neg logit contributions | |
Metatron | -3.771 |
Sac | -3.635 |
Syl | -3.515 |
Es | -3.419 |
inventoryQuantity | -3.297 |
Token | � |
Token ID | 247 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
declass | +1.223 |
lobb | +1.172 |
� | +1.161 |
":[" | +1.100 |
bryce | +1.096 |
Neg logit contributions | |
Metatron | -1.543 |
Sac | -1.496 |
Syl | -1.450 |
Es | -1.415 |
Alphabet | -1.361 |
Token | s |
Token ID | 82 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
declass | +1.928 |
lobb | +1.857 |
� | +1.848 |
":[" | +1.750 |
bryce | +1.740 |
Neg logit contributions | |
Metatron | -1.852 |
Sac | -1.785 |
Syl | -1.724 |
Es | -1.661 |
Alphabet | -1.611 |
Token | right |
Token ID | 826 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
declass | +0.452 |
lobb | +0.433 |
� | +0.424 |
":[" | +0.404 |
Kubrick | +0.403 |
Neg logit contributions | |
Metatron | -0.493 |
Sac | -0.479 |
Syl | -0.462 |
Es | -0.450 |
Alphabet | -0.432 |
Token | ? |
Token ID | 30 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
declass | +1.078 |
lobb | +1.044 |
� | +1.033 |
":[" | +0.989 |
Kubrick | +0.987 |
Neg logit contributions | |
Metatron | -0.752 |
Sac | -0.724 |
Syl | -0.690 |
Es | -0.670 |
Alphabet | -0.632 |
Token |
|
Token ID | 198 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
Metatron | +0.768 |
Sac | +0.743 |
Syl | +0.719 |
Es | +0.695 |
Alphabet | +0.668 |
Neg logit contributions | |
declass | -0.784 |
lobb | -0.755 |
� | -0.739 |
":[" | -0.708 |
bryce | -0.708 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
declass | +0.036 |
lobb | +0.034 |
� | +0.034 |
":[" | +0.033 |
Kubrick | +0.032 |
Neg logit contributions | |
Metatron | -0.041 |
Sac | -0.039 |
Syl | -0.038 |
Es | -0.037 |
Alphabet | -0.036 |
Token | Leave |
Token ID | 35087 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
declass | +1.414 |
� | +1.364 |
lobb | +1.363 |
":[" | +1.317 |
bryce | +1.305 |
Neg logit contributions | |
Metatron | -1.055 |
Sac | -0.989 |
Syl | -0.973 |
Es | -0.915 |
Alphabet | -0.894 |
Token | Shia |
Token ID | 27424 |
Feature activation | -9.60e+00 |
Pos logit contributions | |
declass | +1.973 |
lobb | +1.905 |
� | +1.854 |
":[" | +1.786 |
Kubrick | +1.783 |
Neg logit contributions | |
Metatron | -1.863 |
Sac | -1.814 |
Syl | -1.733 |
Es | -1.693 |
Alphabet | -1.617 |
Token | alone |
Token ID | 3436 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
declass | +6.479 |
lobb | +6.313 |
� | +6.253 |
Kubrick | +6.034 |
Ghostbusters | +5.868 |
Neg logit contributions | |
Metatron | -6.950 |
Sac | -6.728 |
Syl | -6.323 |
Es | -6.237 |
inventoryQuantity | -6.149 |
Token | , |
Token ID | 11 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
declass | +0.413 |
lobb | +0.398 |
� | +0.392 |
":[" | +0.374 |
Kubrick | +0.372 |
Neg logit contributions | |
Metatron | -0.385 |
Sac | -0.374 |
Syl | -0.359 |
Es | -0.349 |
Alphabet | -0.333 |
Token | guys |
Token ID | 3730 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Metatron | +0.566 |
Sac | +0.547 |
Syl | +0.529 |
Es | +0.511 |
Alphabet | +0.491 |
Neg logit contributions | |
declass | -0.578 |
lobb | -0.556 |
� | -0.549 |
":[" | -0.523 |
bryce | -0.523 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Metatron | +1.533 |
Sac | +1.474 |
Syl | +1.423 |
Es | +1.369 |
Alphabet | +1.313 |
Neg logit contributions | |
declass | -1.817 |
lobb | -1.752 |
� | -1.716 |
bryce | -1.655 |
":[" | -1.646 |
Token | You |
Token ID | 921 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Metatron | +0.147 |
Sac | +0.142 |
Syl | +0.136 |
Es | +0.133 |
Alphabet | +0.126 |
Neg logit contributions | |
declass | -0.170 |
lobb | -0.164 |
� | -0.162 |
":[" | -0.155 |
Kubrick | -0.155 |
Token | measures |
Token ID | 5260 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
Metatron | +0.310 |
Sac | +0.300 |
Syl | +0.290 |
Es | +0.281 |
Alphabet | +0.270 |
Neg logit contributions | |
declass | -0.314 |
lobb | -0.302 |
� | -0.298 |
":[" | -0.285 |
bryce | -0.283 |
Token | 0 |
Token ID | 657 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Metatron | +0.507 |
Sac | +0.491 |
Syl | +0.475 |
Es | +0.460 |
Alphabet | +0.443 |
Neg logit contributions | |
declass | -0.488 |
lobb | -0.470 |
� | -0.462 |
":[" | -0.441 |
bryce | -0.439 |
Token | . |
Token ID | 13 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
declass | +1.331 |
lobb | +1.270 |
� | +1.258 |
":[" | +1.202 |
FAC | +1.191 |
Neg logit contributions | |
Metatron | -1.371 |
Sac | -1.326 |
Syl | -1.278 |
Es | -1.231 |
Alphabet | -1.183 |
Token | 02 |
Token ID | 2999 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Metatron | +0.272 |
Sac | +0.263 |
Syl | +0.254 |
Es | +0.245 |
Alphabet | +0.236 |
Neg logit contributions | |
declass | -0.288 |
lobb | -0.277 |
� | -0.273 |
":[" | -0.262 |
bryce | -0.260 |
Token | inches |
Token ID | 8331 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
Metatron | +0.383 |
Sac | +0.371 |
Syl | +0.358 |
Es | +0.348 |
Alphabet | +0.335 |
Neg logit contributions | |
declass | -0.342 |
lobb | -0.328 |
� | -0.323 |
":[" | -0.308 |
bryce | -0.305 |
Token | wide |
Token ID | 3094 |
Feature activation | -9.33e+00 |
Pos logit contributions | |
declass | +4.371 |
lobb | +4.139 |
� | +4.071 |
FAC | +3.866 |
Kubrick | +3.864 |
Neg logit contributions | |
Metatron | -5.172 |
Sac | -4.980 |
Syl | -4.791 |
Es | -4.608 |
inventoryQuantity | -4.425 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
declass | +5.625 |
lobb | +5.295 |
� | +5.170 |
":[" | +4.924 |
FAC | +4.889 |
Neg logit contributions | |
Metatron | -7.746 |
Sac | -7.550 |
Syl | -7.280 |
Es | -7.018 |
inventoryQuantity | -6.778 |
Token | They |
Token ID | 1119 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
declass | +1.725 |
lobb | +1.649 |
� | +1.643 |
Kubrick | +1.575 |
":[" | +1.571 |
Neg logit contributions | |
Metatron | -1.536 |
Sac | -1.488 |
Syl | -1.423 |
Es | -1.387 |
Alphabet | -1.316 |
Token | then |
Token ID | 788 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
declass | +1.257 |
lobb | +1.197 |
� | +1.162 |
":[" | +1.116 |
Kubrick | +1.111 |
Neg logit contributions | |
Metatron | -1.428 |
Sac | -1.382 |
Syl | -1.331 |
Es | -1.300 |
Alphabet | -1.244 |
Token | put |
Token ID | 1234 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
declass | +2.388 |
lobb | +2.257 |
� | +2.161 |
FAC | +2.108 |
":[" | +2.104 |
Neg logit contributions | |
Metatron | -2.592 |
Sac | -2.511 |
Syl | -2.405 |
Es | -2.365 |
Alphabet | -2.253 |
Token | hundreds |
Token ID | 5179 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
Metatron | +0.995 |
Sac | +0.954 |
Syl | +0.931 |
Es | +0.897 |
Alphabet | +0.859 |
Neg logit contributions | |
declass | -1.044 |
lobb | -1.008 |
� | -1.001 |
":[" | -0.953 |
bryce | -0.952 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Metatron | +0.347 |
Sac | +0.334 |
Syl | +0.324 |
Es | +0.314 |
Alphabet | +0.302 |
Neg logit contributions | |
declass | -0.309 |
lobb | -0.295 |
� | -0.290 |
":[" | -0.279 |
Kubrick | -0.276 |
Token | ______ |
Token ID | 25947 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
declass | +0.160 |
lobb | +0.154 |
� | +0.151 |
":[" | +0.144 |
bryce | +0.143 |
Neg logit contributions | |
Metatron | -0.173 |
Sac | -0.169 |
Syl | -0.163 |
Es | -0.158 |
Alphabet | -0.152 |
Token |
|
Token ID | 198 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
declass | +1.081 |
lobb | +1.037 |
� | +1.023 |
":[" | +0.976 |
bryce | +0.968 |
Neg logit contributions | |
Metatron | -1.153 |
Sac | -1.118 |
Syl | -1.081 |
Es | -1.047 |
Alphabet | -1.008 |
Token |
|
Token ID | 198 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
declass | +0.420 |
lobb | +0.399 |
� | +0.391 |
":[" | +0.382 |
Kubrick | +0.375 |
Neg logit contributions | |
Metatron | -0.499 |
Sac | -0.479 |
Syl | -0.465 |
Es | -0.450 |
Alphabet | -0.435 |
Token | X |
Token ID | 55 |
Feature activation | -7.76e+00 |
Pos logit contributions | |
declass | +0.563 |
lobb | +0.543 |
� | +0.535 |
":[" | +0.513 |
bryce | +0.511 |
Neg logit contributions | |
Metatron | -0.479 |
Sac | -0.463 |
Syl | -0.446 |
Es | -0.430 |
Alphabet | -0.412 |
Token | avier |
Token ID | 19492 |
Feature activation | -9.32e+00 |
Pos logit contributions | |
declass | +5.159 |
lobb | +4.818 |
� | +4.817 |
FAC | +4.651 |
":[" | +4.580 |
Neg logit contributions | |
Metatron | -6.118 |
Sac | -5.871 |
Syl | -5.696 |
Es | -5.384 |
Alphabet | -5.340 |
Token | Dum |
Token ID | 30933 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
declass | +5.919 |
lobb | +5.354 |
� | +5.326 |
Kubrick | +5.295 |
FAC | +5.237 |
Neg logit contributions | |
Metatron | -7.305 |
Sac | -7.196 |
Es | -6.641 |
Syl | -6.585 |
inventoryQuantity | -6.571 |
Token | us |
Token ID | 385 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
declass | +3.036 |
lobb | +2.833 |
":[" | +2.772 |
� | +2.701 |
bryce | +2.647 |
Neg logit contributions | |
Metatron | -3.740 |
Sac | -3.464 |
Syl | -3.405 |
Es | -3.240 |
Tablet | -3.183 |
Token | que |
Token ID | 4188 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
declass | +2.606 |
lobb | +2.512 |
� | +2.475 |
":[" | +2.442 |
bryce | +2.412 |
Neg logit contributions | |
Metatron | -1.522 |
Sac | -1.431 |
Syl | -1.379 |
Es | -1.292 |
Alphabet | -1.250 |
Token | et |
Token ID | 2123 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
declass | +2.179 |
lobb | +2.090 |
� | +2.043 |
":[" | +1.954 |
FAC | +1.939 |
Neg logit contributions | |
Metatron | -2.706 |
Sac | -2.647 |
Syl | -2.531 |
Es | -2.474 |
Alphabet | -2.390 |
Token | al |
Token ID | 435 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
declass | +0.878 |
lobb | +0.855 |
� | +0.834 |
":[" | +0.825 |
Kubrick | +0.818 |
Neg logit contributions | |
Metatron | -0.280 |
Sac | -0.263 |
Syl | -0.238 |
Es | -0.226 |
Alphabet | -0.201 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
declass | +0.388 |
lobb | +0.369 |
� | +0.363 |
":[" | +0.352 |
Kubrick | +0.346 |
Neg logit contributions | |
Metatron | -0.452 |
Sac | -0.433 |
Syl | -0.423 |
Es | -0.408 |
Alphabet | -0.394 |
Token | Well |
Token ID | 5779 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
declass | +1.915 |
� | +1.846 |
lobb | +1.834 |
":[" | +1.790 |
bryce | +1.778 |
Neg logit contributions | |
Metatron | -1.370 |
Sac | -1.276 |
Syl | -1.274 |
Es | -1.170 |
Alphabet | -1.155 |
Token | , |
Token ID | 11 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
declass | +0.589 |
lobb | +0.566 |
� | +0.558 |
":[" | +0.534 |
Kubrick | +0.532 |
Neg logit contributions | |
Metatron | -0.510 |
Sac | -0.494 |
Syl | -0.475 |
Es | -0.460 |
Alphabet | -0.439 |
Token | it |
Token ID | 340 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
declass | +3.836 |
lobb | +3.619 |
� | +3.528 |
Kubrick | +3.515 |
Ghostbusters | +3.458 |
Neg logit contributions | |
Metatron | -3.506 |
Sac | -3.486 |
Syl | -3.302 |
Es | -3.241 |
inventoryQuantity | -3.106 |
Token | turns |
Token ID | 4962 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
declass | +2.820 |
lobb | +2.694 |
� | +2.627 |
Kubrick | +2.500 |
":[" | +2.474 |
Neg logit contributions | |
Metatron | -3.453 |
Sac | -3.372 |
Syl | -3.222 |
Es | -3.155 |
Alphabet | -3.011 |
Token | out |
Token ID | 503 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
declass | +4.278 |
lobb | +3.977 |
� | +3.849 |
Kubrick | +3.833 |
":[" | +3.806 |
Neg logit contributions | |
Metatron | -4.134 |
Sac | -4.029 |
Syl | -3.807 |
Es | -3.797 |
inventoryQuantity | -3.695 |
Token | that |
Token ID | 326 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
declass | +6.579 |
Kubrick | +6.183 |
lobb | +6.136 |
Ghostbusters | +6.013 |
� | +6.001 |
Neg logit contributions | |
Sac | -6.422 |
Metatron | -6.310 |
Syl | -6.030 |
Es | -5.983 |
inventoryQuantity | -5.961 |
Token | things |
Token ID | 1243 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
declass | +5.622 |
lobb | +5.279 |
Kubrick | +5.256 |
� | +5.186 |
Ghostbusters | +5.112 |
Neg logit contributions | |
Sac | -5.267 |
Metatron | -5.247 |
Syl | -4.989 |
Es | -4.860 |
inventoryQuantity | -4.843 |
Token | could |
Token ID | 714 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
declass | +1.154 |
lobb | +1.099 |
� | +1.083 |
":[" | +1.036 |
Kubrick | +1.027 |
Neg logit contributions | |
Metatron | -1.326 |
Sac | -1.293 |
Syl | -1.242 |
Es | -1.215 |
Alphabet | -1.161 |
Token | go |
Token ID | 467 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
declass | +3.444 |
� | +3.262 |
lobb | +3.211 |
":[" | +3.061 |
Kubrick | +3.052 |
Neg logit contributions | |
Metatron | -4.277 |
Sac | -4.110 |
Syl | -3.977 |
Es | -3.869 |
Alphabet | -3.696 |
Token | wrong |
Token ID | 2642 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
declass | +2.957 |
� | +2.801 |
lobb | +2.771 |
Kubrick | +2.633 |
FAC | +2.592 |
Neg logit contributions | |
Metatron | -3.756 |
Sac | -3.707 |
Syl | -3.526 |
Es | -3.463 |
2020 | -3.293 |
Token | U |
Token ID | 52 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
Metatron | +0.265 |
Sac | +0.256 |
Syl | +0.245 |
Es | +0.236 |
Alphabet | +0.224 |
Neg logit contributions | |
declass | -0.373 |
lobb | -0.361 |
� | -0.356 |
":[" | -0.342 |
bryce | -0.341 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Metatron | +0.329 |
Sac | +0.318 |
Syl | +0.307 |
Es | +0.297 |
Alphabet | +0.285 |
Neg logit contributions | |
declass | -0.339 |
lobb | -0.326 |
� | -0.320 |
":[" | -0.307 |
bryce | -0.305 |
Token | S |
Token ID | 50 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
declass | +1.327 |
lobb | +1.264 |
� | +1.264 |
":[" | +1.238 |
bryce | +1.212 |
Neg logit contributions | |
Metatron | -1.188 |
Sac | -1.098 |
Syl | -1.090 |
Es | -1.011 |
Alphabet | -1.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
declass | +1.720 |
lobb | +1.635 |
� | +1.594 |
":[" | +1.547 |
FAC | +1.540 |
Neg logit contributions | |
Metatron | -1.891 |
Sac | -1.821 |
Syl | -1.762 |
Es | -1.699 |
Alphabet | -1.629 |
Token | Immigration |
Token ID | 18204 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
Metatron | +0.195 |
Sac | +0.190 |
Syl | +0.184 |
Es | +0.180 |
Alphabet | +0.173 |
Neg logit contributions | |
declass | -0.158 |
lobb | -0.151 |
� | -0.149 |
":[" | -0.142 |
bryce | -0.142 |
Token | and |
Token ID | 290 |
Feature activation | -9.14e+00 |
Pos logit contributions | |
declass | +2.447 |
lobb | +2.360 |
� | +2.263 |
":[" | +2.169 |
FAC | +2.169 |
Neg logit contributions | |
Metatron | -2.758 |
Sac | -2.664 |
Syl | -2.575 |
Es | -2.495 |
Alphabet | -2.412 |
Token | Customs |
Token ID | 23888 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
declass | +1.216 |
lobb | +0.813 |
FAC | +0.637 |
� | +0.611 |
":[" | +0.593 |
Neg logit contributions | |
Metatron | -11.792 |
Sac | -11.481 |
Syl | -11.456 |
Es | -11.221 |
inventoryQuantity | -11.013 |
Token | Enforcement |
Token ID | 19198 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
declass | +2.373 |
lobb | +2.302 |
� | +2.171 |
":[" | +2.153 |
FAC | +2.140 |
Neg logit contributions | |
Metatron | -2.113 |
Sac | -2.051 |
Syl | -1.949 |
Es | -1.881 |
Alphabet | -1.811 |
Token | forb |
Token ID | 11747 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
declass | +2.024 |
lobb | +1.932 |
� | +1.846 |
FAC | +1.783 |
":[" | +1.776 |
Neg logit contributions | |
Metatron | -2.254 |
Sac | -2.189 |
Syl | -2.105 |
Es | -2.046 |
Alphabet | -1.965 |
Token | ade |
Token ID | 671 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
declass | +0.765 |
lobb | +0.720 |
� | +0.682 |
":[" | +0.662 |
bryce | +0.657 |
Neg logit contributions | |
Metatron | -1.293 |
Sac | -1.261 |
Syl | -1.236 |
Es | -1.196 |
Alphabet | -1.159 |
Token | his |
Token ID | 465 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
declass | +0.802 |
lobb | +0.775 |
� | +0.759 |
":[" | +0.735 |
Kubrick | +0.732 |
Neg logit contributions | |
Metatron | -0.500 |
Sac | -0.484 |
Syl | -0.458 |
Es | -0.441 |
Alphabet | -0.415 |
Token | � |
Token ID | 447 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
declass | +3.726 |
lobb | +3.649 |
� | +3.532 |
":[" | +3.366 |
FAC | +3.327 |
Neg logit contributions | |
Metatron | -4.062 |
Sac | -3.942 |
Syl | -3.792 |
Es | -3.687 |
Alphabet | -3.545 |
Token | � |
Token ID | 251 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
declass | +1.944 |
lobb | +1.861 |
� | +1.844 |
":[" | +1.745 |
bryce | +1.730 |
Neg logit contributions | |
Metatron | -2.784 |
Sac | -2.723 |
Syl | -2.633 |
Es | -2.585 |
Alphabet | -2.485 |
Token | when |
Token ID | 618 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
declass | +2.391 |
lobb | +2.312 |
� | +2.260 |
":[" | +2.156 |
Kubrick | +2.136 |
Neg logit contributions | |
Metatron | -2.442 |
Sac | -2.361 |
Syl | -2.278 |
Es | -2.217 |
Alphabet | -2.127 |
Token | , |
Token ID | 11 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
declass | +1.878 |
lobb | +1.809 |
� | +1.779 |
":[" | +1.696 |
FAC | +1.689 |
Neg logit contributions | |
Metatron | -1.810 |
Sac | -1.757 |
Syl | -1.685 |
Es | -1.641 |
Alphabet | -1.566 |
Token | in |
Token ID | 287 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
declass | +2.131 |
lobb | +2.052 |
� | +1.989 |
FAC | +1.906 |
Kubrick | +1.905 |
Neg logit contributions | |
Metatron | -2.148 |
Sac | -2.096 |
Syl | -2.012 |
Es | -1.963 |
Alphabet | -1.863 |
Token | fact |
Token ID | 1109 |
Feature activation | -9.09e+00 |
Pos logit contributions | |
declass | +3.113 |
lobb | +2.968 |
� | +2.887 |
FAC | +2.786 |
Kubrick | +2.755 |
Neg logit contributions | |
Metatron | -3.389 |
Sac | -3.290 |
Syl | -3.145 |
Es | -3.088 |
Alphabet | -2.940 |
Token | , |
Token ID | 11 |
Feature activation | -7.84e+00 |
Pos logit contributions | |
declass | +6.251 |
lobb | +5.998 |
� | +5.942 |
":[" | +5.674 |
FAC | +5.637 |
Neg logit contributions | |
Metatron | -6.568 |
Sac | -6.504 |
Syl | -6.145 |
Es | -6.023 |
2020 | -5.790 |
Token | it |
Token ID | 340 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
declass | +5.456 |
lobb | +5.237 |
� | +5.039 |
FAC | +4.951 |
":[" | +4.832 |
Neg logit contributions | |
Metatron | -5.754 |
Sac | -5.621 |
Syl | -5.303 |
Es | -5.250 |
2020 | -5.032 |
Token | has |
Token ID | 468 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
declass | +3.371 |
lobb | +3.313 |
� | +3.232 |
":[" | +3.074 |
FAC | +3.044 |
Neg logit contributions | |
Metatron | -3.671 |
Sac | -3.509 |
Syl | -3.414 |
Es | -3.267 |
Alphabet | -3.188 |
Token | long |
Token ID | 890 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
declass | +2.071 |
lobb | +1.994 |
� | +1.958 |
":[" | +1.870 |
FAC | +1.852 |
Neg logit contributions | |
Metatron | -1.992 |
Sac | -1.930 |
Syl | -1.857 |
Es | -1.807 |
Alphabet | -1.725 |
Token | been |
Token ID | 587 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Metatron | +1.868 |
Sac | +1.776 |
Syl | +1.713 |
Es | +1.631 |
Alphabet | +1.566 |
Neg logit contributions | |
declass | -2.689 |
lobb | -2.604 |
� | -2.594 |
":[" | -2.502 |
bryce | -2.501 |
Token | notification |
Token ID | 14483 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
Metatron | +0.742 |
Sac | +0.716 |
Syl | +0.693 |
Es | +0.670 |
Alphabet | +0.644 |
Neg logit contributions | |
declass | -0.777 |
lobb | -0.746 |
� | -0.733 |
bryce | -0.703 |
":[" | -0.703 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
declass | +1.985 |
lobb | +1.916 |
� | +1.884 |
":[" | +1.799 |
FAC | +1.780 |
Neg logit contributions | |
Metatron | -1.966 |
Sac | -1.919 |
Syl | -1.831 |
Es | -1.790 |
Alphabet | -1.702 |
Token | From |
Token ID | 3574 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
declass | +1.526 |
� | +1.466 |
lobb | +1.464 |
":[" | +1.392 |
Kubrick | +1.391 |
Neg logit contributions | |
Metatron | -1.342 |
Sac | -1.309 |
Syl | -1.244 |
Es | -1.224 |
Alphabet | -1.147 |
Token | the |
Token ID | 262 |
Feature activation | -6.37e+00 |
Pos logit contributions | |
declass | +3.946 |
lobb | +3.814 |
� | +3.805 |
Ghostbusters | +3.599 |
Kubrick | +3.592 |
Neg logit contributions | |
Metatron | -4.344 |
Sac | -4.333 |
Syl | -4.066 |
Es | -4.027 |
inventoryQuantity | -3.811 |
Token | Kodi |
Token ID | 44129 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
declass | +4.389 |
lobb | +4.295 |
� | +4.179 |
":[" | +4.020 |
Ghostbusters | +4.003 |
Neg logit contributions | |
Metatron | -4.692 |
Sac | -4.683 |
Syl | -4.400 |
Es | -4.377 |
inventoryQuantity | -4.166 |
Token | home |
Token ID | 1363 |
Feature activation | -9.06e+00 |
Pos logit contributions | |
declass | +4.369 |
lobb | +4.331 |
� | +4.135 |
":[" | +3.993 |
Kubrick | +3.956 |
Neg logit contributions | |
Metatron | -4.666 |
Sac | -4.656 |
Syl | -4.380 |
Es | -4.293 |
inventoryQuantity | -4.186 |
Token | screen |
Token ID | 3159 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
declass | +5.160 |
lobb | +4.869 |
� | +4.734 |
foreground | +4.505 |
":[" | +4.500 |
Neg logit contributions | |
Metatron | -7.813 |
Sac | -7.624 |
Syl | -7.294 |
Es | -7.202 |
inventoryQuantity | -6.950 |
Token | , |
Token ID | 11 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
declass | +2.629 |
lobb | +2.529 |
� | +2.507 |
":[" | +2.394 |
Kubrick | +2.355 |
Neg logit contributions | |
Metatron | -2.485 |
Sac | -2.429 |
Syl | -2.312 |
Es | -2.274 |
Alphabet | -2.147 |
Token | choose |
Token ID | 3853 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
declass | +2.095 |
lobb | +1.973 |
� | +1.942 |
":[" | +1.839 |
Kubrick | +1.818 |
Neg logit contributions | |
Metatron | -2.948 |
Sac | -2.879 |
Syl | -2.754 |
Es | -2.739 |
alia | -2.599 |
Token | � |
Token ID | 564 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Metatron | +0.168 |
Sac | +0.162 |
Syl | +0.155 |
Es | +0.150 |
Alphabet | +0.142 |
Neg logit contributions | |
declass | -0.225 |
lobb | -0.217 |
� | -0.214 |
":[" | -0.206 |
Kubrick | -0.205 |
Token | � |
Token ID | 246 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
declass | +1.352 |
� | +1.296 |
lobb | +1.294 |
":[" | +1.232 |
bryce | +1.189 |
Neg logit contributions | |
Metatron | -2.598 |
Sac | -2.501 |
Syl | -2.472 |
Es | -2.383 |
Alphabet | -2.320 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
declass | +0.288 |
lobb | +0.277 |
� | +0.273 |
":[" | +0.260 |
bryce | +0.259 |
Neg logit contributions | |
Metatron | -0.329 |
Sac | -0.319 |
Syl | -0.309 |
Es | -0.300 |
Alphabet | -0.290 |
Token | Centers |
Token ID | 22223 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
declass | +0.940 |
lobb | +0.898 |
� | +0.881 |
":[" | +0.839 |
bryce | +0.833 |
Neg logit contributions | |
Metatron | -1.074 |
Sac | -1.043 |
Syl | -1.008 |
Es | -0.981 |
Alphabet | -0.941 |
Token | for |
Token ID | 329 |
Feature activation | -7.35e+00 |
Pos logit contributions | |
declass | +1.884 |
lobb | +1.806 |
� | +1.780 |
":[" | +1.700 |
bryce | +1.681 |
Neg logit contributions | |
Metatron | -1.965 |
Sac | -1.904 |
Syl | -1.843 |
Es | -1.786 |
Alphabet | -1.711 |
Token | Disease |
Token ID | 17344 |
Feature activation | -6.39e+00 |
Pos logit contributions | |
declass | +6.167 |
� | +5.667 |
lobb | +5.614 |
FAC | +5.539 |
":[" | +5.503 |
Neg logit contributions | |
Metatron | -4.542 |
Sac | -4.412 |
Es | -4.192 |
Syl | -4.174 |
inventoryQuantity | -4.016 |
Token | Control |
Token ID | 6779 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
declass | +4.997 |
lobb | +4.821 |
� | +4.676 |
":[" | +4.652 |
FAC | +4.624 |
Neg logit contributions | |
Metatron | -4.187 |
Sac | -4.070 |
Syl | -3.970 |
Es | -3.841 |
inventoryQuantity | -3.702 |
Token | and |
Token ID | 290 |
Feature activation | -9.03e+00 |
Pos logit contributions | |
declass | +4.961 |
lobb | +4.710 |
� | +4.681 |
":[" | +4.387 |
FAC | +4.286 |
Neg logit contributions | |
Metatron | -5.592 |
Sac | -5.446 |
Syl | -5.220 |
Es | -5.100 |
inventoryQuantity | -4.933 |
Token | Prevention |
Token ID | 18313 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
declass | +6.981 |
lobb | +6.598 |
� | +6.462 |
":[" | +6.372 |
FAC | +6.318 |
Neg logit contributions | |
Metatron | -5.966 |
Sac | -5.887 |
Syl | -5.630 |
Es | -5.483 |
inventoryQuantity | -5.362 |
Token | in |
Token ID | 287 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
declass | +3.486 |
lobb | +3.320 |
� | +3.297 |
":[" | +3.094 |
Kubrick | +3.064 |
Neg logit contributions | |
Metatron | -3.564 |
Sac | -3.457 |
Syl | -3.321 |
Es | -3.229 |
Alphabet | -3.079 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Metatron | +0.171 |
Sac | +0.166 |
Syl | +0.160 |
Es | +0.156 |
Alphabet | +0.150 |
Neg logit contributions | |
declass | -0.157 |
lobb | -0.151 |
� | -0.148 |
":[" | -0.141 |
Kubrick | -0.140 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Metatron | +0.810 |
Sac | +0.783 |
Syl | +0.756 |
Es | +0.732 |
Alphabet | +0.700 |
Neg logit contributions | |
declass | -0.950 |
lobb | -0.916 |
� | -0.897 |
bryce | -0.865 |
":[" | -0.865 |
Token | Georgia |
Token ID | 7859 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
declass | +0.085 |
lobb | +0.081 |
� | +0.080 |
":[" | +0.075 |
bryce | +0.075 |
Neg logit contributions | |
Metatron | -0.134 |
Sac | -0.131 |
Syl | -0.127 |
Es | -0.124 |
Alphabet | -0.120 |
Token |
|
Token ID | 198 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
declass | +2.454 |
lobb | +2.322 |
� | +2.282 |
Kubrick | +2.197 |
":[" | +2.187 |
Neg logit contributions | |
Metatron | -2.869 |
Sac | -2.801 |
Syl | -2.703 |
Es | -2.621 |
Alphabet | -2.526 |
Token |
|
Token ID | 198 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
declass | +0.519 |
lobb | +0.490 |
� | +0.481 |
":[" | +0.471 |
Kubrick | +0.462 |
Neg logit contributions | |
Metatron | -0.629 |
Sac | -0.601 |
Syl | -0.587 |
Es | -0.567 |
Alphabet | -0.548 |
Token | 2012 |
Token ID | 6999 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
declass | +2.002 |
bryce | +1.949 |
":[" | +1.924 |
lobb | +1.893 |
� | +1.883 |
Neg logit contributions | |
Metatron | -1.613 |
Syl | -1.521 |
Sac | -1.450 |
Alphabet | -1.379 |
Es | -1.340 |
Token | Louis |
Token ID | 5593 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
Metatron | +1.910 |
Sac | +1.818 |
Syl | +1.786 |
Es | +1.705 |
Alphabet | +1.645 |
Neg logit contributions | |
declass | -2.094 |
lobb | -2.008 |
� | -1.980 |
bryce | -1.885 |
":[" | -1.885 |
Token | C |
Token ID | 327 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
declass | +1.877 |
lobb | +1.758 |
Kubrick | +1.696 |
� | +1.674 |
Ghostbusters | +1.631 |
Neg logit contributions | |
Sac | -3.409 |
Metatron | -3.409 |
Syl | -3.262 |
Es | -3.215 |
inventoryQuantity | -3.101 |
Token | . |
Token ID | 13 |
Feature activation | -9.02e+00 |
Pos logit contributions | |
declass | +3.510 |
lobb | +3.268 |
Kubrick | +3.250 |
":[" | +3.214 |
� | +3.162 |
Neg logit contributions | |
Metatron | -4.669 |
Sac | -4.471 |
Syl | -4.379 |
Es | -4.208 |
inventoryQuantity | -4.114 |
Token | K |
Token ID | 42 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
Kubrick | +4.123 |
declass | +3.987 |
":[" | +3.815 |
bryce | +3.787 |
lobb | +3.727 |
Neg logit contributions | |
Metatron | -8.470 |
Syl | -8.013 |
alia | -7.852 |
Sac | -7.643 |
inventoryQuantity | -7.617 |
Token | . |
Token ID | 13 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
declass | +2.565 |
lobb | +2.433 |
Kubrick | +2.369 |
":[" | +2.364 |
� | +2.351 |
Neg logit contributions | |
Metatron | -3.220 |
Sac | -3.102 |
Syl | -3.003 |
Es | -2.900 |
Alphabet | -2.798 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
declass | +2.585 |
lobb | +2.467 |
� | +2.404 |
Kubrick | +2.332 |
":[" | +2.321 |
Neg logit contributions | |
Metatron | -2.849 |
Sac | -2.775 |
Syl | -2.678 |
Es | -2.584 |
Alphabet | -2.491 |
Token |
|
Token ID | 198 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
declass | +2.124 |
lobb | +1.961 |
":[" | +1.951 |
� | +1.922 |
Kubrick | +1.889 |
Neg logit contributions | |
Metatron | -3.025 |
Sac | -2.846 |
Syl | -2.810 |
Es | -2.702 |
inventoryQuantity | -2.623 |
Token | 2012 |
Token ID | 6999 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
bryce | +2.717 |
declass | +2.713 |
":[" | +2.685 |
Kubrick | +2.540 |
� | +2.519 |
Neg logit contributions | |
Metatron | -2.509 |
Syl | -2.373 |
Sac | -2.182 |
Alphabet | -2.142 |
Tablet | -2.053 |
Token | he |
Token ID | 339 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Metatron | +2.070 |
Sac | +1.991 |
Syl | +1.941 |
Es | +1.863 |
Alphabet | +1.802 |
Neg logit contributions | |
declass | -2.148 |
lobb | -2.087 |
� | -2.085 |
bryce | -2.005 |
":[" | -1.987 |
Token | is |
Token ID | 318 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
Metatron | +1.652 |
Sac | +1.602 |
Syl | +1.544 |
Es | +1.502 |
Alphabet | +1.438 |
Neg logit contributions | |
declass | -1.614 |
lobb | -1.543 |
� | -1.535 |
bryce | -1.480 |
":[" | -1.466 |
Token | in |
Token ID | 287 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
Metatron | +2.833 |
Sac | +2.724 |
Syl | +2.634 |
Es | +2.562 |
Alphabet | +2.462 |
Neg logit contributions | |
declass | -2.733 |
lobb | -2.661 |
� | -2.656 |
bryce | -2.559 |
":[" | -2.545 |
Token | control |
Token ID | 1630 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Metatron | +0.717 |
Sac | +0.695 |
Syl | +0.674 |
Es | +0.653 |
Alphabet | +0.629 |
Neg logit contributions | |
declass | -0.658 |
lobb | -0.633 |
� | -0.624 |
":[" | -0.597 |
bryce | -0.596 |
Token | one |
Token ID | 530 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
declass | +0.279 |
lobb | +0.269 |
� | +0.265 |
":[" | +0.254 |
bryce | +0.252 |
Neg logit contributions | |
Metatron | -0.246 |
Sac | -0.238 |
Syl | -0.229 |
Es | -0.222 |
Alphabet | -0.212 |
Token | way |
Token ID | 835 |
Feature activation | -9.00e+00 |
Pos logit contributions | |
declass | +1.639 |
lobb | +1.569 |
� | +1.544 |
":[" | +1.463 |
Kubrick | +1.459 |
Neg logit contributions | |
Metatron | -1.743 |
Sac | -1.686 |
Syl | -1.628 |
Es | -1.584 |
Alphabet | -1.511 |
Token | or |
Token ID | 393 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
declass | +5.412 |
� | +5.120 |
lobb | +5.044 |
FAC | +4.720 |
Kubrick | +4.716 |
Neg logit contributions | |
Metatron | -7.497 |
Sac | -7.307 |
Syl | -7.044 |
Es | -6.920 |
inventoryQuantity | -6.831 |
Token | another |
Token ID | 1194 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
declass | +3.718 |
lobb | +3.560 |
� | +3.470 |
Kubrick | +3.312 |
FAC | +3.289 |
Neg logit contributions | |
Metatron | -3.992 |
Sac | -3.912 |
Syl | -3.737 |
Es | -3.684 |
2020 | -3.478 |
Token | of |
Token ID | 286 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
declass | +3.481 |
lobb | +3.330 |
� | +3.296 |
":[" | +3.098 |
FAC | +3.093 |
Neg logit contributions | |
Metatron | -3.561 |
Sac | -3.493 |
Syl | -3.339 |
Es | -3.252 |
Alphabet | -3.127 |
Token | his |
Token ID | 465 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
declass | +0.463 |
lobb | +0.444 |
� | +0.434 |
":[" | +0.414 |
bryce | +0.412 |
Neg logit contributions | |
Metatron | -0.510 |
Sac | -0.495 |
Syl | -0.478 |
Es | -0.465 |
Alphabet | -0.447 |
Token | " |
Token ID | 366 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
Metatron | +0.059 |
Sac | +0.057 |
Syl | +0.055 |
Es | +0.054 |
Alphabet | +0.052 |
Neg logit contributions | |
declass | -0.049 |
lobb | -0.047 |
� | -0.046 |
":[" | -0.044 |
bryce | -0.043 |
Token | SAS |
Token ID | 35516 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
declass | +1.143 |
lobb | +1.100 |
� | +1.075 |
":[" | +1.032 |
Kubrick | +1.032 |
Neg logit contributions | |
Metatron | -1.047 |
Sac | -1.019 |
Syl | -0.973 |
Es | -0.951 |
Alphabet | -0.907 |
Token | K |
Token ID | 42 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
declass | +0.762 |
lobb | +0.734 |
� | +0.723 |
":[" | +0.693 |
bryce | +0.691 |
Neg logit contributions | |
Metatron | -0.664 |
Sac | -0.642 |
Syl | -0.618 |
Es | -0.597 |
Alphabet | -0.572 |
Token | ATCH |
Token ID | 11417 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
declass | +3.301 |
lobb | +3.177 |
� | +3.119 |
":[" | +3.002 |
FAC | +2.999 |
Neg logit contributions | |
Metatron | -2.731 |
Sac | -2.615 |
Syl | -2.534 |
Es | -2.406 |
Alphabet | -2.332 |
Token | EW |
Token ID | 6217 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
declass | +2.213 |
lobb | +2.126 |
� | +2.089 |
":[" | +2.011 |
Kubrick | +2.004 |
Neg logit contributions | |
Metatron | -1.874 |
Sac | -1.800 |
Syl | -1.737 |
Es | -1.656 |
Alphabet | -1.602 |
Token | AN |
Token ID | 1565 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
declass | +2.701 |
lobb | +2.604 |
� | +2.552 |
Kubrick | +2.455 |
":[" | +2.455 |
Neg logit contributions | |
Metatron | -2.301 |
Sac | -2.201 |
Syl | -2.136 |
Es | -2.016 |
Alphabet | -1.959 |
Token | - |
Token ID | 532 |
Feature activation | -8.95e+00 |
Pos logit contributions | |
declass | +1.074 |
lobb | +1.035 |
� | +1.019 |
":[" | +0.976 |
bryce | +0.972 |
Neg logit contributions | |
Metatron | -0.954 |
Sac | -0.923 |
Syl | -0.889 |
Es | -0.860 |
Alphabet | -0.822 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
declass | +4.495 |
lobb | +3.864 |
foreground | +3.609 |
Kubrick | +3.557 |
FAC | +3.529 |
Neg logit contributions | |
Metatron | -8.434 |
Sac | -8.264 |
Syl | -7.908 |
Es | -7.838 |
alia | -7.615 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
declass | +3.254 |
lobb | +2.897 |
Kubrick | +2.713 |
foreground | +2.695 |
Ghostbusters | +2.646 |
Neg logit contributions | |
Metatron | -5.599 |
Sac | -5.458 |
Es | -5.245 |
Syl | -5.241 |
alia | -5.032 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
declass | +3.198 |
lobb | +2.851 |
Kubrick | +2.669 |
foreground | +2.652 |
Ghostbusters | +2.606 |
Neg logit contributions | |
Metatron | -5.491 |
Sac | -5.352 |
Es | -5.137 |
Syl | -5.137 |
alia | -4.927 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
declass | +2.905 |
lobb | +2.629 |
Kubrick | +2.457 |
foreground | +2.425 |
Ghostbusters | +2.398 |
Neg logit contributions | |
Metatron | -4.751 |
Sac | -4.631 |
Syl | -4.447 |
Es | -4.422 |
alia | -4.243 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.63e+00 |
Pos logit contributions | |
declass | +3.429 |
lobb | +3.151 |
� | +2.952 |
Kubrick | +2.942 |
Ghostbusters | +2.887 |
Neg logit contributions | |
Metatron | -5.033 |
Sac | -4.898 |
Syl | -4.715 |
Es | -4.645 |
alia | -4.455 |
Token | ett |
Token ID | 3087 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
declass | +0.958 |
lobb | +0.926 |
� | +0.906 |
":[" | +0.872 |
bryce | +0.870 |
Neg logit contributions | |
Metatron | -0.865 |
Sac | -0.838 |
Syl | -0.808 |
Es | -0.779 |
Alphabet | -0.747 |
Token | in |
Token ID | 259 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
declass | +0.351 |
lobb | +0.340 |
� | +0.334 |
":[" | +0.322 |
bryce | +0.321 |
Neg logit contributions | |
Metatron | -0.240 |
Sac | -0.232 |
Syl | -0.220 |
Es | -0.213 |
Alphabet | -0.201 |
Token | Old |
Token ID | 5706 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
declass | +2.170 |
lobb | +2.097 |
� | +2.056 |
Kubrick | +1.987 |
FAC | +1.977 |
Neg logit contributions | |
Metatron | -1.990 |
Sac | -1.936 |
Syl | -1.834 |
Es | -1.798 |
Alphabet | -1.693 |
Token | - |
Token ID | 12 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
declass | +3.655 |
lobb | +3.514 |
� | +3.393 |
Ghostbusters | +3.360 |
FAC | +3.348 |
Neg logit contributions | |
Metatron | -3.464 |
Sac | -3.373 |
Syl | -3.169 |
Es | -3.099 |
inventoryQuantity | -3.046 |
Token | E |
Token ID | 36 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
declass | +0.026 |
lobb | +0.025 |
� | +0.025 |
":[" | +0.024 |
bryce | +0.024 |
Neg logit contributions | |
Metatron | -0.020 |
Sac | -0.019 |
Syl | -0.018 |
Es | -0.018 |
Alphabet | -0.017 |
Token | pt |
Token ID | 457 |
Feature activation | -8.87e+00 |
Pos logit contributions | |
declass | +1.010 |
lobb | +0.976 |
� | +0.960 |
":[" | +0.922 |
bryce | +0.918 |
Neg logit contributions | |
Metatron | -0.805 |
Sac | -0.777 |
Syl | -0.745 |
Es | -0.717 |
Alphabet | -0.686 |
Token | sch |
Token ID | 20601 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
declass | +6.177 |
lobb | +5.936 |
� | +5.741 |
Kubrick | +5.703 |
bryce | +5.692 |
Neg logit contributions | |
Metatron | -6.368 |
Sac | -6.154 |
Syl | -5.850 |
Es | -5.783 |
inventoryQuantity | -5.604 |
Token | tein |
Token ID | 22006 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
declass | +1.204 |
lobb | +1.164 |
� | +1.145 |
":[" | +1.100 |
Kubrick | +1.094 |
Neg logit contributions | |
Metatron | -1.009 |
Sac | -0.977 |
Syl | -0.936 |
Es | -0.906 |
Alphabet | -0.864 |
Token | Pt |
Token ID | 34352 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
declass | +4.241 |
lobb | +4.071 |
� | +3.999 |
Kubrick | +3.904 |
Ghostbusters | +3.885 |
Neg logit contributions | |
Metatron | -4.276 |
Sac | -4.091 |
Syl | -3.886 |
Es | -3.872 |
inventoryQuantity | -3.728 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
declass | +0.893 |
lobb | +0.859 |
� | +0.843 |
":[" | +0.807 |
Kubrick | +0.806 |
Neg logit contributions | |
Metatron | -0.847 |
Sac | -0.820 |
Syl | -0.787 |
Es | -0.765 |
Alphabet | -0.732 |
Token | - |
Token ID | 12 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
declass | +1.123 |
lobb | +1.077 |
� | +1.060 |
":[" | +1.013 |
bryce | +1.007 |
Neg logit contributions | |
Metatron | -1.163 |
Sac | -1.124 |
Syl | -1.084 |
Es | -1.053 |
Alphabet | -1.011 |
Token | n |
Token ID | 77 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
declass | +1.363 |
lobb | +1.316 |
� | +1.286 |
bryce | +1.249 |
":[" | +1.247 |
Neg logit contributions | |
Metatron | -1.032 |
Sac | -0.977 |
Syl | -0.947 |
Es | -0.909 |
Alphabet | -0.865 |
Token | h |
Token ID | 71 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
declass | +0.887 |
lobb | +0.854 |
� | +0.830 |
":[" | +0.813 |
bryce | +0.808 |
Neg logit contributions | |
Metatron | -0.848 |
Sac | -0.804 |
Syl | -0.779 |
Es | -0.755 |
Alphabet | -0.727 |
Token | ts |
Token ID | 912 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
declass | +0.902 |
lobb | +0.861 |
� | +0.832 |
":[" | +0.807 |
bryce | +0.803 |
Neg logit contributions | |
Metatron | -1.017 |
Sac | -0.961 |
Syl | -0.935 |
Es | -0.909 |
Alphabet | -0.881 |
Token | a |
Token ID | 64 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
declass | +3.073 |
lobb | +2.909 |
":[" | +2.836 |
bryce | +2.685 |
� | +2.667 |
Neg logit contributions | |
Metatron | -3.629 |
Sac | -3.331 |
Syl | -3.320 |
Es | -3.199 |
Alphabet | -3.081 |
Token | . |
Token ID | 13 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
declass | +3.312 |
lobb | +3.083 |
":[" | +3.056 |
bryce | +2.914 |
Kubrick | +2.894 |
Neg logit contributions | |
Metatron | -4.464 |
Syl | -4.149 |
Sac | -4.141 |
Es | -3.935 |
inventoryQuantity | -3.884 |
Token | dot |
Token ID | 26518 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
declass | +4.293 |
lobb | +4.076 |
bryce | +3.887 |
� | +3.878 |
":[" | +3.848 |
Neg logit contributions | |
Metatron | -4.147 |
Sac | -3.940 |
Syl | -3.811 |
Es | -3.716 |
Alphabet | -3.529 |
Token | . |
Token ID | 13 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
declass | +4.738 |
":[" | +4.469 |
lobb | +4.259 |
Kubrick | +4.126 |
FAC | +4.078 |
Neg logit contributions | |
Metatron | -7.856 |
Sac | -7.214 |
Syl | -7.074 |
inventoryQuantity | -7.025 |
Es | -6.855 |
Token | gov |
Token ID | 9567 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
declass | +2.381 |
lobb | +2.191 |
":[" | +2.143 |
Kubrick | +2.034 |
bryce | +2.034 |
Neg logit contributions | |
Metatron | -4.834 |
Sac | -4.591 |
Syl | -4.519 |
Es | -4.383 |
inventoryQuantity | -4.279 |
Token | / |
Token ID | 14 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
declass | +2.440 |
lobb | +2.289 |
":[" | +2.238 |
� | +2.199 |
Kubrick | +2.155 |
Neg logit contributions | |
Metatron | -3.511 |
Sac | -3.354 |
Syl | -3.259 |
Es | -3.178 |
inventoryQuantity | -3.089 |
Token | people |
Token ID | 15332 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
declass | +2.708 |
lobb | +2.564 |
� | +2.488 |
bryce | +2.380 |
":[" | +2.363 |
Neg logit contributions | |
Metatron | -4.053 |
Sac | -3.853 |
Syl | -3.830 |
Es | -3.665 |
Alphabet | -3.596 |
Token | / |
Token ID | 14 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
declass | +3.689 |
lobb | +3.524 |
� | +3.402 |
":[" | +3.343 |
bryce | +3.304 |
Neg logit contributions | |
Metatron | -4.461 |
Sac | -4.196 |
Syl | -4.129 |
Es | -3.880 |
Alphabet | -3.819 |
Token | fourth |
Token ID | 5544 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
declass | +1.479 |
lobb | +1.425 |
� | +1.396 |
":[" | +1.319 |
FAC | +1.314 |
Neg logit contributions | |
Metatron | -1.584 |
Sac | -1.535 |
Syl | -1.474 |
Es | -1.441 |
Alphabet | -1.380 |
Token | big |
Token ID | 1263 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
declass | +2.524 |
lobb | +2.420 |
� | +2.368 |
":[" | +2.259 |
Ghostbusters | +2.251 |
Neg logit contributions | |
Metatron | -2.820 |
Sac | -2.732 |
Syl | -2.614 |
Es | -2.568 |
Alphabet | -2.459 |
Token | Project |
Token ID | 4935 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
declass | +1.876 |
lobb | +1.802 |
� | +1.761 |
Ghostbusters | +1.673 |
":[" | +1.671 |
Neg logit contributions | |
Metatron | -2.061 |
Sac | -1.998 |
Syl | -1.923 |
Es | -1.865 |
Alphabet | -1.800 |
Token | DI |
Token ID | 14766 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
Metatron | +0.145 |
Sac | +0.140 |
Syl | +0.135 |
Es | +0.131 |
Alphabet | +0.125 |
Neg logit contributions | |
declass | -0.163 |
lobb | -0.157 |
� | -0.155 |
":[" | -0.148 |
bryce | -0.147 |
Token | va |
Token ID | 6862 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Metatron | +0.714 |
Sac | +0.692 |
Syl | +0.668 |
Es | +0.647 |
Alphabet | +0.620 |
Neg logit contributions | |
declass | -0.744 |
lobb | -0.716 |
� | -0.705 |
":[" | -0.674 |
bryce | -0.672 |
Token | X |
Token ID | 1395 |
Feature activation | -8.85e+00 |
Pos logit contributions | |
declass | +1.075 |
lobb | +1.031 |
� | +1.009 |
":[" | +0.959 |
Kubrick | +0.957 |
Neg logit contributions | |
Metatron | -1.154 |
Sac | -1.115 |
Syl | -1.075 |
Es | -1.039 |
Alphabet | -1.007 |
Token | update |
Token ID | 4296 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
declass | +5.932 |
lobb | +5.763 |
� | +5.548 |
Ghostbusters | +5.351 |
beaut | +5.327 |
Neg logit contributions | |
Metatron | -6.539 |
Sac | -6.266 |
inventoryQuantity | -6.040 |
Syl | -5.985 |
Es | -5.797 |
Token | is |
Token ID | 318 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
declass | +1.554 |
lobb | +1.494 |
� | +1.436 |
":[" | +1.381 |
FAC | +1.377 |
Neg logit contributions | |
Metatron | -1.512 |
Sac | -1.464 |
Syl | -1.395 |
Es | -1.371 |
Alphabet | -1.305 |
Token | in |
Token ID | 287 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
declass | +1.345 |
lobb | +1.278 |
� | +1.248 |
":[" | +1.190 |
FAC | +1.189 |
Neg logit contributions | |
Metatron | -1.299 |
Sac | -1.263 |
Syl | -1.201 |
Es | -1.169 |
Alphabet | -1.120 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
declass | +1.098 |
lobb | +1.053 |
� | +1.034 |
":[" | +0.984 |
bryce | +0.977 |
Neg logit contributions | |
Metatron | -1.221 |
Sac | -1.186 |
Syl | -1.145 |
Es | -1.113 |
Alphabet | -1.069 |
Token |
|
Token ID | 198 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
declass | +1.194 |
lobb | +1.148 |
� | +1.139 |
":[" | +1.083 |
Kubrick | +1.080 |
Neg logit contributions | |
Metatron | -1.049 |
Sac | -1.016 |
Syl | -0.971 |
Es | -0.944 |
Alphabet | -0.900 |
Token | with |
Token ID | 351 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Metatron | +0.300 |
Sac | +0.290 |
Syl | +0.280 |
Es | +0.271 |
Alphabet | +0.260 |
Neg logit contributions | |
declass | -0.311 |
lobb | -0.300 |
� | -0.295 |
":[" | -0.282 |
bryce | -0.280 |
Token | someone |
Token ID | 2130 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Metatron | +2.115 |
Sac | +2.029 |
Syl | +1.971 |
Es | +1.898 |
Alphabet | +1.831 |
Neg logit contributions | |
declass | -2.357 |
lobb | -2.272 |
� | -2.238 |
":[" | -2.146 |
bryce | -2.139 |
Token | as |
Token ID | 355 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
declass | +0.929 |
lobb | +0.895 |
� | +0.888 |
Kubrick | +0.846 |
":[" | +0.846 |
Neg logit contributions | |
Metatron | -0.724 |
Sac | -0.702 |
Syl | -0.669 |
Es | -0.648 |
Alphabet | -0.614 |
Token | interesting |
Token ID | 3499 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
declass | +0.375 |
lobb | +0.357 |
� | +0.352 |
":[" | +0.331 |
Kubrick | +0.329 |
Neg logit contributions | |
Metatron | -0.525 |
Sac | -0.511 |
Syl | -0.496 |
Es | -0.484 |
Alphabet | -0.466 |
Token | and |
Token ID | 290 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
declass | +1.699 |
lobb | +1.632 |
� | +1.619 |
":[" | +1.525 |
Kubrick | +1.510 |
Neg logit contributions | |
Metatron | -2.048 |
Sac | -1.988 |
Syl | -1.921 |
Es | -1.873 |
Alphabet | -1.793 |
Token | accomplished |
Token ID | 13013 |
Feature activation | -8.78e+00 |
Pos logit contributions | |
declass | +1.939 |
lobb | +1.842 |
� | +1.820 |
FAC | +1.698 |
Kubrick | +1.696 |
Neg logit contributions | |
Metatron | -2.713 |
Sac | -2.629 |
Syl | -2.567 |
Es | -2.492 |
Alphabet | -2.394 |
Token | as |
Token ID | 355 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
declass | +4.796 |
� | +4.687 |
lobb | +4.607 |
":[" | +4.334 |
FAC | +4.255 |
Neg logit contributions | |
Metatron | -7.658 |
Sac | -7.467 |
Syl | -7.172 |
Es | -7.057 |
Alphabet | -6.750 |
Token | Will |
Token ID | 2561 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
declass | +1.159 |
lobb | +1.118 |
� | +1.098 |
":[" | +1.063 |
Kubrick | +1.060 |
Neg logit contributions | |
Metatron | -1.019 |
Sac | -1.002 |
Syl | -0.942 |
Es | -0.927 |
Alphabet | -0.868 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
declass | +1.029 |
lobb | +0.987 |
� | +0.974 |
Kubrick | +0.923 |
":[" | +0.920 |
Neg logit contributions | |
Metatron | -1.184 |
Sac | -1.158 |
Syl | -1.110 |
Es | -1.077 |
Alphabet | -1.040 |
Token | Whether |
Token ID | 10127 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
Metatron | +1.054 |
Sac | +1.018 |
Syl | +0.981 |
Es | +0.947 |
Alphabet | +0.907 |
Neg logit contributions | |
declass | -1.218 |
lobb | -1.176 |
� | -1.153 |
":[" | -1.107 |
bryce | -1.104 |
Token | you |
Token ID | 345 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Metatron | +1.731 |
Sac | +1.666 |
Syl | +1.608 |
Es | +1.550 |
Alphabet | +1.491 |
Neg logit contributions | |
declass | -2.198 |
lobb | -2.117 |
� | -2.100 |
":[" | -2.011 |
bryce | -2.010 |
Token | people |
Token ID | 661 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
declass | +1.368 |
lobb | +1.322 |
� | +1.300 |
":[" | +1.244 |
bryce | +1.239 |
Neg logit contributions | |
Metatron | -1.193 |
Sac | -1.155 |
Syl | -1.108 |
Es | -1.075 |
Alphabet | -1.026 |
Token | ? |
Token ID | 30 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
declass | +1.105 |
lobb | +1.070 |
� | +1.056 |
":[" | +1.012 |
bryce | +1.008 |
Neg logit contributions | |
Metatron | -0.843 |
Sac | -0.815 |
Syl | -0.779 |
Es | -0.754 |
Alphabet | -0.715 |
Token |
|
Token ID | 198 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
declass | +0.982 |
lobb | +0.949 |
� | +0.939 |
":[" | +0.894 |
Kubrick | +0.889 |
Neg logit contributions | |
Metatron | -0.942 |
Sac | -0.917 |
Syl | -0.877 |
Es | -0.854 |
Alphabet | -0.815 |
Token |
|
Token ID | 198 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
declass | +1.816 |
lobb | +1.704 |
� | +1.670 |
":[" | +1.669 |
Kubrick | +1.616 |
Neg logit contributions | |
Metatron | -2.477 |
Sac | -2.338 |
Syl | -2.295 |
Es | -2.217 |
inventoryQuantity | -2.143 |
Token | We |
Token ID | 1135 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
declass | +2.572 |
� | +2.515 |
lobb | +2.499 |
":[" | +2.419 |
bryce | +2.390 |
Neg logit contributions | |
Metatron | -2.078 |
Sac | -1.944 |
Syl | -1.922 |
Es | -1.794 |
Alphabet | -1.767 |
Token | do |
Token ID | 466 |
Feature activation | -8.75e+00 |
Pos logit contributions | |
declass | +2.431 |
lobb | +2.335 |
� | +2.320 |
":[" | +2.193 |
FAC | +2.183 |
Neg logit contributions | |
Metatron | -2.601 |
Sac | -2.508 |
Syl | -2.414 |
Es | -2.352 |
Alphabet | -2.243 |
Token | have |
Token ID | 423 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
declass | +5.897 |
lobb | +5.717 |
� | +5.687 |
FAC | +5.412 |
Kubrick | +5.365 |
Neg logit contributions | |
Metatron | -6.565 |
Sac | -6.397 |
Syl | -6.101 |
Es | -5.944 |
inventoryQuantity | -5.771 |
Token | a |
Token ID | 257 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
declass | +1.682 |
lobb | +1.628 |
� | +1.595 |
":[" | +1.521 |
FAC | +1.514 |
Neg logit contributions | |
Metatron | -1.668 |
Sac | -1.624 |
Syl | -1.555 |
Es | -1.517 |
Alphabet | -1.447 |
Token | couple |
Token ID | 3155 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
declass | +1.740 |
lobb | +1.667 |
� | +1.635 |
":[" | +1.556 |
Kubrick | +1.551 |
Neg logit contributions | |
Metatron | -1.965 |
Sac | -1.907 |
Syl | -1.838 |
Es | -1.793 |
Alphabet | -1.723 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
declass | +2.383 |
lobb | +2.308 |
� | +2.264 |
Kubrick | +2.152 |
":[" | +2.150 |
Neg logit contributions | |
Metatron | -2.204 |
Sac | -2.145 |
Syl | -2.045 |
Es | -1.993 |
Alphabet | -1.906 |
Token | though |
Token ID | 996 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
declass | +0.874 |
lobb | +0.842 |
� | +0.827 |
":[" | +0.789 |
bryce | +0.784 |
Neg logit contributions | |
Metatron | -0.855 |
Sac | -0.831 |
Syl | -0.798 |
Es | -0.776 |
Alphabet | -0.743 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
declass | +1.118 |
lobb | +1.042 |
� | +1.023 |
bryce | +1.000 |
":[" | +0.987 |
Neg logit contributions | |
Metatron | -1.816 |
Sac | -1.729 |
Syl | -1.718 |
Es | -1.652 |
Alphabet | -1.629 |
Token | : |
Token ID | 25 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Metatron | +2.176 |
Sac | +2.133 |
Syl | +2.030 |
Es | +1.956 |
Alphabet | +1.861 |
Neg logit contributions | |
declass | -3.037 |
lobb | -2.966 |
� | -2.925 |
bryce | -2.780 |
FAC | -2.755 |
Token | Mike |
Token ID | 4995 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
declass | +1.307 |
lobb | +1.256 |
� | +1.228 |
Kubrick | +1.179 |
":[" | +1.178 |
Neg logit contributions | |
Metatron | -1.186 |
Sac | -1.155 |
Syl | -1.100 |
Es | -1.076 |
Alphabet | -1.025 |
Token | M |
Token ID | 44 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
declass | +2.920 |
lobb | +2.820 |
� | +2.801 |
Kubrick | +2.671 |
bryce | +2.664 |
Neg logit contributions | |
Metatron | -2.636 |
Sac | -2.537 |
Syl | -2.448 |
Es | -2.352 |
Alphabet | -2.282 |
Token | anners |
Token ID | 15672 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
declass | +1.757 |
lobb | +1.693 |
� | +1.666 |
":[" | +1.595 |
bryce | +1.591 |
Neg logit contributions | |
Metatron | -1.526 |
Sac | -1.471 |
Syl | -1.424 |
Es | -1.372 |
Alphabet | -1.308 |
Token | - |
Token ID | 532 |
Feature activation | -8.74e+00 |
Pos logit contributions | |
declass | +2.696 |
lobb | +2.592 |
� | +2.543 |
bryce | +2.444 |
":[" | +2.443 |
Neg logit contributions | |
Metatron | -2.440 |
Sac | -2.347 |
Syl | -2.278 |
Es | -2.183 |
Alphabet | -2.106 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
declass | +4.365 |
lobb | +3.723 |
foreground | +3.474 |
Kubrick | +3.437 |
beaut | +3.386 |
Neg logit contributions | |
Metatron | -8.286 |
Sac | -8.100 |
Syl | -7.758 |
Es | -7.720 |
alia | -7.494 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
declass | +3.191 |
lobb | +2.841 |
Kubrick | +2.656 |
foreground | +2.639 |
":[" | +2.592 |
Neg logit contributions | |
Metatron | -5.438 |
Sac | -5.296 |
Es | -5.086 |
Syl | -5.080 |
alia | -4.881 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
declass | +3.072 |
lobb | +2.743 |
Kubrick | +2.565 |
foreground | +2.545 |
Ghostbusters | +2.504 |
Neg logit contributions | |
Metatron | -5.179 |
Sac | -5.045 |
Syl | -4.838 |
Es | -4.836 |
2020 | -4.640 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
declass | +2.623 |
lobb | +2.384 |
Kubrick | +2.226 |
foreground | +2.191 |
":[" | +2.175 |
Neg logit contributions | |
Metatron | -4.165 |
Sac | -4.057 |
Syl | -3.895 |
Es | -3.868 |
alia | -3.710 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
declass | +2.943 |
lobb | +2.743 |
� | +2.619 |
Kubrick | +2.560 |
":[" | +2.528 |
Neg logit contributions | |
Metatron | -3.939 |
Sac | -3.835 |
Syl | -3.695 |
Es | -3.622 |
Alphabet | -3.467 |
Token | | |
Token ID | 930 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
declass | +0.667 |
lobb | +0.636 |
� | +0.622 |
":[" | +0.598 |
Kubrick | +0.594 |
Neg logit contributions | |
Metatron | -0.643 |
Sac | -0.621 |
Syl | -0.597 |
Es | -0.583 |
Alphabet | -0.552 |
Token | ---- |
Token ID | 13498 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
Metatron | +0.595 |
Sac | +0.578 |
Syl | +0.559 |
Es | +0.541 |
Alphabet | +0.521 |
Neg logit contributions | |
declass | -0.566 |
lobb | -0.544 |
� | -0.535 |
":[" | -0.510 |
bryce | -0.509 |
Token | -+ |
Token ID | 19529 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
Metatron | +0.536 |
Sac | +0.515 |
Syl | +0.494 |
Es | +0.475 |
Alphabet | +0.451 |
Neg logit contributions | |
declass | -0.768 |
lobb | -0.743 |
� | -0.733 |
":[" | -0.705 |
bryce | -0.702 |
Token | -------------------------------- |
Token ID | 3880 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
declass | +0.411 |
lobb | +0.396 |
� | +0.390 |
":[" | +0.373 |
bryce | +0.370 |
Neg logit contributions | |
Metatron | -0.390 |
Sac | -0.378 |
Syl | -0.363 |
Es | -0.352 |
Alphabet | -0.337 |
Token | + |
Token ID | 10 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Metatron | +0.104 |
Sac | +0.101 |
Syl | +0.097 |
Es | +0.094 |
Alphabet | +0.090 |
Neg logit contributions | |
declass | -0.108 |
lobb | -0.104 |
� | -0.102 |
":[" | -0.098 |
bryce | -0.097 |
Token | ------- |
Token ID | 26866 |
Feature activation | -8.73e+00 |
Pos logit contributions | |
declass | +1.142 |
lobb | +1.095 |
� | +1.085 |
":[" | +1.032 |
bryce | +1.021 |
Neg logit contributions | |
Metatron | -1.229 |
Sac | -1.195 |
Syl | -1.144 |
Es | -1.115 |
Alphabet | -1.070 |
Token | | |
Token ID | 91 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
declass | +5.171 |
� | +4.971 |
lobb | +4.895 |
":[" | +4.714 |
bryce | +4.623 |
Neg logit contributions | |
Metatron | -7.118 |
Sac | -6.892 |
Syl | -6.482 |
Es | -6.348 |
Alphabet | -6.139 |
Token | | |
Token ID | 930 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
declass | +3.160 |
lobb | +3.019 |
� | +2.967 |
":[" | +2.837 |
FAC | +2.810 |
Neg logit contributions | |
Metatron | -3.398 |
Sac | -3.324 |
Syl | -3.129 |
Es | -3.109 |
2020 | -2.952 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
declass | +0.282 |
lobb | +0.272 |
� | +0.267 |
":[" | +0.257 |
bryce | +0.255 |
Neg logit contributions | |
Metatron | -0.238 |
Sac | -0.230 |
Syl | -0.221 |
Es | -0.214 |
Alphabet | -0.204 |
Token | | |
Token ID | 930 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Metatron | +0.857 |
Sac | +0.828 |
Syl | +0.798 |
Es | +0.769 |
Alphabet | +0.736 |
Neg logit contributions | |
declass | -1.028 |
lobb | -0.993 |
� | -0.978 |
":[" | -0.936 |
bryce | -0.935 |
Token | org |
Token ID | 8745 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
declass | +1.667 |
lobb | +1.603 |
� | +1.566 |
":[" | +1.511 |
Kubrick | +1.495 |
Neg logit contributions | |
Metatron | -1.546 |
Sac | -1.499 |
Syl | -1.430 |
Es | -1.401 |
Alphabet | -1.328 |
Token | honour |
Token ID | 15393 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
declass | +0.292 |
lobb | +0.279 |
� | +0.274 |
":[" | +0.260 |
bryce | +0.259 |
Neg logit contributions | |
Metatron | -0.341 |
Sac | -0.331 |
Syl | -0.321 |
Es | -0.312 |
Alphabet | -0.300 |
Token | to |
Token ID | 284 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
declass | +2.242 |
lobb | +2.135 |
� | +2.108 |
":[" | +2.013 |
Kubrick | +1.999 |
Neg logit contributions | |
Metatron | -2.151 |
Sac | -2.089 |
Syl | -2.026 |
Es | -1.960 |
Alphabet | -1.905 |
Token | be |
Token ID | 307 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
declass | +1.172 |
lobb | +1.101 |
� | +1.060 |
":[" | +1.032 |
FAC | +1.022 |
Neg logit contributions | |
Metatron | -1.194 |
Sac | -1.153 |
Syl | -1.120 |
Es | -1.091 |
Alphabet | -1.047 |
Token | , |
Token ID | 11 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
declass | +2.467 |
lobb | +2.350 |
� | +2.279 |
Kubrick | +2.192 |
FAC | +2.187 |
Neg logit contributions | |
Metatron | -2.478 |
Sac | -2.439 |
Syl | -2.349 |
Es | -2.280 |
Alphabet | -2.185 |
Token | Mad |
Token ID | 4627 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
declass | +0.533 |
lobb | +0.513 |
� | +0.504 |
":[" | +0.482 |
bryce | +0.480 |
Neg logit contributions | |
Metatron | -0.521 |
Sac | -0.505 |
Syl | -0.487 |
Es | -0.472 |
Alphabet | -0.452 |
Token | am |
Token ID | 321 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
Metatron | +0.713 |
Sac | +0.690 |
Syl | +0.667 |
Es | +0.646 |
Alphabet | +0.620 |
Neg logit contributions | |
declass | -0.743 |
lobb | -0.716 |
� | -0.706 |
":[" | -0.673 |
bryce | -0.671 |
Token | , |
Token ID | 11 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
Metatron | +4.876 |
Sac | +4.591 |
Syl | +4.536 |
Es | +4.300 |
Alphabet | +4.256 |
Neg logit contributions | |
declass | -4.560 |
lobb | -4.475 |
� | -4.457 |
":[" | -4.239 |
bryce | -4.236 |
Token | Your |
Token ID | 3406 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
Metatron | +0.687 |
Sac | +0.660 |
Syl | +0.637 |
Es | +0.620 |
Alphabet | +0.595 |
Neg logit contributions | |
declass | -0.691 |
lobb | -0.667 |
� | -0.660 |
":[" | -0.629 |
bryce | -0.628 |
Token | Majesty |
Token ID | 25788 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
declass | +0.487 |
lobb | +0.467 |
� | +0.457 |
":[" | +0.438 |
Kubrick | +0.434 |
Neg logit contributions | |
Metatron | -0.486 |
Sac | -0.470 |
Syl | -0.455 |
Es | -0.440 |
Alphabet | -0.423 |
Token | 's |
Token ID | 338 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Metatron | +3.913 |
Sac | +3.749 |
Syl | +3.581 |
Es | +3.534 |
alia | +3.321 |
Neg logit contributions | |
declass | -4.356 |
lobb | -4.310 |
� | -4.229 |
bryce | -4.044 |
":[" | -4.033 |
Token | humble |
Token ID | 19695 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
Metatron | +2.102 |
Sac | +2.036 |
Syl | +1.969 |
Es | +1.906 |
Alphabet | +1.851 |
Neg logit contributions | |
declass | -1.962 |
lobb | -1.898 |
� | -1.884 |
":[" | -1.791 |
bryce | -1.780 |
Token | Score |
Token ID | 26595 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
Metatron | +2.172 |
Sac | +2.107 |
Syl | +2.034 |
Es | +1.965 |
Alphabet | +1.863 |
Neg logit contributions | |
declass | -2.653 |
lobb | -2.549 |
� | -2.528 |
bryce | -2.435 |
":[" | -2.423 |
Token | esports |
Token ID | 37407 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
Metatron | +3.000 |
Sac | +2.930 |
Es | +2.802 |
Syl | +2.709 |
2020 | +2.464 |
Neg logit contributions | |
declass | -6.920 |
lobb | -6.638 |
�� | -6.548 |
� | -6.543 |
":[" | -6.404 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Metatron | +2.441 |
Sac | +2.368 |
Syl | +2.285 |
Es | +2.215 |
Alphabet | +2.115 |
Neg logit contributions | |
declass | -2.834 |
lobb | -2.687 |
� | -2.656 |
bryce | -2.579 |
Kubrick | -2.548 |
Token | You |
Token ID | 921 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Metatron | +1.640 |
Sac | +1.575 |
Syl | +1.504 |
Es | +1.443 |
Alphabet | +1.367 |
Neg logit contributions | |
declass | -2.560 |
lobb | -2.480 |
� | -2.447 |
":[" | -2.358 |
bryce | -2.349 |
Token | can |
Token ID | 460 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
Metatron | +1.787 |
Sac | +1.742 |
Syl | +1.695 |
Es | +1.645 |
Alphabet | +1.584 |
Neg logit contributions | |
declass | -1.418 |
lobb | -1.343 |
� | -1.312 |
bryce | -1.256 |
":[" | -1.247 |
Token | follow |
Token ID | 1061 |
Feature activation | +6.36e+00 |
Pos logit contributions | |
Metatron | +2.264 |
Sac | +2.185 |
Syl | +2.092 |
Es | +2.014 |
Alphabet | +1.908 |
Neg logit contributions | |
declass | -3.424 |
lobb | -3.322 |
� | -3.290 |
bryce | -3.175 |
":[" | -3.152 |
Token | him |
Token ID | 683 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
Metatron | +2.296 |
Sac | +2.136 |
Syl | +2.050 |
Es | +1.910 |
Alphabet | +1.683 |
Neg logit contributions | |
declass | -7.013 |
lobb | -6.810 |
� | -6.755 |
bryce | -6.537 |
":[" | -6.510 |
Token | on |
Token ID | 319 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
Metatron | +2.140 |
Sac | +2.084 |
Syl | +2.004 |
Es | +1.953 |
Alphabet | +1.855 |
Neg logit contributions | |
declass | -2.493 |
lobb | -2.388 |
� | -2.352 |
":[" | -2.256 |
bryce | -2.254 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Metatron | +1.421 |
Sac | +1.371 |
Syl | +1.309 |
Es | +1.265 |
Alphabet | +1.193 |
Neg logit contributions | |
declass | -2.244 |
lobb | -2.170 |
� | -2.137 |
bryce | -2.066 |
":[" | -2.054 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Metatron | +1.471 |
Sac | +1.424 |
Syl | +1.371 |
Es | +1.331 |
Alphabet | +1.274 |
Neg logit contributions | |
declass | -1.552 |
lobb | -1.492 |
� | -1.466 |
bryce | -1.400 |
":[" | -1.396 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Metatron | +1.367 |
Sac | +1.325 |
Syl | +1.274 |
Es | +1.233 |
Alphabet | +1.177 |
Neg logit contributions | |
declass | -1.587 |
lobb | -1.528 |
� | -1.501 |
":[" | -1.438 |
bryce | -1.436 |
Token |
|
Token ID | 198 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
declass | +0.447 |
lobb | +0.430 |
� | +0.423 |
":[" | +0.404 |
bryce | +0.401 |
Neg logit contributions | |
Metatron | -0.445 |
Sac | -0.431 |
Syl | -0.415 |
Es | -0.403 |
Alphabet | -0.386 |
Token |
|
Token ID | 198 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
Metatron | +2.529 |
Sac | +2.486 |
Syl | +2.383 |
Es | +2.317 |
Alphabet | +2.221 |
Neg logit contributions | |
declass | -2.682 |
lobb | -2.603 |
� | -2.555 |
bryce | -2.434 |
":[" | -2.400 |
Token | First |
Token ID | 5962 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Metatron | +1.922 |
Sac | +1.919 |
Syl | +1.780 |
Es | +1.770 |
Alphabet | +1.635 |
Neg logit contributions | |
declass | -2.871 |
lobb | -2.795 |
� | -2.716 |
Kubrick | -2.627 |
bryce | -2.617 |
Token | , |
Token ID | 11 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
Metatron | +1.446 |
Sac | +1.393 |
Syl | +1.345 |
Es | +1.296 |
Alphabet | +1.241 |
Neg logit contributions | |
declass | -1.733 |
lobb | -1.676 |
� | -1.648 |
bryce | -1.587 |
":[" | -1.583 |
Token | D |
Token ID | 360 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Metatron | +0.361 |
Sac | +0.349 |
Syl | +0.335 |
Es | +0.324 |
Alphabet | +0.309 |
Neg logit contributions | |
declass | -0.432 |
lobb | -0.417 |
� | -0.410 |
":[" | -0.393 |
Kubrick | -0.390 |
Token | DoS |
Token ID | 46498 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
Metatron | +1.272 |
Sac | +1.218 |
Syl | +1.158 |
Es | +1.109 |
Alphabet | +1.042 |
Neg logit contributions | |
declass | -2.274 |
lobb | -2.207 |
� | -2.178 |
":[" | -2.103 |
bryce | -2.096 |
Token | attacks |
Token ID | 3434 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Metatron | +3.981 |
Sac | +3.958 |
Syl | +3.783 |
Es | +3.747 |
Alphabet | +3.518 |
Neg logit contributions | |
declass | -4.912 |
� | -4.715 |
lobb | -4.689 |
bryce | -4.588 |
Kubrick | -4.580 |
Token | strike |
Token ID | 5587 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
Metatron | +2.474 |
Sac | +2.423 |
Syl | +2.332 |
Es | +2.242 |
Alphabet | +2.172 |
Neg logit contributions | |
declass | -2.545 |
lobb | -2.467 |
� | -2.442 |
bryce | -2.360 |
Kubrick | -2.318 |
Token | networks |
Token ID | 7686 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Metatron | +0.047 |
Sac | +0.046 |
Syl | +0.044 |
Es | +0.043 |
Alphabet | +0.041 |
Neg logit contributions | |
declass | -0.046 |
lobb | -0.044 |
� | -0.043 |
":[" | -0.041 |
bryce | -0.041 |
Token | on |
Token ID | 319 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
Metatron | +2.026 |
Sac | +1.948 |
Syl | +1.895 |
Es | +1.833 |
Alphabet | +1.755 |
Neg logit contributions | |
declass | -2.245 |
lobb | -2.160 |
� | -2.130 |
bryce | -2.053 |
":[" | -2.041 |
Token | three |
Token ID | 1115 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Metatron | +0.734 |
Sac | +0.710 |
Syl | +0.690 |
Es | +0.666 |
Alphabet | +0.643 |
Neg logit contributions | |
declass | -0.719 |
lobb | -0.691 |
� | -0.683 |
bryce | -0.653 |
":[" | -0.652 |
Token | Grant |
Token ID | 12181 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
Metatron | +1.715 |
Sac | +1.610 |
Syl | +1.526 |
Es | +1.424 |
Alphabet | +1.345 |
Neg logit contributions | |
declass | -4.550 |
lobb | -4.415 |
� | -4.394 |
bryce | -4.285 |
":[" | -4.242 |
Token | makers |
Token ID | 6620 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
declass | +2.123 |
lobb | +2.114 |
� | +1.785 |
bryce | +1.764 |
":[" | +1.690 |
Neg logit contributions | |
Metatron | -7.398 |
Sac | -7.196 |
Syl | -7.143 |
Es | -6.851 |
Alphabet | -6.749 |
Token | Association |
Token ID | 5396 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Metatron | +0.046 |
Sac | +0.044 |
Syl | +0.041 |
Es | +0.039 |
Alphabet | +0.036 |
Neg logit contributions | |
declass | -0.108 |
lobb | -0.105 |
� | -0.104 |
":[" | -0.101 |
bryce | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
declass | +1.312 |
lobb | +1.267 |
� | +1.239 |
":[" | +1.197 |
Kubrick | +1.181 |
Neg logit contributions | |
Metatron | -1.151 |
Sac | -1.113 |
Syl | -1.071 |
Es | -1.036 |
Alphabet | -0.989 |
Token | Rockefeller |
Token ID | 32764 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
declass | +1.157 |
lobb | +1.112 |
� | +1.085 |
":[" | +1.037 |
Kubrick | +1.032 |
Neg logit contributions | |
Metatron | -1.338 |
Sac | -1.300 |
Syl | -1.257 |
Es | -1.226 |
Alphabet | -1.172 |
Token | Family |
Token ID | 7884 |
Feature activation | +8.19e+00 |
Pos logit contributions | |
Metatron | +0.514 |
Sac | +0.503 |
Syl | +0.489 |
Es | +0.480 |
Alphabet | +0.461 |
Neg logit contributions | |
declass | -0.269 |
lobb | -0.254 |
� | -0.245 |
":[" | -0.232 |
Kubrick | -0.230 |
Token | Fund |
Token ID | 7557 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
Metatron | +3.876 |
Sac | +3.702 |
Syl | +3.545 |
Es | +3.288 |
Alphabet | +3.258 |
Neg logit contributions | |
declass | -7.989 |
� | -7.852 |
lobb | -7.826 |
bryce | -7.588 |
�� | -7.570 |
Token | , |
Token ID | 11 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
Metatron | +2.220 |
Sac | +2.146 |
Syl | +2.050 |
Es | +1.973 |
Alphabet | +1.887 |
Neg logit contributions | |
declass | -3.060 |
lobb | -2.967 |
� | -2.956 |
bryce | -2.826 |
Kubrick | -2.789 |
Token | Inc |
Token ID | 3457 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
Metatron | +1.626 |
Sac | +1.564 |
Syl | +1.480 |
Es | +1.377 |
Alphabet | +1.303 |
Neg logit contributions | |
declass | -3.694 |
lobb | -3.616 |
� | -3.600 |
bryce | -3.451 |
":[" | -3.441 |
Token | .: |
Token ID | 11207 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
Metatron | +0.532 |
Sac | +0.521 |
Syl | +0.507 |
Es | +0.496 |
Alphabet | +0.479 |
Neg logit contributions | |
declass | -0.290 |
lobb | -0.275 |
� | -0.268 |
bryce | -0.249 |
Kubrick | -0.248 |
Token | New |
Token ID | 968 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
Metatron | +0.414 |
Sac | +0.401 |
Syl | +0.386 |
Es | +0.374 |
Alphabet | +0.357 |
Neg logit contributions | |
declass | -0.454 |
lobb | -0.437 |
� | -0.429 |
":[" | -0.412 |
bryce | -0.409 |
Token | physics |
Token ID | 11887 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
Metatron | +0.454 |
Sac | +0.440 |
Syl | +0.427 |
Es | +0.413 |
Alphabet | +0.398 |
Neg logit contributions | |
declass | -0.412 |
lobb | -0.396 |
� | -0.391 |
":[" | -0.372 |
bryce | -0.372 |
Token | and |
Token ID | 290 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Metatron | +0.040 |
Sac | +0.039 |
Syl | +0.037 |
Es | +0.036 |
Alphabet | +0.035 |
Neg logit contributions | |
declass | -0.041 |
lobb | -0.039 |
� | -0.038 |
":[" | -0.037 |
bryce | -0.037 |
Token | has |
Token ID | 468 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
declass | +1.279 |
lobb | +1.230 |
� | +1.192 |
Kubrick | +1.145 |
":[" | +1.140 |
Neg logit contributions | |
Metatron | -1.385 |
Sac | -1.354 |
Syl | -1.299 |
Es | -1.264 |
Alphabet | -1.205 |
Token | made |
Token ID | 925 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
declass | +0.532 |
lobb | +0.511 |
� | +0.501 |
":[" | +0.480 |
Kubrick | +0.478 |
Neg logit contributions | |
Metatron | -0.499 |
Sac | -0.486 |
Syl | -0.466 |
Es | -0.453 |
Alphabet | -0.432 |
Token | its |
Token ID | 663 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
declass | +0.311 |
lobb | +0.298 |
� | +0.292 |
":[" | +0.279 |
bryce | +0.278 |
Neg logit contributions | |
Metatron | -0.328 |
Sac | -0.319 |
Syl | -0.307 |
Es | -0.298 |
Alphabet | -0.286 |
Token | way |
Token ID | 835 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
Metatron | +3.664 |
Sac | +3.546 |
Syl | +3.454 |
Es | +3.374 |
Alphabet | +3.281 |
Neg logit contributions | |
declass | -2.732 |
� | -2.650 |
lobb | -2.632 |
":[" | -2.517 |
bryce | -2.506 |
Token | into |
Token ID | 656 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Metatron | +3.258 |
Sac | +3.070 |
Syl | +3.024 |
Es | +2.892 |
Alphabet | +2.800 |
Neg logit contributions | |
declass | -4.646 |
lobb | -4.540 |
� | -4.468 |
bryce | -4.409 |
":[" | -4.361 |
Token | astronomy |
Token ID | 37145 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Metatron | +2.013 |
Sac | +1.940 |
Syl | +1.898 |
Es | +1.840 |
Alphabet | +1.797 |
Neg logit contributions | |
declass | -1.691 |
� | -1.634 |
lobb | -1.622 |
bryce | -1.552 |
":[" | -1.543 |
Token | , |
Token ID | 11 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Metatron | +0.781 |
Sac | +0.753 |
Syl | +0.726 |
Es | +0.704 |
Alphabet | +0.674 |
Neg logit contributions | |
declass | -0.859 |
lobb | -0.827 |
� | -0.815 |
":[" | -0.780 |
bryce | -0.779 |
Token | � |
Token ID | 447 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
declass | +1.017 |
lobb | +0.983 |
� | +0.964 |
":[" | +0.923 |
Kubrick | +0.913 |
Neg logit contributions | |
Metatron | -0.994 |
Sac | -0.969 |
Syl | -0.928 |
Es | -0.904 |
Alphabet | -0.867 |
Token | � |
Token ID | 251 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Metatron | +0.408 |
Sac | +0.396 |
Syl | +0.383 |
Es | +0.373 |
Alphabet | +0.359 |
Neg logit contributions | |
declass | -0.345 |
lobb | -0.331 |
� | -0.325 |
":[" | -0.310 |
bryce | -0.308 |
Token | ? |
Token ID | 30 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
declass | +1.082 |
lobb | +1.040 |
� | +1.028 |
":[" | +0.980 |
Kubrick | +0.979 |
Neg logit contributions | |
Metatron | -0.951 |
Sac | -0.928 |
Syl | -0.883 |
Es | -0.860 |
Alphabet | -0.821 |
Token | Due |
Token ID | 14444 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
Metatron | +1.251 |
Sac | +1.207 |
Syl | +1.166 |
Es | +1.124 |
Alphabet | +1.076 |
Neg logit contributions | |
declass | -1.456 |
lobb | -1.405 |
� | -1.374 |
bryce | -1.324 |
":[" | -1.321 |
Token | to |
Token ID | 284 |
Feature activation | +6.75e-03 |
Pos logit contributions | |
declass | +0.013 |
lobb | +0.013 |
� | +0.013 |
":[" | +0.012 |
bryce | +0.012 |
Neg logit contributions | |
Metatron | -0.012 |
Sac | -0.011 |
Syl | -0.011 |
Es | -0.010 |
Alphabet | -0.010 |
Token | all |
Token ID | 477 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Metatron | +0.005 |
Sac | +0.005 |
Syl | +0.005 |
Es | +0.005 |
Alphabet | +0.004 |
Neg logit contributions | |
declass | -0.005 |
lobb | -0.005 |
� | -0.005 |
":[" | -0.004 |
bryce | -0.004 |
Token | these |
Token ID | 777 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
declass | +0.082 |
lobb | +0.079 |
� | +0.077 |
":[" | +0.074 |
bryce | +0.074 |
Neg logit contributions | |
Metatron | -0.084 |
Sac | -0.082 |
Syl | -0.079 |
Es | -0.076 |
Alphabet | -0.073 |
Token | delays |
Token ID | 16119 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Metatron | +0.297 |
Sac | +0.288 |
Syl | +0.278 |
Es | +0.270 |
Alphabet | +0.259 |
Neg logit contributions | |
declass | -0.289 |
lobb | -0.278 |
� | -0.272 |
":[" | -0.260 |
bryce | -0.258 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Metatron | +1.451 |
Sac | +1.400 |
Syl | +1.352 |
Es | +1.304 |
Alphabet | +1.247 |
Neg logit contributions | |
declass | -1.698 |
lobb | -1.637 |
� | -1.608 |
":[" | -1.545 |
bryce | -1.543 |
Token | we |
Token ID | 356 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Metatron | +0.795 |
Sac | +0.767 |
Syl | +0.739 |
Es | +0.713 |
Alphabet | +0.682 |
Neg logit contributions | |
declass | -0.950 |
lobb | -0.916 |
� | -0.902 |
":[" | -0.866 |
bryce | -0.863 |
Token | have |
Token ID | 423 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
Metatron | +0.161 |
Sac | +0.156 |
Syl | +0.150 |
Es | +0.146 |
Alphabet | +0.140 |
Neg logit contributions | |
declass | -0.156 |
lobb | -0.150 |
� | -0.147 |
":[" | -0.141 |
bryce | -0.139 |
Token | lost |
Token ID | 2626 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Metatron | +0.624 |
Sac | +0.605 |
Syl | +0.584 |
Es | +0.565 |
Alphabet | +0.543 |
Neg logit contributions | |
declass | -0.635 |
lobb | -0.611 |
� | -0.601 |
":[" | -0.574 |
bryce | -0.572 |
Token | all |
Token ID | 477 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
declass | +0.928 |
lobb | +0.894 |
� | +0.879 |
":[" | +0.837 |
Kubrick | +0.833 |
Neg logit contributions | |
Metatron | -0.927 |
Sac | -0.909 |
Syl | -0.867 |
Es | -0.849 |
Alphabet | -0.808 |
Token | idea |
Token ID | 2126 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Metatron | +0.556 |
Sac | +0.539 |
Syl | +0.522 |
Es | +0.507 |
Alphabet | +0.488 |
Neg logit contributions | |
declass | -0.479 |
lobb | -0.458 |
� | -0.451 |
":[" | -0.429 |
bryce | -0.428 |
Token | is |
Token ID | 318 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Metatron | +0.235 |
Sac | +0.227 |
Syl | +0.219 |
Es | +0.211 |
Alphabet | +0.202 |
Neg logit contributions | |
declass | -0.267 |
lobb | -0.258 |
� | -0.253 |
":[" | -0.243 |
bryce | -0.241 |
Token | challenge |
Token ID | 4427 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Metatron | +0.123 |
Sac | +0.119 |
Syl | +0.114 |
Es | +0.111 |
Alphabet | +0.106 |
Neg logit contributions | |
declass | -0.131 |
lobb | -0.126 |
� | -0.124 |
":[" | -0.119 |
bryce | -0.118 |
Token | by |
Token ID | 416 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Metatron | +1.776 |
Sac | +1.705 |
Syl | +1.638 |
Es | +1.584 |
Alphabet | +1.516 |
Neg logit contributions | |
declass | -2.179 |
� | -2.093 |
lobb | -2.086 |
bryce | -2.011 |
":[" | -1.993 |
Token | choice |
Token ID | 3572 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Metatron | +0.249 |
Sac | +0.242 |
Syl | +0.235 |
Es | +0.229 |
Alphabet | +0.222 |
Neg logit contributions | |
declass | -0.168 |
lobb | -0.160 |
� | -0.158 |
":[" | -0.148 |
bryce | -0.148 |
Token | ," |
Token ID | 553 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Metatron | +0.993 |
Sac | +0.959 |
Syl | +0.924 |
Es | +0.894 |
Alphabet | +0.855 |
Neg logit contributions | |
declass | -1.134 |
lobb | -1.091 |
� | -1.080 |
bryce | -1.031 |
":[" | -1.030 |
Token | said |
Token ID | 531 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Metatron | +0.813 |
Sac | +0.780 |
Syl | +0.758 |
Es | +0.723 |
Alphabet | +0.696 |
Neg logit contributions | |
declass | -0.994 |
lobb | -0.958 |
� | -0.950 |
bryce | -0.914 |
":[" | -0.913 |
Token | Carter |
Token ID | 10831 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Metatron | +0.849 |
Sac | +0.816 |
Syl | +0.797 |
Es | +0.766 |
Alphabet | +0.738 |
Neg logit contributions | |
declass | -0.832 |
lobb | -0.799 |
� | -0.792 |
":[" | -0.756 |
bryce | -0.754 |
Token | . |
Token ID | 13 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Metatron | +0.786 |
Sac | +0.757 |
Syl | +0.735 |
Es | +0.708 |
Alphabet | +0.677 |
Neg logit contributions | |
declass | -0.912 |
lobb | -0.880 |
� | -0.866 |
":[" | -0.835 |
bryce | -0.831 |
Token | " |
Token ID | 366 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
Metatron | +0.291 |
Sac | +0.281 |
Syl | +0.272 |
Es | +0.262 |
Alphabet | +0.252 |
Neg logit contributions | |
declass | -0.317 |
lobb | -0.304 |
� | -0.299 |
bryce | -0.286 |
":[" | -0.285 |
Token | So |
Token ID | 2396 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
declass | +0.083 |
lobb | +0.080 |
� | +0.079 |
":[" | +0.077 |
bryce | +0.076 |
Neg logit contributions | |
Metatron | -0.051 |
Sac | -0.048 |
Syl | -0.046 |
Es | -0.044 |
Alphabet | -0.042 |
Token | on |
Token ID | 319 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Metatron | +0.582 |
Sac | +0.563 |
Syl | +0.542 |
Es | +0.524 |
Alphabet | +0.501 |
Neg logit contributions | |
declass | -0.667 |
lobb | -0.643 |
� | -0.633 |
":[" | -0.606 |
bryce | -0.604 |
Token | different |
Token ID | 1180 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
declass | +1.580 |
lobb | +1.521 |
� | +1.473 |
":[" | +1.406 |
Kubrick | +1.400 |
Neg logit contributions | |
Metatron | -1.703 |
Sac | -1.666 |
Syl | -1.586 |
Es | -1.556 |
Alphabet | -1.480 |
Token | software |
Token ID | 3788 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Metatron | +1.250 |
Sac | +1.207 |
Syl | +1.166 |
Es | +1.126 |
Alphabet | +1.079 |
Neg logit contributions | |
declass | -1.406 |
lobb | -1.352 |
� | -1.340 |
":[" | -1.281 |
bryce | -1.281 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Metatron | +1.267 |
Sac | +1.225 |
Syl | +1.186 |
Es | +1.151 |
Alphabet | +1.099 |
Neg logit contributions | |
declass | -1.363 |
lobb | -1.306 |
� | -1.300 |
bryce | -1.242 |
":[" | -1.241 |
Token | Store |
Token ID | 9363 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Metatron | +1.712 |
Sac | +1.652 |
Syl | +1.597 |
Es | +1.537 |
Alphabet | +1.480 |
Neg logit contributions | |
declass | -2.027 |
lobb | -1.959 |
� | -1.925 |
bryce | -1.851 |
":[" | -1.849 |
Token | stuff |
Token ID | 3404 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
declass | +0.155 |
lobb | +0.150 |
� | +0.147 |
":[" | +0.140 |
bryce | +0.139 |
Neg logit contributions | |
Metatron | -0.147 |
Sac | -0.143 |
Syl | -0.137 |
Es | -0.133 |
Alphabet | -0.127 |
Token | on |
Token ID | 319 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Metatron | +0.399 |
Sac | +0.387 |
Syl | +0.373 |
Es | +0.361 |
Alphabet | +0.346 |
Neg logit contributions | |
declass | -0.418 |
lobb | -0.402 |
� | -0.395 |
":[" | -0.378 |
bryce | -0.375 |
Token | different |
Token ID | 1180 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
declass | +0.751 |
lobb | +0.717 |
� | +0.694 |
":[" | +0.657 |
Kubrick | +0.656 |
Neg logit contributions | |
Metatron | -0.967 |
Sac | -0.947 |
Syl | -0.908 |
Es | -0.891 |
Alphabet | -0.851 |
Token | vendor |
Token ID | 18371 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
Metatron | +1.180 |
Sac | +1.142 |
Syl | +1.102 |
Es | +1.067 |
Alphabet | +1.024 |
Neg logit contributions | |
declass | -1.231 |
lobb | -1.184 |
� | -1.168 |
":[" | -1.116 |
bryce | -1.112 |
Token | gear |
Token ID | 7733 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
Metatron | +2.017 |
Sac | +1.953 |
Syl | +1.885 |
Es | +1.832 |
Alphabet | +1.749 |
Neg logit contributions | |
declass | -2.182 |
lobb | -2.084 |
� | -2.080 |
":[" | -1.997 |
bryce | -1.991 |
Token | to |
Token ID | 284 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
Metatron | +4.322 |
Sac | +4.149 |
Syl | +4.020 |
Es | +3.906 |
Alphabet | +3.703 |
Neg logit contributions | |
declass | -4.920 |
lobb | -4.691 |
� | -4.680 |
bryce | -4.581 |
":[" | -4.519 |
Token | India |
Token ID | 3794 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Metatron | +0.622 |
Sac | +0.602 |
Syl | +0.581 |
Es | +0.563 |
Alphabet | +0.540 |
Neg logit contributions | |
declass | -0.655 |
lobb | -0.629 |
� | -0.620 |
":[" | -0.593 |
bryce | -0.592 |
Token | follows |
Token ID | 5679 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Metatron | +0.229 |
Sac | +0.221 |
Syl | +0.213 |
Es | +0.207 |
Alphabet | +0.198 |
Neg logit contributions | |
declass | -0.247 |
lobb | -0.238 |
� | -0.234 |
":[" | -0.224 |
bryce | -0.223 |
Token | a |
Token ID | 257 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Metatron | +1.133 |
Sac | +1.091 |
Syl | +1.060 |
Es | +1.024 |
Alphabet | +0.993 |
Neg logit contributions | |
declass | -1.143 |
lobb | -1.099 |
� | -1.093 |
":[" | -1.041 |
bryce | -1.040 |
Token | protracted |
Token ID | 44466 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Metatron | +1.671 |
Sac | +1.615 |
Syl | +1.571 |
Es | +1.518 |
Alphabet | +1.480 |
Neg logit contributions | |
declass | -1.438 |
� | -1.397 |
lobb | -1.397 |
":[" | -1.325 |
bryce | -1.320 |
Token | legal |
Token ID | 2742 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Metatron | +1.160 |
Sac | +1.123 |
Syl | +1.091 |
Es | +1.055 |
Alphabet | +1.024 |
Neg logit contributions | |
declass | -1.015 |
lobb | -0.974 |
� | -0.969 |
":[" | -0.921 |
bryce | -0.917 |
Token | dispute |
Token ID | 11047 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Metatron | +2.174 |
Sac | +2.121 |
Syl | +2.065 |
Es | +1.991 |
Alphabet | +1.954 |
Neg logit contributions | |
declass | -1.672 |
� | -1.609 |
lobb | -1.603 |
":[" | -1.516 |
bryce | -1.513 |
Token | with |
Token ID | 351 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Metatron | +0.778 |
Sac | +0.752 |
Syl | +0.729 |
Es | +0.701 |
Alphabet | +0.676 |
Neg logit contributions | |
declass | -0.843 |
lobb | -0.813 |
� | -0.804 |
":[" | -0.769 |
bryce | -0.768 |
Token | CPR |
Token ID | 42920 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Metatron | +1.283 |
Sac | +1.237 |
Syl | +1.207 |
Es | +1.163 |
Alphabet | +1.135 |
Neg logit contributions | |
declass | -1.181 |
� | -1.124 |
lobb | -1.122 |
bryce | -1.072 |
":[" | -1.066 |
Token | L |
Token ID | 43 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Metatron | +2.642 |
Sac | +2.599 |
Syl | +2.466 |
Es | +2.428 |
Alphabet | +2.294 |
Neg logit contributions | |
declass | -3.189 |
lobb | -3.067 |
� | -3.064 |
bryce | -2.910 |
":[" | -2.894 |
Token | that |
Token ID | 326 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
Metatron | +1.417 |
Sac | +1.375 |
Syl | +1.328 |
Es | +1.287 |
Alphabet | +1.238 |
Neg logit contributions | |
declass | -1.449 |
lobb | -1.390 |
� | -1.381 |
bryce | -1.318 |
":[" | -1.317 |
Token | started |
Token ID | 2067 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
declass | +0.375 |
lobb | +0.362 |
� | +0.353 |
Kubrick | +0.337 |
":[" | +0.336 |
Neg logit contributions | |
Metatron | -0.379 |
Sac | -0.369 |
Syl | -0.354 |
Es | -0.345 |
Alphabet | -0.328 |
Token | WC |
Token ID | 27353 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
declass | +1.346 |
lobb | +1.301 |
� | +1.265 |
":[" | +1.236 |
bryce | +1.232 |
Neg logit contributions | |
Metatron | -1.338 |
Sac | -1.264 |
Syl | -1.256 |
Es | -1.183 |
Alphabet | -1.159 |
Token | with |
Token ID | 351 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
Metatron | +1.308 |
Sac | +1.270 |
Syl | +1.223 |
Es | +1.185 |
Alphabet | +1.139 |
Neg logit contributions | |
declass | -1.341 |
lobb | -1.287 |
� | -1.274 |
":[" | -1.217 |
bryce | -1.210 |
Token | four |
Token ID | 1440 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
declass | +0.642 |
lobb | +0.617 |
� | +0.605 |
":[" | +0.576 |
bryce | +0.574 |
Neg logit contributions | |
Metatron | -0.708 |
Sac | -0.687 |
Syl | -0.664 |
Es | -0.646 |
Alphabet | -0.620 |
Token | football |
Token ID | 4346 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
declass | +0.545 |
lobb | +0.522 |
� | +0.509 |
":[" | +0.482 |
bryce | +0.480 |
Neg logit contributions | |
Metatron | -0.715 |
Sac | -0.695 |
Syl | -0.674 |
Es | -0.656 |
Alphabet | -0.632 |
Token | power |
Token ID | 1176 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
declass | +1.782 |
lobb | +1.733 |
� | +1.652 |
":[" | +1.567 |
bryce | +1.563 |
Neg logit contributions | |
Metatron | -2.469 |
Sac | -2.400 |
Syl | -2.337 |
Es | -2.246 |
Alphabet | -2.195 |
Token | houses |
Token ID | 20089 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Metatron | +1.894 |
Sac | +1.838 |
Syl | +1.752 |
Es | +1.717 |
Alphabet | +1.623 |
Neg logit contributions | |
declass | -2.193 |
lobb | -2.091 |
� | -2.090 |
bryce | -2.005 |
":[" | -1.999 |
Token | ( |
Token ID | 357 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
Metatron | +0.858 |
Sac | +0.831 |
Syl | +0.800 |
Es | +0.775 |
Alphabet | +0.742 |
Neg logit contributions | |
declass | -0.929 |
lobb | -0.896 |
� | -0.880 |
":[" | -0.842 |
bryce | -0.839 |
Token | all |
Token ID | 439 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Sac | +2.472 |
Metatron | +2.425 |
Es | +2.288 |
Syl | +2.257 |
2020 | +2.145 |
Neg logit contributions | |
declass | -2.738 |
lobb | -2.629 |
� | -2.576 |
Kubrick | -2.475 |
":[" | -2.443 |
Token | of |
Token ID | 286 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
Metatron | +1.157 |
Sac | +1.123 |
Syl | +1.082 |
Es | +1.047 |
Alphabet | +1.008 |
Neg logit contributions | |
declass | -1.179 |
lobb | -1.134 |
� | -1.119 |
":[" | -1.070 |
bryce | -1.065 |
Token | whom |
Token ID | 4150 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
declass | +0.067 |
lobb | +0.065 |
� | +0.064 |
":[" | +0.062 |
bryce | +0.061 |
Neg logit contributions | |
Metatron | -0.056 |
Sac | -0.054 |
Syl | -0.052 |
Es | -0.050 |
Alphabet | -0.048 |
Token | have |
Token ID | 423 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Metatron | +1.781 |
Sac | +1.728 |
Syl | +1.667 |
Es | +1.611 |
Alphabet | +1.554 |
Neg logit contributions | |
declass | -1.804 |
lobb | -1.732 |
� | -1.714 |
":[" | -1.637 |
bryce | -1.633 |
Token | . |
Token ID | 13 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
Metatron | +0.689 |
Sac | +0.665 |
Syl | +0.642 |
Es | +0.620 |
Alphabet | +0.594 |
Neg logit contributions | |
declass | -0.767 |
lobb | -0.738 |
� | -0.728 |
":[" | -0.697 |
bryce | -0.695 |
Token | If |
Token ID | 1002 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
Metatron | +0.264 |
Sac | +0.255 |
Syl | +0.244 |
Es | +0.236 |
Alphabet | +0.224 |
Neg logit contributions | |
declass | -0.353 |
lobb | -0.341 |
� | -0.337 |
":[" | -0.324 |
Kubrick | -0.322 |
Token | it |
Token ID | 340 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
declass | +0.419 |
lobb | +0.404 |
� | +0.398 |
":[" | +0.382 |
bryce | +0.380 |
Neg logit contributions | |
Metatron | -0.350 |
Sac | -0.338 |
Syl | -0.325 |
Es | -0.314 |
Alphabet | -0.300 |
Token | ble |
Token ID | 7245 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
declass | +3.306 |
lobb | +3.237 |
� | +3.067 |
":[" | +3.004 |
Kubrick | +2.935 |
Neg logit contributions | |
Metatron | -3.848 |
Sac | -3.724 |
Syl | -3.538 |
Es | -3.485 |
Alphabet | -3.350 |
Token | eds |
Token ID | 5379 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Metatron | +0.907 |
Sac | +0.874 |
Syl | +0.834 |
Es | +0.804 |
Alphabet | +0.756 |
Neg logit contributions | |
declass | -1.457 |
lobb | -1.407 |
� | -1.399 |
":[" | -1.341 |
bryce | -1.339 |
Token | , |
Token ID | 11 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Metatron | +0.262 |
Sac | +0.253 |
Syl | +0.244 |
Es | +0.236 |
Alphabet | +0.226 |
Neg logit contributions | |
declass | -0.282 |
lobb | -0.272 |
� | -0.268 |
":[" | -0.256 |
bryce | -0.255 |
Token | you |
Token ID | 345 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
declass | +1.143 |
lobb | +1.100 |
� | +1.078 |
":[" | +1.032 |
Kubrick | +1.026 |
Neg logit contributions | |
Metatron | -1.144 |
Sac | -1.111 |
Syl | -1.067 |
Es | -1.040 |
Alphabet | -0.996 |
Token | let |
Token ID | 1309 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
declass | +0.683 |
lobb | +0.656 |
� | +0.647 |
":[" | +0.619 |
Kubrick | +0.609 |
Neg logit contributions | |
Metatron | -0.753 |
Sac | -0.728 |
Syl | -0.705 |
Es | -0.685 |
Alphabet | -0.659 |
Token | it |
Token ID | 340 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Metatron | +0.234 |
Sac | +0.227 |
Syl | +0.218 |
Es | +0.211 |
Alphabet | +0.202 |
Neg logit contributions | |
declass | -0.258 |
lobb | -0.248 |
� | -0.244 |
":[" | -0.234 |
bryce | -0.233 |
Token | dry |
Token ID | 5894 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
declass | +0.082 |
lobb | +0.080 |
� | +0.078 |
":[" | +0.075 |
FAC | +0.074 |
Neg logit contributions | |
Metatron | -0.075 |
Sac | -0.072 |
Syl | -0.069 |
Es | -0.068 |
Alphabet | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
declass | +4.130 |
lobb | +4.024 |
� | +3.946 |
FAC | +3.738 |
":[" | +3.704 |
Neg logit contributions | |
Metatron | -4.436 |
Sac | -4.366 |
Syl | -4.168 |
Es | -4.071 |
Alphabet | -3.850 |
Token | . |
Token ID | 13 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
declass | +1.396 |
lobb | +1.348 |
� | +1.326 |
":[" | +1.268 |
bryce | +1.251 |
Neg logit contributions | |
Metatron | -1.391 |
Sac | -1.347 |
Syl | -1.297 |
Es | -1.257 |
Alphabet | -1.207 |
Token | One |
Token ID | 1881 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
Metatron | +0.372 |
Sac | +0.360 |
Syl | +0.347 |
Es | +0.336 |
Alphabet | +0.322 |
Neg logit contributions | |
declass | -0.404 |
lobb | -0.390 |
� | -0.384 |
":[" | -0.367 |
bryce | -0.365 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
Metatron | +0.024 |
Sac | +0.023 |
Syl | +0.022 |
Es | +0.022 |
Alphabet | +0.021 |
Neg logit contributions | |
declass | -0.024 |
lobb | -0.023 |
� | -0.023 |
":[" | -0.022 |
Kubrick | -0.021 |
Token | he |
Token ID | 339 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
declass | +2.399 |
lobb | +2.349 |
� | +2.281 |
Kubrick | +2.182 |
":[" | +2.162 |
Neg logit contributions | |
Metatron | -2.198 |
Sac | -2.137 |
Syl | -2.056 |
Es | -1.975 |
Alphabet | -1.878 |
Token | pitched |
Token ID | 21730 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
declass | +0.772 |
lobb | +0.754 |
� | +0.735 |
":[" | +0.696 |
bryce | +0.689 |
Neg logit contributions | |
Metatron | -0.798 |
Sac | -0.773 |
Syl | -0.747 |
Es | -0.721 |
Alphabet | -0.696 |
Token | is |
Token ID | 318 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
declass | +1.367 |
lobb | +1.330 |
� | +1.296 |
":[" | +1.232 |
Kubrick | +1.227 |
Neg logit contributions | |
Metatron | -1.336 |
Sac | -1.293 |
Syl | -1.239 |
Es | -1.209 |
Alphabet | -1.149 |
Token | a |
Token ID | 257 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
declass | +0.105 |
lobb | +0.101 |
� | +0.099 |
":[" | +0.095 |
bryce | +0.094 |
Neg logit contributions | |
Metatron | -0.099 |
Sac | -0.095 |
Syl | -0.092 |
Es | -0.089 |
Alphabet | -0.085 |
Token | new |
Token ID | 649 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Metatron | +0.624 |
Sac | +0.606 |
Syl | +0.586 |
Es | +0.568 |
Alphabet | +0.547 |
Neg logit contributions | |
declass | -0.572 |
lobb | -0.549 |
� | -0.540 |
":[" | -0.515 |
bryce | -0.513 |
Token | ordinance |
Token ID | 19784 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
Metatron | +1.119 |
Sac | +1.086 |
Syl | +1.047 |
Es | +1.012 |
Alphabet | +0.975 |
Neg logit contributions | |
declass | -1.194 |
lobb | -1.149 |
� | -1.133 |
bryce | -1.085 |
":[" | -1.084 |
Token | that |
Token ID | 326 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Metatron | +0.031 |
Sac | +0.030 |
Syl | +0.029 |
Es | +0.028 |
Alphabet | +0.027 |
Neg logit contributions | |
declass | -0.032 |
lobb | -0.031 |
� | -0.031 |
":[" | -0.029 |
bryce | -0.029 |
Token | would |
Token ID | 561 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
declass | +0.846 |
lobb | +0.820 |
� | +0.797 |
":[" | +0.762 |
FAC | +0.754 |
Neg logit contributions | |
Metatron | -0.827 |
Sac | -0.802 |
Syl | -0.772 |
Es | -0.751 |
Alphabet | -0.714 |
Token | 's |
Token ID | 338 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
declass | +1.368 |
lobb | +1.320 |
� | +1.279 |
FAC | +1.224 |
":[" | +1.223 |
Neg logit contributions | |
Metatron | -1.508 |
Sac | -1.464 |
Syl | -1.403 |
Es | -1.365 |
Alphabet | -1.308 |
Token | organizers |
Token ID | 19043 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
declass | +1.394 |
lobb | +1.350 |
� | +1.305 |
FAC | +1.250 |
":[" | +1.243 |
Neg logit contributions | |
Metatron | -1.566 |
Sac | -1.530 |
Syl | -1.462 |
Es | -1.426 |
Alphabet | -1.370 |
Token | stated |
Token ID | 5081 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Metatron | +0.398 |
Sac | +0.386 |
Syl | +0.371 |
Es | +0.360 |
Alphabet | +0.344 |
Neg logit contributions | |
declass | -0.431 |
lobb | -0.415 |
� | -0.409 |
":[" | -0.391 |
bryce | -0.389 |
Token | that |
Token ID | 326 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
Metatron | +0.325 |
Sac | +0.314 |
Syl | +0.304 |
Es | +0.295 |
Alphabet | +0.284 |
Neg logit contributions | |
declass | -0.316 |
lobb | -0.304 |
� | -0.299 |
bryce | -0.285 |
":[" | -0.285 |
Token | the |
Token ID | 262 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
declass | +0.498 |
lobb | +0.480 |
� | +0.470 |
":[" | +0.448 |
Kubrick | +0.444 |
Neg logit contributions | |
Metatron | -0.525 |
Sac | -0.511 |
Syl | -0.492 |
Es | -0.477 |
Alphabet | -0.459 |
Token | full |
Token ID | 1336 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Metatron | +0.140 |
Sac | +0.136 |
Syl | +0.131 |
Es | +0.127 |
Alphabet | +0.122 |
Neg logit contributions | |
declass | -0.136 |
lobb | -0.131 |
� | -0.128 |
":[" | -0.122 |
bryce | -0.122 |
Token | lineup |
Token ID | 12750 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
declass | +1.245 |
lobb | +1.203 |
� | +1.169 |
FAC | +1.120 |
":[" | +1.118 |
Neg logit contributions | |
Metatron | -1.158 |
Sac | -1.125 |
Syl | -1.078 |
Es | -1.048 |
Alphabet | -0.999 |
Token | of |
Token ID | 286 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Metatron | +0.784 |
Sac | +0.761 |
Syl | +0.735 |
Es | +0.705 |
Alphabet | +0.680 |
Neg logit contributions | |
declass | -0.931 |
lobb | -0.898 |
� | -0.893 |
bryce | -0.853 |
":[" | -0.850 |
Token | games |
Token ID | 1830 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Metatron | +1.688 |
Sac | +1.626 |
Syl | +1.589 |
Es | +1.541 |
Alphabet | +1.477 |
Neg logit contributions | |
declass | -1.726 |
� | -1.656 |
lobb | -1.628 |
bryce | -1.594 |
":[" | -1.576 |
Token | that |
Token ID | 326 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
Metatron | +0.101 |
Sac | +0.098 |
Syl | +0.094 |
Es | +0.091 |
Alphabet | +0.087 |
Neg logit contributions | |
declass | -0.104 |
lobb | -0.100 |
� | -0.098 |
":[" | -0.094 |
Kubrick | -0.094 |
Token | will |
Token ID | 481 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
Metatron | +0.525 |
Sac | +0.507 |
Syl | +0.487 |
Es | +0.470 |
Alphabet | +0.448 |
Neg logit contributions | |
declass | -0.660 |
lobb | -0.637 |
� | -0.628 |
":[" | -0.603 |
bryce | -0.601 |
Token | issues |
Token ID | 2428 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
declass | +0.772 |
lobb | +0.745 |
� | +0.716 |
":[" | +0.692 |
Kubrick | +0.688 |
Neg logit contributions | |
Metatron | -0.763 |
Sac | -0.739 |
Syl | -0.717 |
Es | -0.694 |
Alphabet | -0.662 |
Token | related |
Token ID | 3519 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
declass | +1.318 |
lobb | +1.267 |
� | +1.232 |
Kubrick | +1.180 |
":[" | +1.179 |
Neg logit contributions | |
Metatron | -1.298 |
Sac | -1.262 |
Syl | -1.215 |
Es | -1.184 |
Alphabet | -1.125 |
Token | to |
Token ID | 284 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
declass | +0.177 |
lobb | +0.171 |
� | +0.168 |
":[" | +0.161 |
bryce | +0.161 |
Neg logit contributions | |
Metatron | -0.154 |
Sac | -0.149 |
Syl | -0.144 |
Es | -0.139 |
Alphabet | -0.133 |
Token | the |
Token ID | 262 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
declass | +0.282 |
lobb | +0.271 |
� | +0.266 |
":[" | +0.254 |
bryce | +0.253 |
Neg logit contributions | |
Metatron | -0.288 |
Sac | -0.279 |
Syl | -0.269 |
Es | -0.261 |
Alphabet | -0.251 |
Token | Palestine |
Token ID | 17263 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
declass | +0.367 |
lobb | +0.352 |
� | +0.344 |
":[" | +0.328 |
bryce | +0.326 |
Neg logit contributions | |
Metatron | -0.410 |
Sac | -0.399 |
Syl | -0.386 |
Es | -0.375 |
Alphabet | -0.360 |
Token | - |
Token ID | 12 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
declass | +1.561 |
lobb | +1.503 |
� | +1.464 |
":[" | +1.379 |
Kubrick | +1.375 |
Neg logit contributions | |
Metatron | -2.051 |
Sac | -1.994 |
Syl | -1.932 |
Es | -1.892 |
Alphabet | -1.809 |
Token | Israel |
Token ID | 14040 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
declass | +1.637 |
lobb | +1.590 |
� | +1.560 |
":[" | +1.500 |
bryce | +1.495 |
Neg logit contributions | |
Metatron | -1.358 |
Sac | -1.286 |
Syl | -1.263 |
Es | -1.197 |
Alphabet | -1.159 |
Token | conflict |
Token ID | 5358 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
declass | +2.911 |
lobb | +2.818 |
� | +2.688 |
FAC | +2.526 |
":[" | +2.522 |
Neg logit contributions | |
Metatron | -3.995 |
Sac | -3.863 |
Syl | -3.792 |
Es | -3.707 |
inventoryQuantity | -3.533 |
Token | ; |
Token ID | 26 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
declass | +0.181 |
lobb | +0.174 |
� | +0.171 |
":[" | +0.164 |
bryce | +0.163 |
Neg logit contributions | |
Metatron | -0.168 |
Sac | -0.163 |
Syl | -0.157 |
Es | -0.152 |
Alphabet | -0.146 |
Token | it |
Token ID | 340 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
declass | +1.308 |
lobb | +1.259 |
� | +1.226 |
":[" | +1.174 |
Kubrick | +1.169 |
Neg logit contributions | |
Metatron | -1.321 |
Sac | -1.284 |
Syl | -1.238 |
Es | -1.200 |
Alphabet | -1.150 |
Token | has |
Token ID | 468 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
declass | +0.900 |
lobb | +0.870 |
� | +0.849 |
":[" | +0.811 |
Kubrick | +0.807 |
Neg logit contributions | |
Metatron | -0.850 |
Sac | -0.823 |
Syl | -0.792 |
Es | -0.768 |
Alphabet | -0.736 |
Token | self |
Token ID | 2116 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Metatron | +0.251 |
Sac | +0.243 |
Syl | +0.236 |
Es | +0.228 |
Alphabet | +0.220 |
Neg logit contributions | |
declass | -0.231 |
lobb | -0.222 |
� | -0.218 |
":[" | -0.208 |
bryce | -0.208 |
Token | and |
Token ID | 290 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
declass | +0.767 |
lobb | +0.736 |
� | +0.727 |
":[" | +0.693 |
bryce | +0.688 |
Neg logit contributions | |
Metatron | -0.781 |
Sac | -0.756 |
Syl | -0.731 |
Es | -0.709 |
Alphabet | -0.680 |
Token | feeling |
Token ID | 4203 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
declass | +0.705 |
lobb | +0.676 |
� | +0.664 |
":[" | +0.634 |
bryce | +0.631 |
Neg logit contributions | |
Metatron | -0.748 |
Sac | -0.726 |
Syl | -0.701 |
Es | -0.681 |
Alphabet | -0.654 |
Token | that |
Token ID | 326 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
declass | +2.480 |
lobb | +2.355 |
� | +2.298 |
":[" | +2.220 |
Kubrick | +2.220 |
Neg logit contributions | |
Metatron | -2.643 |
Sac | -2.600 |
Syl | -2.484 |
Es | -2.455 |
Alphabet | -2.348 |
Token | muscle |
Token ID | 8280 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
declass | +0.524 |
lobb | +0.504 |
� | +0.494 |
":[" | +0.472 |
Kubrick | +0.469 |
Neg logit contributions | |
Metatron | -0.551 |
Sac | -0.535 |
Syl | -0.516 |
Es | -0.502 |
Alphabet | -0.482 |
Token | memory |
Token ID | 4088 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
declass | +0.536 |
lobb | +0.515 |
� | +0.507 |
":[" | +0.483 |
bryce | +0.481 |
Neg logit contributions | |
Metatron | -0.553 |
Sac | -0.536 |
Syl | -0.518 |
Es | -0.503 |
Alphabet | -0.483 |
Token | return |
Token ID | 1441 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
declass | +3.186 |
lobb | +3.060 |
� | +2.938 |
":[" | +2.878 |
FAC | +2.834 |
Neg logit contributions | |
Metatron | -3.199 |
Sac | -3.092 |
Syl | -2.957 |
Es | -2.902 |
Alphabet | -2.798 |
Token | . |
Token ID | 13 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
declass | +3.164 |
lobb | +3.031 |
� | +3.006 |
":[" | +2.877 |
Kubrick | +2.849 |
Neg logit contributions | |
Metatron | -3.194 |
Sac | -3.109 |
Syl | -2.972 |
Es | -2.895 |
Alphabet | -2.814 |
Token | That |
Token ID | 1320 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Metatron | +0.035 |
Sac | +0.034 |
Syl | +0.033 |
Es | +0.032 |
Alphabet | +0.030 |
Neg logit contributions | |
declass | -0.044 |
lobb | -0.042 |
� | -0.042 |
":[" | -0.040 |
Kubrick | -0.040 |
Token | � |
Token ID | 447 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
declass | +1.134 |
lobb | +1.088 |
� | +1.071 |
":[" | +1.021 |
Kubrick | +1.016 |
Neg logit contributions | |
Metatron | -1.144 |
Sac | -1.110 |
Syl | -1.070 |
Es | -1.040 |
Alphabet | -0.998 |
Token | � |
Token ID | 247 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
declass | +0.439 |
lobb | +0.420 |
� | +0.417 |
":[" | +0.398 |
Kubrick | +0.389 |
Neg logit contributions | |
Metatron | -0.640 |
Sac | -0.619 |
Syl | -0.605 |
Es | -0.591 |
Alphabet | -0.570 |
Token | shif |
Token ID | 7143 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
declass | +0.283 |
lobb | +0.272 |
� | +0.267 |
":[" | +0.255 |
bryce | +0.254 |
Neg logit contributions | |
Metatron | -0.289 |
Sac | -0.281 |
Syl | -0.271 |
Es | -0.263 |
Alphabet | -0.252 |
Token | ter |
Token ID | 353 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
declass | +0.016 |
lobb | +0.015 |
� | +0.015 |
":[" | +0.015 |
Kubrick | +0.014 |
Neg logit contributions | |
Metatron | -0.015 |
Sac | -0.015 |
Syl | -0.014 |
Es | -0.014 |
Alphabet | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
declass | +0.164 |
lobb | +0.158 |
� | +0.155 |
":[" | +0.148 |
bryce | +0.147 |
Neg logit contributions | |
Metatron | -0.161 |
Sac | -0.156 |
Syl | -0.151 |
Es | -0.146 |
Alphabet | -0.140 |
Token | You |
Token ID | 921 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
declass | +1.207 |
lobb | +1.160 |
� | +1.152 |
":[" | +1.104 |
Kubrick | +1.101 |
Neg logit contributions | |
Metatron | -0.918 |
Sac | -0.883 |
Syl | -0.850 |
Es | -0.821 |
Alphabet | -0.777 |
Token | DO |
Token ID | 8410 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
declass | +1.843 |
lobb | +1.756 |
� | +1.713 |
":[" | +1.663 |
FAC | +1.642 |
Neg logit contributions | |
Metatron | -1.856 |
Sac | -1.797 |
Syl | -1.740 |
Es | -1.687 |
Alphabet | -1.613 |
Token | NOT |
Token ID | 5626 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
declass | +4.338 |
lobb | +3.921 |
� | +3.913 |
FAC | +3.823 |
":[" | +3.808 |
Neg logit contributions | |
Metatron | -5.953 |
Sac | -5.721 |
Syl | -5.651 |
Es | -5.383 |
inventoryQuantity | -5.280 |
Token | need |
Token ID | 761 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
declass | +4.235 |
lobb | +3.904 |
� | +3.833 |
FAC | +3.763 |
":[" | +3.749 |
Neg logit contributions | |
Metatron | -4.377 |
Sac | -4.207 |
Syl | -4.074 |
Es | -3.933 |
inventoryQuantity | -3.807 |
Token | to |
Token ID | 284 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
declass | +1.592 |
lobb | +1.535 |
� | +1.509 |
":[" | +1.445 |
bryce | +1.436 |
Neg logit contributions | |
Metatron | -1.467 |
Sac | -1.421 |
Syl | -1.368 |
Es | -1.326 |
Alphabet | -1.269 |
Token | remove |
Token ID | 4781 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
declass | +1.721 |
lobb | +1.621 |
� | +1.569 |
":[" | +1.520 |
Kubrick | +1.512 |
Neg logit contributions | |
Metatron | -1.945 |
Sac | -1.873 |
Syl | -1.810 |
Es | -1.776 |
Alphabet | -1.687 |
Token | the |
Token ID | 262 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
declass | +0.309 |
lobb | +0.297 |
� | +0.292 |
":[" | +0.279 |
bryce | +0.278 |
Neg logit contributions | |
Metatron | -0.308 |
Sac | -0.298 |
Syl | -0.288 |
Es | -0.279 |
Alphabet | -0.267 |
Token | four |
Token ID | 1440 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
declass | +1.212 |
lobb | +1.169 |
� | +1.139 |
":[" | +1.090 |
Kubrick | +1.081 |
Neg logit contributions | |
Metatron | -1.278 |
Sac | -1.246 |
Syl | -1.198 |
Es | -1.166 |
Alphabet | -1.118 |
Token | demographic |
Token ID | 16728 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Metatron | +0.115 |
Sac | +0.111 |
Syl | +0.108 |
Es | +0.105 |
Alphabet | +0.101 |
Neg logit contributions | |
declass | -0.094 |
lobb | -0.090 |
� | -0.089 |
":[" | -0.085 |
bryce | -0.084 |
Token | that |
Token ID | 326 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Metatron | +1.159 |
Sac | +1.123 |
Syl | +1.084 |
Es | +1.049 |
Alphabet | +1.014 |
Neg logit contributions | |
declass | -1.130 |
lobb | -1.083 |
� | -1.078 |
":[" | -1.028 |
bryce | -1.021 |
Token | has |
Token ID | 468 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Metatron | +0.970 |
Sac | +0.937 |
Syl | +0.904 |
Es | +0.872 |
Alphabet | +0.837 |
Neg logit contributions | |
declass | -1.105 |
lobb | -1.063 |
� | -1.050 |
":[" | -1.005 |
bryce | -1.002 |
Token | under |
Token ID | 739 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Metatron | +0.843 |
Sac | +0.817 |
Syl | +0.787 |
Es | +0.762 |
Alphabet | +0.731 |
Neg logit contributions | |
declass | -0.890 |
lobb | -0.857 |
� | -0.843 |
":[" | -0.806 |
bryce | -0.803 |
Token | - |
Token ID | 12 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Metatron | +1.151 |
Sac | +1.100 |
Syl | +1.068 |
Es | +1.006 |
Alphabet | +0.973 |
Neg logit contributions | |
declass | -1.604 |
lobb | -1.540 |
� | -1.526 |
":[" | -1.465 |
bryce | -1.458 |
Token | priv |
Token ID | 13776 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
declass | +2.324 |
lobb | +2.261 |
� | +2.220 |
bryce | +2.160 |
":[" | +2.154 |
Neg logit contributions | |
Metatron | -1.297 |
Sac | -1.226 |
Syl | -1.182 |
Es | -1.119 |
Alphabet | -1.063 |
Token | ileged |
Token ID | 48446 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
declass | +2.896 |
lobb | +2.736 |
� | +2.602 |
bryce | +2.513 |
FAC | +2.460 |
Neg logit contributions | |
Metatron | -5.268 |
Sac | -4.938 |
Syl | -4.909 |
Es | -4.697 |
alia | -4.580 |
Token | access |
Token ID | 1895 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
declass | +0.670 |
lobb | +0.647 |
� | +0.629 |
":[" | +0.596 |
bryce | +0.594 |
Neg logit contributions | |
Metatron | -0.795 |
Sac | -0.773 |
Syl | -0.745 |
Es | -0.727 |
Alphabet | -0.697 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Metatron | +0.343 |
Sac | +0.332 |
Syl | +0.320 |
Es | +0.310 |
Alphabet | +0.295 |
Neg logit contributions | |
declass | -0.402 |
lobb | -0.385 |
� | -0.380 |
":[" | -0.365 |
bryce | -0.363 |
Token | calendars |
Token ID | 50215 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
declass | +0.712 |
lobb | +0.686 |
� | +0.665 |
":[" | +0.635 |
Kubrick | +0.631 |
Neg logit contributions | |
Metatron | -0.846 |
Sac | -0.823 |
Syl | -0.794 |
Es | -0.773 |
Alphabet | -0.742 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
declass | +1.494 |
lobb | +1.448 |
� | +1.421 |
":[" | +1.345 |
Kubrick | +1.341 |
Neg logit contributions | |
Metatron | -1.465 |
Sac | -1.421 |
Syl | -1.368 |
Es | -1.324 |
Alphabet | -1.268 |
Token | supposed |
Token ID | 4385 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
Metatron | +0.202 |
Sac | +0.196 |
Syl | +0.191 |
Es | +0.186 |
Alphabet | +0.180 |
Neg logit contributions | |
declass | -0.134 |
lobb | -0.128 |
� | -0.125 |
":[" | -0.118 |
bryce | -0.118 |
Token | to |
Token ID | 284 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
declass | +1.821 |
lobb | +1.739 |
":[" | +1.702 |
� | +1.689 |
Kubrick | +1.637 |
Neg logit contributions | |
Metatron | -2.063 |
Sac | -1.974 |
Syl | -1.912 |
Es | -1.869 |
Alphabet | -1.794 |
Token | be |
Token ID | 307 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
declass | +1.440 |
lobb | +1.363 |
":[" | +1.321 |
� | +1.306 |
Kubrick | +1.275 |
Neg logit contributions | |
Metatron | -1.901 |
Sac | -1.838 |
Syl | -1.779 |
Es | -1.743 |
Alphabet | -1.666 |
Token | a |
Token ID | 257 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
declass | +3.267 |
lobb | +3.121 |
� | +3.047 |
":[" | +2.932 |
Kubrick | +2.917 |
Neg logit contributions | |
Metatron | -3.521 |
Sac | -3.415 |
Syl | -3.299 |
Es | -3.234 |
Alphabet | -3.070 |
Token | New |
Token ID | 968 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
declass | +4.580 |
lobb | +4.363 |
� | +4.217 |
Kubrick | +4.134 |
":[" | +4.069 |
Neg logit contributions | |
Metatron | -4.840 |
Sac | -4.656 |
Syl | -4.540 |
Es | -4.418 |
Alphabet | -4.228 |
Token | York |
Token ID | 1971 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
declass | +2.641 |
lobb | +2.470 |
� | +2.355 |
Ghostbusters | +2.335 |
Kubrick | +2.332 |
Neg logit contributions | |
Metatron | -4.634 |
Sac | -4.453 |
Syl | -4.285 |
Es | -4.258 |
inventoryQuantity | -4.137 |
Token | City |
Token ID | 2254 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
declass | +3.848 |
lobb | +3.667 |
Ghostbusters | +3.512 |
":[" | +3.509 |
Kubrick | +3.469 |
Neg logit contributions | |
Metatron | -4.784 |
Sac | -4.618 |
Es | -4.438 |
Syl | -4.420 |
inventoryQuantity | -4.272 |
Token | mansion |
Token ID | 24141 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
declass | +2.278 |
lobb | +2.189 |
� | +2.082 |
":[" | +2.050 |
Kubrick | +2.028 |
Neg logit contributions | |
Metatron | -2.359 |
Sac | -2.291 |
Syl | -2.198 |
Es | -2.172 |
Alphabet | -2.051 |
Token | , |
Token ID | 11 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
declass | +2.894 |
lobb | +2.766 |
":[" | +2.670 |
� | +2.669 |
Kubrick | +2.621 |
Neg logit contributions | |
Metatron | -3.084 |
Sac | -2.956 |
Syl | -2.871 |
Es | -2.846 |
inventoryQuantity | -2.715 |
Token | called |
Token ID | 1444 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
declass | +0.382 |
lobb | +0.368 |
� | +0.359 |
":[" | +0.350 |
Kubrick | +0.348 |
Neg logit contributions | |
Metatron | -0.286 |
Sac | -0.274 |
Syl | -0.264 |
Es | -0.257 |
Alphabet | -0.242 |
Token | Ald |
Token ID | 15586 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
declass | +3.633 |
lobb | +3.521 |
� | +3.432 |
":[" | +3.338 |
Kubrick | +3.328 |
Neg logit contributions | |
Metatron | -2.961 |
Sac | -2.821 |
Syl | -2.749 |
Es | -2.649 |
Alphabet | -2.501 |
Token |
|
Token ID | 198 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Metatron | +0.743 |
Sac | +0.719 |
Syl | +0.694 |
Es | +0.672 |
Alphabet | +0.646 |
Neg logit contributions | |
declass | -0.791 |
lobb | -0.762 |
� | -0.745 |
bryce | -0.719 |
":[" | -0.718 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Metatron | +2.104 |
Sac | +2.057 |
Syl | +1.977 |
Es | +1.921 |
Alphabet | +1.842 |
Neg logit contributions | |
declass | -2.137 |
lobb | -2.067 |
� | -2.032 |
bryce | -1.931 |
":[" | -1.918 |
Token | Previously |
Token ID | 36837 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
Metatron | +0.787 |
Sac | +0.777 |
Syl | +0.726 |
Es | +0.717 |
Alphabet | +0.666 |
Neg logit contributions | |
declass | -1.129 |
lobb | -1.097 |
� | -1.067 |
":[" | -1.025 |
Kubrick | -1.024 |
Token | home |
Token ID | 1363 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
Metatron | +0.376 |
Sac | +0.363 |
Syl | +0.349 |
Es | +0.336 |
Alphabet | +0.321 |
Neg logit contributions | |
declass | -0.473 |
lobb | -0.457 |
� | -0.451 |
":[" | -0.433 |
bryce | -0.431 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
declass | +0.599 |
lobb | +0.575 |
� | +0.566 |
":[" | +0.544 |
bryce | +0.542 |
Neg logit contributions | |
Metatron | -0.508 |
Sac | -0.492 |
Syl | -0.473 |
Es | -0.455 |
Alphabet | -0.436 |
Token | Great |
Token ID | 3878 |
Feature activation | -5.64e+00 |
Pos logit contributions | |
declass | +0.775 |
lobb | +0.745 |
� | +0.732 |
":[" | +0.699 |
bryce | +0.696 |
Neg logit contributions | |
Metatron | -0.790 |
Sac | -0.766 |
Syl | -0.740 |
Es | -0.717 |
Alphabet | -0.688 |
Token | full |
Token ID | 12853 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
declass | +3.824 |
lobb | +3.729 |
� | +3.728 |
Kubrick | +3.482 |
":[" | +3.467 |
Neg logit contributions | |
Metatron | -4.270 |
Sac | -4.107 |
Syl | -4.030 |
Es | -3.933 |
Alphabet | -3.756 |
Token | Taco |
Token ID | 40129 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
declass | +0.357 |
lobb | +0.343 |
� | +0.337 |
":[" | +0.321 |
bryce | +0.319 |
Neg logit contributions | |
Metatron | -0.392 |
Sac | -0.381 |
Syl | -0.368 |
Es | -0.358 |
Alphabet | -0.344 |
Token | ( |
Token ID | 357 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
declass | +0.371 |
lobb | +0.358 |
� | +0.352 |
":[" | +0.337 |
bryce | +0.336 |
Neg logit contributions | |
Metatron | -0.326 |
Sac | -0.315 |
Syl | -0.304 |
Es | -0.293 |
Alphabet | -0.281 |
Token | which |
Token ID | 4758 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
declass | +0.832 |
lobb | +0.802 |
� | +0.790 |
":[" | +0.756 |
bryce | +0.753 |
Neg logit contributions | |
Metatron | -0.796 |
Sac | -0.765 |
Syl | -0.743 |
Es | -0.716 |
Alphabet | -0.690 |
Token | , |
Token ID | 11 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
declass | +0.700 |
lobb | +0.675 |
� | +0.657 |
Kubrick | +0.629 |
":[" | +0.628 |
Neg logit contributions | |
Metatron | -0.681 |
Sac | -0.662 |
Syl | -0.633 |
Es | -0.618 |
Alphabet | -0.589 |
Token | . |
Token ID | 13 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
Metatron | +1.546 |
Sac | +1.486 |
Syl | +1.441 |
Es | +1.389 |
Alphabet | +1.332 |
Neg logit contributions | |
declass | -1.743 |
lobb | -1.677 |
� | -1.645 |
":[" | -1.585 |
bryce | -1.580 |
Token | So |
Token ID | 1406 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Metatron | +0.257 |
Sac | +0.248 |
Syl | +0.238 |
Es | +0.229 |
Alphabet | +0.218 |
Neg logit contributions | |
declass | -0.343 |
lobb | -0.332 |
� | -0.328 |
":[" | -0.315 |
bryce | -0.313 |
Token | I |
Token ID | 314 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
declass | +0.991 |
lobb | +0.956 |
� | +0.941 |
":[" | +0.903 |
Kubrick | +0.898 |
Neg logit contributions | |
Metatron | -0.834 |
Sac | -0.808 |
Syl | -0.775 |
Es | -0.749 |
Alphabet | -0.717 |
Token | miss |
Token ID | 2051 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
declass | +1.045 |
lobb | +1.004 |
� | +0.978 |
":[" | +0.948 |
Kubrick | +0.925 |
Neg logit contributions | |
Metatron | -1.166 |
Sac | -1.130 |
Syl | -1.094 |
Es | -1.065 |
Alphabet | -1.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
declass | +0.389 |
lobb | +0.374 |
� | +0.367 |
":[" | +0.351 |
bryce | +0.349 |
Neg logit contributions | |
Metatron | -0.411 |
Sac | -0.400 |
Syl | -0.385 |
Es | -0.373 |
Alphabet | -0.359 |
Token | conversations |
Token ID | 10275 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
declass | +1.209 |
lobb | +1.166 |
� | +1.140 |
":[" | +1.084 |
Kubrick | +1.081 |
Neg logit contributions | |
Metatron | -1.401 |
Sac | -1.366 |
Syl | -1.314 |
Es | -1.285 |
Alphabet | -1.232 |
Token | , |
Token ID | 11 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
declass | +4.104 |
lobb | +3.987 |
� | +3.900 |
Kubrick | +3.773 |
":[" | +3.762 |
Neg logit contributions | |
Metatron | -3.773 |
Sac | -3.751 |
Syl | -3.516 |
Es | -3.444 |
2020 | -3.314 |
Token | her |
Token ID | 607 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
declass | +2.408 |
lobb | +2.341 |
� | +2.282 |
":[" | +2.189 |
Kubrick | +2.184 |
Neg logit contributions | |
Metatron | -2.313 |
Sac | -2.253 |
Syl | -2.159 |
Es | -2.105 |
Alphabet | -2.019 |
Token | friendship |
Token ID | 14738 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
declass | +1.703 |
lobb | +1.646 |
� | +1.600 |
":[" | +1.520 |
Kubrick | +1.519 |
Neg logit contributions | |
Metatron | -1.914 |
Sac | -1.866 |
Syl | -1.804 |
Es | -1.752 |
Alphabet | -1.674 |
Token | and |
Token ID | 290 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
declass | +0.688 |
lobb | +0.665 |
� | +0.653 |
":[" | +0.626 |
bryce | +0.623 |
Neg logit contributions | |
Metatron | -0.607 |
Sac | -0.588 |
Syl | -0.565 |
Es | -0.547 |
Alphabet | -0.523 |
Token | seeing |
Token ID | 4379 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Metatron | +0.058 |
Sac | +0.056 |
Syl | +0.054 |
Es | +0.052 |
Alphabet | +0.050 |
Neg logit contributions | |
declass | -0.055 |
lobb | -0.053 |
� | -0.052 |
":[" | -0.049 |
bryce | -0.049 |