Token | is |
Token ID | 318 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
APH | +2.701 |
Pyro | +2.441 |
ray | +2.417 |
� | +2.344 |
experien | +2.314 |
Neg logit contributions | |
idth | -2.195 |
psey | -1.568 |
Spoiler | -1.472 |
ento | -1.349 |
uning | -1.298 |
Token | false |
Token ID | 3991 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
idth | +0.274 |
psey | +0.205 |
Spoiler | +0.194 |
ento | +0.183 |
aunch | +0.173 |
Neg logit contributions | |
APH | -0.295 |
Pyro | -0.266 |
ray | -0.265 |
� | -0.254 |
xual | -0.250 |
Token | . |
Token ID | 13 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
APH | +0.302 |
Pyro | +0.272 |
ray | +0.271 |
� | +0.261 |
experien | +0.254 |
Neg logit contributions | |
idth | -0.322 |
psey | -0.242 |
Spoiler | -0.224 |
ento | -0.210 |
aunch | -0.202 |
Token |
|
Token ID | 198 |
Feature activation | +7.67e-03 |
Pos logit contributions | |
idth | +1.191 |
psey | +0.903 |
Spoiler | +0.841 |
ento | +0.789 |
uning | +0.759 |
Neg logit contributions | |
APH | -1.060 |
Pyro | -0.948 |
ray | -0.947 |
� | -0.914 |
experien | -0.893 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
idth | +0.078 |
Spoiler | +0.056 |
psey | +0.051 |
ento | +0.048 |
avis | +0.047 |
Neg logit contributions | |
APH | -0.106 |
experien | -0.098 |
xual | -0.096 |
Pyro | -0.095 |
�醒 | -0.095 |
Token | M |
Token ID | 44 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
idth | +1.486 |
psey | +1.100 |
Spoiler | +1.071 |
ento | +1.002 |
uning | +0.947 |
Neg logit contributions | |
APH | -1.456 |
Pyro | -1.370 |
experien | -1.317 |
xual | -1.317 |
ray | -1.308 |
Token | int |
Token ID | 600 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
idth | +9.789 |
psey | +7.573 |
ento | +7.290 |
uning | +6.108 |
aunch | +5.944 |
Neg logit contributions | |
Pyro | -13.135 |
APH | -12.889 |
experien | -12.094 |
xual | -12.058 |
Cyrus | -12.025 |
Token | z |
Token ID | 89 |
Feature activation | +6.54e-03 |
Pos logit contributions | |
APH | +0.869 |
experien | +0.796 |
Pyro | +0.787 |
�醒 | +0.775 |
BuyableInstoreAndOnline | +0.775 |
Neg logit contributions | |
idth | -0.773 |
psey | -0.553 |
Spoiler | -0.519 |
ento | -0.496 |
avis | -0.478 |
Token | has |
Token ID | 468 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
idth | +0.068 |
psey | +0.048 |
Spoiler | +0.044 |
ento | +0.040 |
uning | +0.039 |
Neg logit contributions | |
APH | -0.093 |
Pyro | -0.083 |
ray | -0.082 |
experien | -0.080 |
� | -0.080 |
Token | denied |
Token ID | 6699 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
idth | +1.228 |
psey | +0.844 |
Spoiler | +0.776 |
ento | +0.751 |
aunch | +0.693 |
Neg logit contributions | |
APH | -1.754 |
ray | -1.572 |
Pyro | -1.557 |
� | -1.527 |
xual | -1.506 |
Token | he |
Token ID | 339 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
APH | +0.618 |
Pyro | +0.548 |
ray | +0.544 |
� | +0.535 |
experien | +0.518 |
Neg logit contributions | |
idth | -0.536 |
psey | -0.400 |
Spoiler | -0.373 |
ento | -0.347 |
uning | -0.326 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
idth | +3.167 |
psey | +2.328 |
Spoiler | +2.207 |
ento | +2.009 |
uning | +1.965 |
Neg logit contributions | |
APH | -3.490 |
Pyro | -3.175 |
ray | -3.109 |
xual | -3.004 |
� | -3.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
idth | +0.276 |
psey | +0.208 |
Spoiler | +0.194 |
ento | +0.181 |
uning | +0.175 |
Neg logit contributions | |
APH | -0.248 |
Pyro | -0.221 |
ray | -0.221 |
� | -0.214 |
experien | -0.210 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
APH | +1.632 |
experien | +1.486 |
Pyro | +1.468 |
xual | +1.455 |
ray | +1.435 |
Neg logit contributions | |
idth | -1.339 |
Spoiler | -0.950 |
psey | -0.921 |
ento | -0.842 |
avis | -0.818 |
Token | CH |
Token ID | 3398 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
idth | +2.073 |
psey | +1.456 |
Spoiler | +1.410 |
aunch | +1.279 |
ento | +1.279 |
Neg logit contributions | |
APH | -2.175 |
xual | -2.086 |
Pyro | -2.076 |
experien | -2.010 |
ray | -1.927 |
Token | IC |
Token ID | 2149 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
idth | +5.927 |
Spoiler | +4.048 |
avis | +3.737 |
psey | +3.716 |
aunch | +3.650 |
Neg logit contributions | |
experien | -7.260 |
xual | -7.200 |
ray | -7.094 |
Pyro | -7.017 |
Skydragon | -7.001 |
Token | AG |
Token ID | 4760 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
idth | +1.140 |
psey | +0.882 |
Spoiler | +0.845 |
avis | +0.794 |
aunch | +0.786 |
Neg logit contributions | |
APH | -0.825 |
ray | -0.771 |
Pyro | -0.764 |
xual | -0.713 |
experien | -0.710 |
Token | O |
Token ID | 46 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
idth | +2.635 |
Spoiler | +1.132 |
ento | +0.520 |
O | +0.044 |
POST | -0.013 |
Neg logit contributions | |
BuyableInstoreAndOnline | -16.845 |
xual | -16.812 |
experien | -16.760 |
igree | -16.558 |
ray | -16.383 |
Token | -- |
Token ID | 1377 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
idth | +1.885 |
psey | +1.391 |
Spoiler | +1.317 |
ento | +1.190 |
uning | +1.171 |
Neg logit contributions | |
APH | -1.964 |
ray | -1.765 |
Pyro | -1.753 |
experien | -1.688 |
� | -1.676 |
Token | It |
Token ID | 632 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
idth | +2.815 |
Spoiler | +2.090 |
psey | +2.001 |
avis | +1.754 |
Flores | +1.753 |
Neg logit contributions | |
APH | -2.877 |
xual | -2.619 |
experien | -2.526 |
ray | -2.518 |
Pyro | -2.443 |
Token | 's |
Token ID | 338 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
idth | +0.278 |
psey | +0.201 |
Spoiler | +0.186 |
ento | +0.170 |
uning | +0.167 |
Neg logit contributions | |
APH | -0.340 |
Pyro | -0.308 |
ray | -0.304 |
� | -0.297 |
xual | -0.290 |
Token | going |
Token ID | 1016 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
idth | +4.058 |
psey | +3.068 |
Spoiler | +2.883 |
clicked | +2.568 |
assumed | +2.565 |
Neg logit contributions | |
APH | -6.059 |
xual | -5.361 |
ray | -5.235 |
�醒 | -5.221 |
� | -5.198 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
APH | +0.922 |
Pyro | +0.821 |
ray | +0.819 |
� | +0.798 |
experien | +0.774 |
Neg logit contributions | |
idth | -1.027 |
psey | -0.782 |
Spoiler | -0.720 |
ento | -0.672 |
uning | -0.650 |
Token | Flyers |
Token ID | 30652 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
APH | +1.120 |
ray | +0.981 |
Pyro | +0.981 |
� | +0.955 |
experien | +0.926 |
Neg logit contributions | |
idth | -1.404 |
psey | -1.083 |
Spoiler | -1.012 |
ento | -0.937 |
uning | -0.911 |
Token | was |
Token ID | 373 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
APH | +1.502 |
Pyro | +1.342 |
ray | +1.337 |
� | +1.304 |
experien | +1.277 |
Neg logit contributions | |
idth | -1.199 |
psey | -0.880 |
Spoiler | -0.806 |
ento | -0.737 |
uning | -0.704 |
Token | Chicago |
Token ID | 4842 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
idth | +0.391 |
psey | +0.288 |
Spoiler | +0.272 |
ento | +0.238 |
uning | +0.235 |
Neg logit contributions | |
APH | -0.464 |
ray | -0.412 |
Pyro | -0.409 |
� | -0.406 |
xual | -0.401 |
Token | 's |
Token ID | 338 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
idth | +5.837 |
psey | +3.966 |
Spoiler | +3.633 |
uning | +3.256 |
avis | +3.101 |
Neg logit contributions | |
APH | -9.068 |
Pyro | -8.177 |
xual | -8.023 |
ray | -7.994 |
� | -7.992 |
Token | fourth |
Token ID | 5544 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
idth | +5.395 |
Spoiler | +3.992 |
psey | +3.927 |
Flores | +3.349 |
clicked | +3.270 |
Neg logit contributions | |
APH | -7.232 |
xual | -6.397 |
ray | -6.241 |
�醒 | -6.179 |
� | -6.121 |
Token | straight |
Token ID | 3892 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
idth | +7.901 |
Spoiler | +5.792 |
psey | +5.480 |
clicked | +4.802 |
assumed | +4.729 |
Neg logit contributions | |
APH | -12.290 |
xual | -11.173 |
BuyableInstoreAndOnline | -10.969 |
ray | -10.836 |
guiActiveUn | -10.777 |
Token | , |
Token ID | 11 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
idth | +4.796 |
psey | +3.386 |
Spoiler | +3.384 |
ento | +2.914 |
clicked | +2.878 |
Neg logit contributions | |
APH | -6.462 |
xual | -5.773 |
ray | -5.721 |
Pyro | -5.695 |
BuyableInstoreAndOnline | -5.611 |
Token | the |
Token ID | 262 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
idth | +1.590 |
psey | +1.154 |
Spoiler | +1.095 |
ento | +0.959 |
uning | +0.958 |
Neg logit contributions | |
APH | -1.946 |
ray | -1.771 |
xual | -1.739 |
Pyro | -1.723 |
� | -1.704 |
Token | Blackhawks |
Token ID | 35663 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
idth | +2.382 |
psey | +1.728 |
Spoiler | +1.706 |
ento | +1.500 |
uning | +1.444 |
Neg logit contributions | |
APH | -2.617 |
xual | -2.308 |
ray | -2.269 |
Pyro | -2.252 |
� | -2.222 |
Token | ' |
Token ID | 6 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
idth | +6.057 |
psey | +4.424 |
Spoiler | +4.196 |
clicked | +3.869 |
contend | +3.776 |
Neg logit contributions | |
APH | -8.971 |
xual | -8.160 |
�醒 | -8.057 |
Pyro | -7.932 |
ray | -7.806 |
Token | s |
Token ID | 264 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
APH | +3.003 |
Pyro | +2.725 |
ray | +2.665 |
� | +2.646 |
ax | +2.448 |
Neg logit contributions | |
idth | -4.378 |
psey | -3.502 |
Spoiler | -3.080 |
ento | -3.039 |
aunch | -2.979 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
APH | +0.442 |
experien | +0.408 |
Pyro | +0.401 |
BuyableInstoreAndOnline | +0.399 |
�醒 | +0.396 |
Neg logit contributions | |
idth | -0.344 |
Spoiler | -0.236 |
psey | -0.225 |
ento | -0.209 |
avis | -0.206 |
Token | t |
Token ID | 83 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
APH | +2.369 |
Pyro | +2.105 |
experien | +2.066 |
ray | +2.017 |
Cyrus | +1.972 |
Neg logit contributions | |
idth | -2.659 |
psey | -1.964 |
Spoiler | -1.906 |
ento | -1.814 |
uning | -1.743 |
Token | . |
Token ID | 13 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
APH | +3.178 |
Pyro | +2.854 |
ray | +2.812 |
experien | +2.810 |
xual | +2.750 |
Neg logit contributions | |
idth | -2.883 |
psey | -2.038 |
Spoiler | -2.018 |
ento | -1.824 |
uning | -1.777 |
Token | I |
Token ID | 314 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
idth | +0.424 |
Spoiler | +0.311 |
psey | +0.304 |
ento | +0.271 |
uning | +0.263 |
Neg logit contributions | |
APH | -0.426 |
ray | -0.381 |
Pyro | -0.371 |
xual | -0.366 |
� | -0.359 |
Token | TA |
Token ID | 5603 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
idth | +2.547 |
psey | +1.868 |
Spoiler | +1.853 |
ento | +1.797 |
uning | +1.756 |
Neg logit contributions | |
APH | -2.271 |
Pyro | -2.166 |
experien | -2.121 |
ray | -2.108 |
xual | -2.104 |
Token | 8 |
Token ID | 807 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
idth | +10.765 |
psey | +7.705 |
Spoiler | +7.376 |
ento | +6.641 |
uning | +6.578 |
Neg logit contributions | |
APH | -11.756 |
ray | -10.574 |
Pyro | -10.401 |
� | -10.205 |
experien | -10.091 |
Token | Dan |
Token ID | 6035 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
idth | +0.936 |
psey | +0.685 |
Spoiler | +0.669 |
ento | +0.596 |
avis | +0.596 |
Neg logit contributions | |
APH | -0.880 |
ray | -0.776 |
Pyro | -0.753 |
experien | -0.746 |
� | -0.745 |
Token | ie |
Token ID | 494 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
APH | +2.305 |
Pyro | +2.045 |
ray | +2.032 |
� | +1.983 |
experien | +1.953 |
Neg logit contributions | |
idth | -2.443 |
psey | -1.828 |
Spoiler | -1.691 |
ento | -1.586 |
avis | -1.547 |
Token | le |
Token ID | 293 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
idth | +2.188 |
Spoiler | +1.658 |
psey | +1.576 |
avis | +1.473 |
ento | +1.463 |
Neg logit contributions | |
APH | -2.324 |
experien | -1.991 |
Pyro | -1.965 |
ray | -1.951 |
xual | -1.937 |
Token | Benn |
Token ID | 14025 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
idth | +2.741 |
psey | +2.107 |
Spoiler | +2.028 |
Flores | +1.908 |
avis | +1.898 |
Neg logit contributions | |
APH | -3.177 |
experien | -2.743 |
� | -2.694 |
ray | -2.682 |
xual | -2.667 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
APH | +3.170 |
Pyro | +2.840 |
ray | +2.835 |
� | +2.760 |
experien | +2.684 |
Neg logit contributions | |
idth | -3.253 |
psey | -2.438 |
Spoiler | -2.267 |
ento | -2.120 |
uning | -2.045 |
Token | In |
Token ID | 554 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
APH | +1.624 |
ray | +1.461 |
experien | +1.420 |
xual | +1.411 |
Pyro | +1.396 |
Neg logit contributions | |
idth | -1.512 |
Spoiler | -1.157 |
psey | -1.084 |
ento | -0.978 |
avis | -0.967 |
Token | addition |
Token ID | 3090 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
APH | +3.464 |
Pyro | +3.111 |
ray | +3.111 |
� | +3.029 |
experien | +2.941 |
Neg logit contributions | |
idth | -3.456 |
psey | -2.573 |
Spoiler | -2.367 |
ento | -2.215 |
uning | -2.125 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
APH | +1.472 |
Pyro | +1.355 |
ray | +1.334 |
� | +1.291 |
Cyrus | +1.243 |
Neg logit contributions | |
idth | -2.121 |
psey | -1.698 |
Spoiler | -1.525 |
ento | -1.496 |
aunch | -1.433 |
Token | without |
Token ID | 1231 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
APH | +0.138 |
ray | +0.123 |
� | +0.121 |
Pyro | +0.121 |
experien | +0.116 |
Neg logit contributions | |
idth | -0.123 |
psey | -0.090 |
Spoiler | -0.086 |
ento | -0.078 |
uning | -0.075 |
Token | spo |
Token ID | 15106 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
idth | +0.861 |
psey | +0.644 |
Spoiler | +0.611 |
ento | +0.548 |
uning | +0.535 |
Neg logit contributions | |
APH | -0.971 |
ray | -0.865 |
� | -0.855 |
Pyro | -0.853 |
ax | -0.816 |
Token | iling |
Token ID | 4386 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
idth | +5.486 |
psey | +2.405 |
uning | +2.017 |
avis | +1.986 |
Spoiler | +1.714 |
Neg logit contributions | |
APH | -15.607 |
Pyro | -14.844 |
Skydragon | -14.636 |
experien | -14.579 |
BuyableInstoreAndOnline | -14.500 |
Token | , |
Token ID | 11 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
idth | +2.433 |
psey | +1.752 |
Spoiler | +1.704 |
ento | +1.526 |
aunch | +1.491 |
Neg logit contributions | |
APH | -2.834 |
ray | -2.543 |
Pyro | -2.529 |
� | -2.477 |
experien | -2.439 |
Token | for |
Token ID | 329 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
APH | +1.134 |
ray | +1.018 |
Pyro | +1.008 |
� | +0.994 |
experien | +0.962 |
Neg logit contributions | |
idth | -1.061 |
psey | -0.782 |
Spoiler | -0.736 |
ento | -0.671 |
uning | -0.649 |
Token | some |
Token ID | 617 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
idth | +1.238 |
psey | +0.903 |
Spoiler | +0.862 |
ento | +0.796 |
avis | +0.770 |
Neg logit contributions | |
APH | -1.321 |
ray | -1.183 |
Pyro | -1.167 |
� | -1.161 |
xual | -1.119 |
Token | of |
Token ID | 286 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
APH | +1.925 |
Pyro | +1.723 |
ray | +1.718 |
� | +1.685 |
ax | +1.624 |
Neg logit contributions | |
idth | -1.920 |
psey | -1.430 |
Spoiler | -1.334 |
ento | -1.234 |
uning | -1.194 |
Token | the |
Token ID | 262 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
idth | +1.861 |
psey | +1.396 |
Spoiler | +1.249 |
uning | +1.141 |
ento | +1.104 |
Neg logit contributions | |
APH | -2.262 |
Pyro | -2.026 |
ray | -2.018 |
xual | -1.994 |
� | -1.976 |
Token | club |
Token ID | 3430 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
idth | +2.430 |
psey | +1.868 |
Spoiler | +1.793 |
uning | +1.531 |
ento | +1.519 |
Neg logit contributions | |
APH | -2.786 |
xual | -2.483 |
ray | -2.441 |
Pyro | -2.409 |
� | -2.391 |
Token | � |
Token ID | 447 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
idth | +3.865 |
psey | +2.927 |
Spoiler | +2.581 |
ento | +2.383 |
uning | +2.381 |
Neg logit contributions | |
APH | -4.942 |
Pyro | -4.448 |
ray | -4.380 |
xual | -4.295 |
� | -4.252 |
Token | � |
Token ID | 247 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
idth | +1.258 |
psey | +0.988 |
Spoiler | +0.940 |
uning | +0.889 |
aunch | +0.879 |
Neg logit contributions | |
APH | -0.981 |
Pyro | -0.879 |
ray | -0.864 |
experien | -0.844 |
BuyableInstoreAndOnline | -0.839 |
Token | s |
Token ID | 82 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
APH | +0.380 |
Pyro | +0.342 |
ray | +0.335 |
� | +0.327 |
experien | +0.319 |
Neg logit contributions | |
idth | -0.410 |
psey | -0.312 |
Spoiler | -0.286 |
ento | -0.270 |
aunch | -0.264 |
Token | third |
Token ID | 2368 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
idth | +4.219 |
psey | +3.208 |
Spoiler | +3.023 |
aunch | +2.705 |
uning | +2.629 |
Neg logit contributions | |
APH | -4.875 |
xual | -4.339 |
Pyro | -4.212 |
ray | -4.185 |
� | -4.108 |
Token | Stanley |
Token ID | 14167 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
idth | +9.424 |
psey | +6.972 |
Spoiler | +6.868 |
peat | +6.239 |
uning | +6.155 |
Neg logit contributions | |
APH | -10.372 |
xual | -10.058 |
ray | -9.273 |
Pyro | -9.109 |
experien | -8.995 |
Token | Cup |
Token ID | 5454 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
idth | +1.382 |
psey | +1.054 |
Spoiler | +1.039 |
ento | +0.922 |
aunch | +0.917 |
Neg logit contributions | |
APH | -1.198 |
Pyro | -1.050 |
ray | -1.048 |
xual | -1.040 |
experien | -1.031 |
Token | championship |
Token ID | 12184 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
idth | +4.982 |
psey | +3.759 |
Spoiler | +3.651 |
aunch | +3.199 |
ento | +3.148 |
Neg logit contributions | |
APH | -5.747 |
Pyro | -5.125 |
xual | -5.047 |
ray | -5.041 |
experien | -4.821 |
Token | in |
Token ID | 287 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
idth | +1.870 |
psey | +1.420 |
Spoiler | +1.332 |
ento | +1.204 |
aunch | +1.171 |
Neg logit contributions | |
APH | -1.959 |
Pyro | -1.776 |
ray | -1.749 |
xual | -1.708 |
� | -1.673 |
Token | 2003 |
Token ID | 5816 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
idth | +1.427 |
psey | +1.028 |
Spoiler | +0.993 |
aunch | +0.864 |
ento | +0.862 |
Neg logit contributions | |
APH | -1.675 |
ray | -1.464 |
xual | -1.451 |
� | -1.445 |
Pyro | -1.443 |
Token | one |
Token ID | 530 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
idth | +2.247 |
psey | +1.591 |
Spoiler | +1.534 |
ento | +1.345 |
uning | +1.322 |
Neg logit contributions | |
APH | -2.749 |
� | -2.424 |
ray | -2.423 |
Pyro | -2.411 |
者 | -2.374 |
Token | which |
Token ID | 543 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
idth | +0.817 |
psey | +0.573 |
Spoiler | +0.556 |
ento | +0.499 |
uning | +0.480 |
Neg logit contributions | |
APH | -0.963 |
Pyro | -0.858 |
ray | -0.849 |
� | -0.843 |
BuyableInstoreAndOnline | -0.830 |
Token | is |
Token ID | 318 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
idth | +0.308 |
psey | +0.216 |
Spoiler | +0.214 |
ento | +0.190 |
uning | +0.187 |
Neg logit contributions | |
APH | -0.369 |
ray | -0.327 |
Pyro | -0.322 |
� | -0.322 |
者 | -0.312 |
Token | a |
Token ID | 257 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
idth | +1.855 |
psey | +1.340 |
Spoiler | +1.268 |
ento | +1.159 |
uning | +1.134 |
Neg logit contributions | |
APH | -2.146 |
ray | -1.926 |
� | -1.906 |
Pyro | -1.901 |
xual | -1.861 |
Token | super |
Token ID | 2208 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
idth | +2.032 |
psey | +1.535 |
Spoiler | +1.456 |
ento | +1.311 |
aah | +1.283 |
Neg logit contributions | |
APH | -1.946 |
� | -1.706 |
ray | -1.702 |
Pyro | -1.679 |
xual | -1.630 |
Token | higher |
Token ID | 2440 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
idth | +5.766 |
psey | +4.224 |
Spoiler | +3.890 |
avis | +3.636 |
ento | +3.515 |
Neg logit contributions | |
APH | -5.640 |
Pyro | -5.146 |
� | -5.046 |
xual | -5.044 |
ray | -5.000 |
Token | resolution |
Token ID | 6323 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
idth | +7.718 |
psey | +5.346 |
Spoiler | +5.090 |
ento | +4.251 |
uning | +4.185 |
Neg logit contributions | |
APH | -12.071 |
Pyro | -10.894 |
ray | -10.715 |
� | -10.704 |
BuyableInstoreAndOnline | -10.703 |
Token | that |
Token ID | 326 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
idth | +3.112 |
psey | +2.237 |
Spoiler | +2.166 |
ento | +1.886 |
uning | +1.864 |
Neg logit contributions | |
APH | -3.546 |
Pyro | -3.148 |
ray | -3.135 |
BuyableInstoreAndOnline | -3.092 |
� | -3.073 |
Token | I |
Token ID | 314 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
idth | +0.656 |
psey | +0.463 |
Spoiler | +0.457 |
ento | +0.408 |
uning | +0.397 |
Neg logit contributions | |
APH | -0.745 |
ray | -0.661 |
Pyro | -0.653 |
� | -0.648 |
者 | -0.630 |
Token | effectively |
Token ID | 6840 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
idth | +0.913 |
psey | +0.682 |
Spoiler | +0.632 |
ento | +0.585 |
clicked | +0.580 |
Neg logit contributions | |
APH | -1.047 |
ray | -0.925 |
Pyro | -0.921 |
� | -0.917 |
�醒 | -0.903 |
Token | can |
Token ID | 460 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
APH | +4.890 |
Pyro | +4.388 |
ray | +4.385 |
� | +4.271 |
ax | +4.127 |
Neg logit contributions | |
idth | -4.794 |
psey | -3.568 |
Spoiler | -3.291 |
ento | -3.064 |
uning | -2.947 |
Token | on |
Token ID | 319 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
idth | +1.654 |
psey | +1.203 |
Spoiler | +1.133 |
ento | +1.029 |
aunch | +1.001 |
Neg logit contributions | |
APH | -2.031 |
Pyro | -1.824 |
ray | -1.786 |
experien | -1.753 |
Skydragon | -1.730 |
Token | why |
Token ID | 1521 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
idth | +1.400 |
psey | +1.048 |
Spoiler | +0.987 |
ento | +0.893 |
aunch | +0.840 |
Neg logit contributions | |
APH | -1.735 |
ray | -1.526 |
� | -1.492 |
Pyro | -1.490 |
xual | -1.443 |
Token | I |
Token ID | 314 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
idth | +1.535 |
psey | +1.126 |
Spoiler | +1.077 |
ento | +0.953 |
aunch | +0.909 |
Neg logit contributions | |
APH | -1.776 |
ray | -1.546 |
Pyro | -1.540 |
� | -1.512 |
xual | -1.483 |
Token | think |
Token ID | 892 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
idth | +2.265 |
psey | +1.650 |
Spoiler | +1.515 |
ento | +1.408 |
clicked | +1.355 |
Neg logit contributions | |
APH | -2.797 |
Pyro | -2.551 |
Skydragon | -2.466 |
ray | -2.463 |
BuyableInstoreAndOnline | -2.408 |
Token | Phil |
Token ID | 4543 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
APH | +0.806 |
Pyro | +0.712 |
ray | +0.711 |
� | +0.696 |
xual | +0.674 |
Neg logit contributions | |
idth | -0.724 |
psey | -0.534 |
Spoiler | -0.505 |
ento | -0.459 |
aunch | -0.438 |
Token | K |
Token ID | 509 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
idth | +5.165 |
psey | +3.946 |
Spoiler | +3.563 |
ento | +3.381 |
uning | +3.160 |
Neg logit contributions | |
APH | -5.174 |
ray | -4.730 |
xual | -4.705 |
Pyro | -4.556 |
BuyableInstoreAndOnline | -4.350 |
Token | essel |
Token ID | 7878 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
idth | +6.077 |
psey | +3.240 |
avis | +2.269 |
Spoiler | +2.000 |
uning | +1.831 |
Neg logit contributions | |
APH | -14.612 |
BuyableInstoreAndOnline | -13.833 |
Cyrus | -13.552 |
Pyro | -13.538 |
Skydragon | -13.475 |
Token | was |
Token ID | 373 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
idth | +0.776 |
psey | +0.569 |
Spoiler | +0.533 |
ento | +0.486 |
uning | +0.466 |
Neg logit contributions | |
APH | -0.867 |
Pyro | -0.775 |
ray | -0.758 |
experien | -0.734 |
� | -0.733 |
Token | sn |
Token ID | 3013 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
idth | +0.288 |
psey | +0.214 |
Spoiler | +0.202 |
ento | +0.183 |
avis | +0.176 |
Neg logit contributions | |
APH | -0.369 |
Pyro | -0.328 |
ray | -0.326 |
� | -0.318 |
xual | -0.315 |
Token | ub |
Token ID | 549 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
idth | +4.354 |
psey | +3.102 |
ento | +2.675 |
Spoiler | +2.608 |
aunch | +2.607 |
Neg logit contributions | |
APH | -5.948 |
Pyro | -5.398 |
experien | -5.339 |
� | -5.206 |
xual | -5.179 |
Token | bed |
Token ID | 3077 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
idth | +1.295 |
psey | +1.024 |
Spoiler | +0.936 |
ento | +0.878 |
uning | +0.848 |
Neg logit contributions | |
APH | -1.145 |
Pyro | -0.999 |
ray | -0.981 |
experien | -0.954 |
xual | -0.933 |
Token |
|
Token ID | 198 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
idth | +1.639 |
Spoiler | +1.212 |
psey | +0.993 |
ento | +0.973 |
avis | +0.962 |
Neg logit contributions | |
APH | -2.638 |
experien | -2.505 |
thous | -2.501 |
exha | -2.476 |
xual | -2.472 |
Token | Are |
Token ID | 8491 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
idth | +2.263 |
psey | +1.661 |
Spoiler | +1.624 |
ento | +1.474 |
aunch | +1.467 |
Neg logit contributions | |
APH | -2.142 |
Pyro | -2.068 |
experien | -2.019 |
xual | -2.016 |
ray | -1.921 |
Token | you |
Token ID | 345 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
idth | +2.302 |
psey | +1.677 |
Spoiler | +1.570 |
ento | +1.403 |
aunch | +1.347 |
Neg logit contributions | |
APH | -2.666 |
Pyro | -2.382 |
� | -2.370 |
ray | -2.367 |
experien | -2.323 |
Token | subscribed |
Token ID | 45794 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
idth | +1.836 |
psey | +1.361 |
Spoiler | +1.285 |
ento | +1.140 |
aunch | +1.109 |
Neg logit contributions | |
APH | -2.278 |
ray | -2.048 |
Pyro | -2.003 |
� | -1.977 |
者 | -1.963 |
Token | to |
Token ID | 284 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
APH | +1.393 |
Pyro | +1.260 |
ray | +1.251 |
� | +1.226 |
experien | +1.167 |
Neg logit contributions | |
idth | -1.637 |
psey | -1.247 |
Spoiler | -1.142 |
ento | -1.087 |
aunch | -1.043 |
Token | The |
Token ID | 383 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
idth | +5.091 |
psey | +3.789 |
Spoiler | +3.778 |
ento | +3.184 |
aunch | +3.142 |
Neg logit contributions | |
APH | -5.657 |
Pyro | -5.068 |
ray | -5.046 |
� | -4.987 |
xual | -4.941 |
Token | Sch |
Token ID | 3059 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
idth | +10.975 |
Spoiler | +8.703 |
psey | +8.062 |
avis | +7.199 |
ento | +7.165 |
Neg logit contributions | |
APH | -8.932 |
xual | -8.179 |
ray | -8.110 |
experien | -7.975 |
ゴ | -7.773 |
Token | m |
Token ID | 76 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
APH | +1.529 |
ray | +1.439 |
Pyro | +1.393 |
� | +1.344 |
ax | +1.341 |
Neg logit contributions | |
idth | -2.419 |
psey | -1.916 |
Spoiler | -1.766 |
ento | -1.666 |
uning | -1.623 |
Token | oes |
Token ID | 3028 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
APH | +2.433 |
Pyro | +2.144 |
ray | +2.132 |
experien | +2.077 |
� | +2.072 |
Neg logit contributions | |
idth | -2.368 |
psey | -1.710 |
Spoiler | -1.577 |
ento | -1.519 |
avis | -1.467 |
Token | on |
Token ID | 319 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
idth | +6.129 |
Spoiler | +4.665 |
psey | +4.577 |
aunch | +4.112 |
ento | +4.053 |
Neg logit contributions | |
APH | -4.655 |
Pyro | -4.033 |
ray | -4.028 |
xual | -3.863 |
experien | -3.836 |
Token | Youtube |
Token ID | 27431 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
APH | +0.768 |
ray | +0.684 |
Pyro | +0.683 |
� | +0.659 |
experien | +0.649 |
Neg logit contributions | |
idth | -0.811 |
psey | -0.607 |
Spoiler | -0.575 |
ento | -0.528 |
aunch | -0.513 |
Token | , |
Token ID | 11 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
idth | +2.859 |
psey | +2.148 |
Spoiler | +2.002 |
ento | +1.806 |
avis | +1.767 |
Neg logit contributions | |
APH | -3.313 |
Pyro | -2.997 |
ray | -2.966 |
� | -2.878 |
experien | -2.838 |
Token | to |
Token ID | 284 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
APH | +0.801 |
ray | +0.723 |
Pyro | +0.717 |
� | +0.705 |
xual | +0.680 |
Neg logit contributions | |
idth | -0.715 |
psey | -0.534 |
Spoiler | -0.498 |
ento | -0.450 |
aunch | -0.430 |
Token | O |
Token ID | 440 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
idth | +1.781 |
psey | +1.348 |
Spoiler | +1.228 |
ento | +1.137 |
aunch | +1.089 |
Neg logit contributions | |
APH | -1.986 |
� | -1.805 |
Pyro | -1.772 |
ray | -1.754 |
xual | -1.718 |
Token | ' |
Token ID | 6 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
APH | +3.839 |
Pyro | +3.544 |
experien | +3.421 |
ray | +3.382 |
� | +3.369 |
Neg logit contributions | |
idth | -3.538 |
psey | -2.619 |
Spoiler | -2.337 |
ento | -2.251 |
aunch | -2.219 |
Token | Neill |
Token ID | 26538 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
APH | +0.866 |
Pyro | +0.802 |
xual | +0.799 |
Skydragon | +0.779 |
experien | +0.777 |
Neg logit contributions | |
idth | -0.553 |
psey | -0.384 |
Spoiler | -0.348 |
uning | -0.320 |
ento | -0.317 |
Token | 's |
Token ID | 338 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
idth | +3.114 |
psey | +2.297 |
Spoiler | +2.166 |
ento | +1.917 |
uning | +1.859 |
Neg logit contributions | |
APH | -4.189 |
Pyro | -3.731 |
ray | -3.695 |
� | -3.579 |
xual | -3.575 |
Token | open |
Token ID | 1280 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
idth | +7.983 |
psey | +6.123 |
Spoiler | +5.539 |
enchanted | +5.418 |
assumed | +5.308 |
Neg logit contributions | |
APH | -11.135 |
xual | -9.774 |
�醒 | -9.623 |
� | -9.602 |
ray | -9.422 |
Token | - |
Token ID | 12 |
Feature activation | -3.52e-04 |
Pos logit contributions | |
idth | +3.270 |
psey | +2.476 |
Spoiler | +2.272 |
ento | +2.207 |
uning | +2.095 |
Neg logit contributions | |
APH | -3.464 |
ray | -2.989 |
� | -2.972 |
Pyro | -2.970 |
xual | -2.966 |
Token | j |
Token ID | 73 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
APH | +0.004 |
Pyro | +0.004 |
ray | +0.004 |
experien | +0.004 |
� | +0.004 |
Neg logit contributions | |
idth | -0.004 |
psey | -0.003 |
Spoiler | -0.003 |
ento | -0.003 |
uning | -0.003 |
Token | awed |
Token ID | 36825 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
idth | +1.989 |
psey | +1.377 |
ento | +1.205 |
Spoiler | +1.199 |
aunch | +1.141 |
Neg logit contributions | |
APH | -2.731 |
Pyro | -2.528 |
� | -2.466 |
ray | -2.388 |
experien | -2.377 |
Token | amaz |
Token ID | 40642 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
idth | +5.572 |
psey | +4.347 |
Spoiler | +4.089 |
ento | +3.740 |
Flores | +3.691 |
Neg logit contributions | |
APH | -6.254 |
xual | -5.479 |
ray | -5.475 |
� | -5.396 |
Pyro | -5.253 |
Token | ative |
Token ID | 876 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
idth | +0.747 |
psey | +0.557 |
Spoiler | +0.514 |
ento | +0.481 |
aunch | +0.472 |
Neg logit contributions | |
APH | -0.685 |
Pyro | -0.612 |
ray | -0.606 |
� | -0.592 |
experien | -0.584 |
Token | forcing |
Token ID | 10833 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
idth | +4.460 |
Spoiler | +3.042 |
psey | +3.033 |
uning | +2.683 |
assumed | +2.596 |
Neg logit contributions | |
APH | -5.903 |
� | -5.022 |
ray | -4.967 |
xual | -4.934 |
Pyro | -4.917 |
Token | Δ |
Token ID | 37455 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
idth | +0.400 |
psey | +0.288 |
Spoiler | +0.277 |
ento | +0.252 |
uning | +0.248 |
Neg logit contributions | |
APH | -0.420 |
ray | -0.367 |
Pyro | -0.361 |
� | -0.356 |
experien | -0.348 |
Token | F |
Token ID | 37 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
idth | +5.762 |
psey | +4.134 |
Spoiler | +3.983 |
uning | +3.782 |
ento | +3.654 |
Neg logit contributions | |
APH | -5.417 |
Pyro | -4.778 |
experien | -4.777 |
Cyrus | -4.690 |
xual | -4.571 |
Token | 2 |
Token ID | 362 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
idth | +6.026 |
psey | +4.285 |
Spoiler | +4.038 |
ento | +3.903 |
uning | +3.808 |
Neg logit contributions | |
APH | -6.097 |
Cyrus | -5.437 |
Pyro | -5.381 |
experien | -5.342 |
者 | -5.260 |
Token | x |
Token ID | 87 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
idth | +8.410 |
psey | +5.918 |
Spoiler | +5.792 |
uning | +5.166 |
avis | +5.019 |
Neg logit contributions | |
APH | -9.168 |
ray | -8.025 |
experien | -7.973 |
Pyro | -7.878 |
者 | -7.840 |
Token | = |
Token ID | 796 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
idth | +9.292 |
psey | +6.352 |
Spoiler | +6.282 |
assumed | +5.896 |
uning | +5.855 |
Neg logit contributions | |
APH | -10.042 |
Pyro | -8.704 |
experien | -8.623 |
Cyrus | -8.594 |
BuyableInstoreAndOnline | -8.539 |
Token | 5 |
Token ID | 642 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
idth | +7.613 |
psey | +5.447 |
Spoiler | +5.209 |
uning | +4.767 |
avis | +4.672 |
Neg logit contributions | |
APH | -7.552 |
Pyro | -6.540 |
者 | -6.483 |
ray | -6.479 |
experien | -6.435 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
idth | +3.606 |
psey | +2.664 |
Spoiler | +2.522 |
ento | +2.356 |
uning | +2.317 |
Neg logit contributions | |
APH | -3.278 |
Pyro | -2.880 |
ray | -2.837 |
experien | -2.808 |
xual | -2.786 |
Token | 35 |
Token ID | 2327 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
idth | +2.556 |
Spoiler | +1.762 |
psey | +1.679 |
ento | +1.523 |
uning | +1.516 |
Neg logit contributions | |
APH | -3.015 |
experien | -2.764 |
ray | -2.745 |
Pyro | -2.702 |
xual | -2.665 |
Token | l |
Token ID | 300 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
idth | +3.652 |
psey | +2.732 |
Spoiler | +2.584 |
uning | +2.385 |
ento | +2.379 |
Neg logit contributions | |
APH | -3.152 |
Pyro | -2.720 |
ray | -2.691 |
experien | -2.687 |
xual | -2.640 |
Token | high |
Token ID | 8929 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
idth | +4.933 |
psey | +3.631 |
Spoiler | +3.445 |
ento | +3.161 |
avis | +3.088 |
Neg logit contributions | |
APH | -4.812 |
Pyro | -4.434 |
experien | -4.241 |
ray | -4.154 |
� | -4.144 |
Token | resolution |
Token ID | 6323 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
idth | +4.055 |
psey | +2.955 |
Spoiler | +2.684 |
ento | +2.503 |
uning | +2.391 |
Neg logit contributions | |
APH | -4.552 |
Pyro | -4.132 |
ray | -4.129 |
� | -4.011 |
experien | -3.904 |
Token | no |
Token ID | 645 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
idth | +5.112 |
psey | +3.675 |
Spoiler | +3.521 |
ento | +3.121 |
uning | +3.092 |
Neg logit contributions | |
APH | -5.318 |
Pyro | -4.798 |
ray | -4.756 |
� | -4.674 |
experien | -4.556 |
Token | j |
Token ID | 474 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
idth | +8.346 |
psey | +6.275 |
Spoiler | +6.052 |
clicked | +5.403 |
aah | +5.324 |
Neg logit contributions | |
APH | -7.590 |
� | -6.704 |
Pyro | -6.610 |
xual | -6.432 |
ray | -6.401 |
Token | agg |
Token ID | 9460 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
APH | +0.186 |
Pyro | +0.171 |
� | +0.163 |
ray | +0.162 |
experien | +0.161 |
Neg logit contributions | |
idth | -0.193 |
psey | -0.143 |
Spoiler | -0.128 |
ento | -0.125 |
avis | -0.124 |
Token | ies |
Token ID | 444 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
idth | +1.803 |
psey | +1.038 |
Spoiler | +0.940 |
ento | +0.879 |
uning | +0.803 |
Neg logit contributions | |
APH | -3.301 |
BuyableInstoreAndOnline | -3.011 |
Pyro | -2.983 |
experien | -2.952 |
Skydragon | -2.951 |
Token | but |
Token ID | 475 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
idth | +9.095 |
psey | +6.428 |
Spoiler | +6.191 |
clicked | +5.318 |
ento | +5.316 |
Neg logit contributions | |
APH | -10.162 |
Pyro | -9.137 |
BuyableInstoreAndOnline | -8.954 |
ray | -8.896 |
� | -8.762 |
Token | screen |
Token ID | 3159 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
idth | +4.063 |
Spoiler | +2.860 |
psey | +2.852 |
clicked | +2.402 |
ento | +2.389 |
Neg logit contributions | |
APH | -4.709 |
� | -4.168 |
Pyro | -4.116 |
BuyableInstoreAndOnline | -4.103 |
ray | -4.074 |
Token | door |
Token ID | 3420 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
idth | +4.617 |
psey | +3.713 |
Spoiler | +3.434 |
ento | +3.299 |
aunch | +3.240 |
Neg logit contributions | |
APH | -2.626 |
ray | -2.313 |
Pyro | -2.303 |
� | -2.195 |
ax | -2.123 |
Token | effect |
Token ID | 1245 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
idth | +4.210 |
psey | +2.924 |
Spoiler | +2.666 |
ento | +2.436 |
uning | +2.320 |
Neg logit contributions | |
APH | -5.625 |
Pyro | -5.125 |
ray | -5.122 |
� | -4.985 |
experien | -4.859 |
Token | " |
Token ID | 1 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
idth | +5.581 |
psey | +3.969 |
Spoiler | +3.885 |
ento | +3.438 |
uning | +3.357 |
Neg logit contributions | |
APH | -5.869 |
Pyro | -5.314 |
ray | -5.183 |
Cyrus | -5.038 |
experien | -4.982 |
Token | t |
Token ID | 83 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
idth | +0.548 |
psey | +0.417 |
Spoiler | +0.379 |
ento | +0.371 |
aunch | +0.355 |
Neg logit contributions | |
APH | -0.477 |
Pyro | -0.427 |
ray | -0.409 |
� | -0.400 |
experien | -0.395 |
Token | got |
Token ID | 1392 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
idth | +0.794 |
psey | +0.553 |
Spoiler | +0.499 |
ento | +0.470 |
uning | +0.446 |
Neg logit contributions | |
APH | -1.163 |
Pyro | -1.043 |
ray | -1.034 |
� | -1.014 |
xual | -0.992 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
idth | +0.776 |
psey | +0.542 |
Spoiler | +0.510 |
ento | +0.460 |
uning | +0.441 |
Neg logit contributions | |
APH | -0.965 |
ray | -0.874 |
Pyro | -0.858 |
� | -0.833 |
xual | -0.823 |
Token | refugee |
Token ID | 12540 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
APH | +1.969 |
ray | +1.753 |
Pyro | +1.747 |
� | +1.680 |
experien | +1.653 |
Neg logit contributions | |
idth | -2.032 |
psey | -1.537 |
Spoiler | -1.427 |
ento | -1.330 |
uning | -1.278 |
Token | crisis |
Token ID | 4902 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
idth | +1.287 |
psey | +0.987 |
Spoiler | +0.925 |
uning | +0.844 |
ento | +0.835 |
Neg logit contributions | |
APH | -1.141 |
ray | -0.996 |
xual | -0.983 |
Pyro | -0.981 |
� | -0.961 |
Token | under |
Token ID | 739 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
idth | +2.722 |
psey | +1.999 |
Spoiler | +1.915 |
ento | +1.725 |
clicked | +1.651 |
Neg logit contributions | |
APH | -3.638 |
ray | -3.277 |
Pyro | -3.259 |
xual | -3.229 |
BuyableInstoreAndOnline | -3.124 |
Token | control |
Token ID | 1630 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
idth | +7.161 |
Spoiler | +4.579 |
psey | +4.271 |
uning | +3.685 |
ento | +3.552 |
Neg logit contributions | |
APH | -12.322 |
ray | -11.001 |
VIDEOS | -10.940 |
xual | -10.730 |
Pyro | -10.719 |
Token | on |
Token ID | 319 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
idth | +4.630 |
psey | +3.349 |
Spoiler | +3.203 |
ento | +2.859 |
uning | +2.781 |
Neg logit contributions | |
APH | -5.325 |
Pyro | -4.766 |
ray | -4.758 |
experien | -4.627 |
BuyableInstoreAndOnline | -4.581 |
Token | a |
Token ID | 257 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
idth | +2.858 |
psey | +1.996 |
Spoiler | +1.942 |
aunch | +1.723 |
uning | +1.705 |
Neg logit contributions | |
APH | -3.179 |
ray | -2.903 |
Pyro | -2.794 |
experien | -2.746 |
xual | -2.705 |
Token | European |
Token ID | 3427 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
idth | +4.121 |
psey | +2.961 |
Spoiler | +2.884 |
uning | +2.552 |
ento | +2.523 |
Neg logit contributions | |
APH | -4.420 |
ray | -4.024 |
� | -3.874 |
Pyro | -3.840 |
者 | -3.834 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
idth | +2.644 |
psey | +1.907 |
Spoiler | +1.828 |
uning | +1.674 |
avis | +1.635 |
Neg logit contributions | |
APH | -2.636 |
ray | -2.358 |
Pyro | -2.307 |
xual | -2.286 |
� | -2.227 |
Token | , |
Token ID | 11 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
APH | +3.089 |
Pyro | +2.780 |
ray | +2.759 |
� | +2.684 |
experien | +2.635 |
Neg logit contributions | |
idth | -2.814 |
psey | -2.096 |
Spoiler | -1.934 |
ento | -1.785 |
aunch | -1.710 |
Token | for |
Token ID | 329 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
APH | +0.733 |
ray | +0.663 |
Pyro | +0.662 |
� | +0.633 |
experien | +0.626 |
Neg logit contributions | |
idth | -0.655 |
psey | -0.486 |
Spoiler | -0.455 |
ento | -0.411 |
uning | -0.397 |
Token | backing |
Token ID | 12285 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
APH | +2.382 |
Pyro | +2.150 |
ray | +2.139 |
� | +2.073 |
ax | +2.032 |
Neg logit contributions | |
idth | -1.962 |
psey | -1.428 |
Spoiler | -1.298 |
ento | -1.201 |
uning | -1.161 |
Token | some |
Token ID | 617 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
APH | +0.479 |
Pyro | +0.428 |
ray | +0.425 |
� | +0.414 |
experien | +0.409 |
Neg logit contributions | |
idth | -0.445 |
psey | -0.326 |
Spoiler | -0.307 |
ento | -0.283 |
aunch | -0.273 |
Token | qu |
Token ID | 627 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
APH | +3.409 |
Pyro | +3.050 |
ray | +3.037 |
� | +2.937 |
experien | +2.859 |
Neg logit contributions | |
idth | -3.639 |
psey | -2.748 |
Spoiler | -2.555 |
ento | -2.377 |
aunch | -2.294 |
Token | ix |
Token ID | 844 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
idth | +3.336 |
psey | +2.519 |
Spoiler | +2.194 |
ento | +2.184 |
uning | +2.113 |
Neg logit contributions | |
APH | -3.307 |
Pyro | -2.940 |
experien | -2.832 |
� | -2.787 |
ray | -2.772 |
Token | otic |
Token ID | 6210 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
idth | +8.015 |
psey | +5.536 |
Spoiler | +4.978 |
ento | +4.653 |
uning | +4.417 |
Neg logit contributions | |
APH | -11.937 |
Pyro | -11.105 |
ray | -10.737 |
experien | -10.610 |
Cyrus | -10.543 |
Token | third |
Token ID | 2368 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
idth | +0.828 |
psey | +0.610 |
Spoiler | +0.587 |
ento | +0.535 |
aunch | +0.521 |
Neg logit contributions | |
APH | -0.854 |
ray | -0.749 |
Pyro | -0.741 |
� | -0.723 |
xual | -0.719 |
Token | - |
Token ID | 12 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
idth | +0.820 |
psey | +0.630 |
Spoiler | +0.600 |
ento | +0.548 |
uning | +0.543 |
Neg logit contributions | |
APH | -0.685 |
Pyro | -0.600 |
ray | -0.595 |
� | -0.582 |
experien | -0.563 |
Token | party |
Token ID | 10608 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
idth | +2.609 |
psey | +1.959 |
Spoiler | +1.828 |
ento | +1.687 |
uning | +1.655 |
Neg logit contributions | |
APH | -2.545 |
Pyro | -2.274 |
� | -2.185 |
ray | -2.170 |
experien | -2.142 |
Token | candidate |
Token ID | 4540 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
idth | +2.080 |
psey | +1.538 |
Spoiler | +1.477 |
ento | +1.306 |
aunch | +1.290 |
Neg logit contributions | |
APH | -2.540 |
Pyro | -2.234 |
ray | -2.189 |
xual | -2.168 |
� | -2.161 |
Token | texting |
Token ID | 36634 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
idth | +2.772 |
psey | +1.971 |
Spoiler | +1.849 |
ento | +1.641 |
uning | +1.607 |
Neg logit contributions | |
APH | -3.620 |
ray | -3.194 |
Pyro | -3.144 |
xual | -3.111 |
� | -3.105 |
Token | on |
Token ID | 319 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
idth | +3.084 |
psey | +2.213 |
Spoiler | +2.165 |
ento | +1.922 |
avis | +1.831 |
Neg logit contributions | |
APH | -3.968 |
ray | -3.531 |
Pyro | -3.518 |
xual | -3.461 |
BuyableInstoreAndOnline | -3.417 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
idth | +2.689 |
psey | +1.937 |
Spoiler | +1.820 |
ento | +1.613 |
uning | +1.604 |
Neg logit contributions | |
APH | -3.068 |
ray | -2.715 |
xual | -2.682 |
Pyro | -2.666 |
� | -2.662 |
Token | smart |
Token ID | 4451 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
idth | +1.820 |
psey | +1.358 |
Spoiler | +1.278 |
ento | +1.162 |
uning | +1.140 |
Neg logit contributions | |
APH | -1.945 |
Pyro | -1.680 |
ray | -1.678 |
xual | -1.674 |
� | -1.665 |
Token | phone |
Token ID | 3072 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
idth | +3.338 |
psey | +2.137 |
Spoiler | +2.137 |
ento | +1.899 |
avis | +1.783 |
Neg logit contributions | |
APH | -4.625 |
xual | -4.245 |
Pyro | -4.212 |
experien | -4.065 |
� | -4.041 |
Token | in |
Token ID | 287 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
idth | +3.622 |
psey | +2.644 |
Spoiler | +2.547 |
ento | +2.217 |
aunch | +2.172 |
Neg logit contributions | |
APH | -4.595 |
Pyro | -4.102 |
ray | -4.039 |
xual | -3.996 |
BuyableInstoreAndOnline | -3.970 |
Token | downtown |
Token ID | 9436 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
idth | +8.867 |
psey | +6.400 |
Spoiler | +6.162 |
avis | +5.369 |
ento | +5.346 |
Neg logit contributions | |
APH | -10.512 |
xual | -9.428 |
ray | -9.185 |
� | -9.041 |
者 | -9.012 |
Token | Toronto |
Token ID | 6586 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
idth | +2.883 |
psey | +2.161 |
Spoiler | +2.048 |
ento | +1.885 |
avis | +1.840 |
Neg logit contributions | |
APH | -2.609 |
ray | -2.279 |
Pyro | -2.257 |
� | -2.205 |
xual | -2.203 |
Token | on |
Token ID | 319 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
APH | +0.458 |
Pyro | +0.412 |
ray | +0.406 |
experien | +0.393 |
� | +0.392 |
Neg logit contributions | |
idth | -0.436 |
psey | -0.323 |
Spoiler | -0.305 |
ento | -0.279 |
uning | -0.271 |
Token | Monday |
Token ID | 3321 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
idth | +2.397 |
psey | +1.711 |
Spoiler | +1.705 |
uning | +1.489 |
avis | +1.470 |
Neg logit contributions | |
APH | -2.581 |
ray | -2.241 |
� | -2.199 |
xual | -2.198 |
Pyro | -2.178 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
APH | +1.265 |
Pyro | +1.135 |
ray | +1.128 |
� | +1.082 |
experien | +1.075 |
Neg logit contributions | |
idth | -1.312 |
psey | -0.973 |
Spoiler | -0.908 |
ento | -0.850 |
uning | -0.820 |
Token | least |
Token ID | 1551 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
APH | +0.702 |
Pyro | +0.636 |
ray | +0.629 |
� | +0.622 |
experien | +0.603 |
Neg logit contributions | |
idth | -0.571 |
psey | -0.407 |
Spoiler | -0.370 |
ento | -0.341 |
uning | -0.331 |
Token | interfering |
Token ID | 32874 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
idth | +5.163 |
psey | +3.436 |
Spoiler | +3.334 |
uning | +2.988 |
assumed | +2.866 |
Neg logit contributions | |
APH | -7.873 |
�醒 | -7.013 |
ray | -7.001 |
者 | -6.871 |
BuyableInstoreAndOnline | -6.808 |
Token | with |
Token ID | 351 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
idth | +2.662 |
psey | +1.940 |
Spoiler | +1.857 |
ento | +1.674 |
avis | +1.664 |
Neg logit contributions | |
APH | -2.951 |
ray | -2.642 |
Pyro | -2.625 |
� | -2.540 |
xual | -2.508 |
Token | spells |
Token ID | 10377 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
idth | +1.911 |
psey | +1.367 |
Spoiler | +1.300 |
ento | +1.150 |
avis | +1.139 |
Neg logit contributions | |
APH | -2.316 |
ray | -2.043 |
Pyro | -2.000 |
� | -1.988 |
xual | -1.972 |
Token | of |
Token ID | 286 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
idth | +2.676 |
psey | +1.896 |
Spoiler | +1.853 |
uning | +1.626 |
avis | +1.625 |
Neg logit contributions | |
APH | -3.361 |
Pyro | -2.965 |
ray | -2.930 |
� | -2.913 |
BuyableInstoreAndOnline | -2.894 |
Token | this |
Token ID | 428 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
idth | +6.590 |
Spoiler | +4.266 |
psey | +4.262 |
Flores | +3.873 |
enchanted | +3.856 |
Neg logit contributions | |
APH | -9.366 |
�醒 | -8.334 |
ray | -8.219 |
� | -8.206 |
xual | -8.160 |
Token | caliber |
Token ID | 28139 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
idth | +8.178 |
psey | +5.913 |
Spoiler | +5.659 |
enchanted | +5.102 |
assumed | +5.100 |
Neg logit contributions | |
APH | -10.544 |
�醒 | -9.386 |
ray | -9.175 |
xual | -9.172 |
VIDEOS | -9.027 |
Token | in |
Token ID | 287 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
idth | +3.794 |
psey | +2.747 |
Spoiler | +2.599 |
uning | +2.325 |
avis | +2.307 |
Neg logit contributions | |
APH | -4.552 |
Pyro | -4.126 |
BuyableInstoreAndOnline | -4.054 |
ray | -4.045 |
� | -3.999 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
idth | +0.784 |
psey | +0.557 |
Spoiler | +0.520 |
ento | +0.464 |
avis | +0.461 |
Neg logit contributions | |
APH | -0.940 |
ray | -0.842 |
Pyro | -0.830 |
� | -0.829 |
xual | -0.801 |
Token | distant |
Token ID | 12899 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
idth | +1.899 |
psey | +1.367 |
Spoiler | +1.304 |
ento | +1.153 |
Flores | +1.114 |
Neg logit contributions | |
APH | -2.478 |
� | -2.186 |
ray | -2.182 |
xual | -2.127 |
Pyro | -2.122 |
Token | past |
Token ID | 1613 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
APH | +0.284 |
ray | +0.254 |
Pyro | +0.252 |
� | +0.250 |
xual | +0.242 |
Neg logit contributions | |
idth | -0.237 |
psey | -0.176 |
Spoiler | -0.161 |
ento | -0.147 |
uning | -0.141 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
idth | +1.003 |
psey | +0.745 |
Spoiler | +0.694 |
ento | +0.637 |
uning | +0.613 |
Neg logit contributions | |
APH | -1.071 |
Pyro | -0.969 |
ray | -0.965 |
� | -0.934 |
experien | -0.926 |
Token |
|
Token ID | 198 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
idth | +1.152 |
Spoiler | +0.832 |
psey | +0.726 |
ento | +0.692 |
avis | +0.691 |
Neg logit contributions | |
APH | -1.726 |
experien | -1.624 |
xual | -1.605 |
�醒 | -1.604 |
thous | -1.601 |
Token | 200 |
Token ID | 2167 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
APH | +0.029 |
Pyro | +0.026 |
ray | +0.025 |
experien | +0.025 |
xual | +0.025 |
Neg logit contributions | |
idth | -0.035 |
psey | -0.027 |
Spoiler | -0.025 |
ento | -0.024 |
uning | -0.023 |
Token | Black |
Token ID | 2619 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
idth | +4.619 |
psey | +3.576 |
Spoiler | +3.377 |
uning | +3.098 |
ento | +3.080 |
Neg logit contributions | |
APH | -4.020 |
Pyro | -3.554 |
ray | -3.551 |
experien | -3.483 |
� | -3.455 |
Token | / |
Token ID | 1220 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
idth | +2.463 |
psey | +1.868 |
Spoiler | +1.784 |
ento | +1.667 |
uning | +1.617 |
Neg logit contributions | |
APH | -2.106 |
Pyro | -1.826 |
ray | -1.818 |
� | -1.774 |
experien | -1.770 |
Token | 100 |
Token ID | 1802 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
idth | +2.769 |
psey | +2.097 |
Spoiler | +2.019 |
ento | +1.795 |
uning | +1.778 |
Neg logit contributions | |
APH | -2.692 |
ray | -2.386 |
Pyro | -2.354 |
� | -2.331 |
experien | -2.322 |
Token | Deep |
Token ID | 10766 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
idth | +9.617 |
Spoiler | +7.502 |
psey | +7.289 |
ento | +6.501 |
uning | +6.295 |
Neg logit contributions | |
APH | -9.034 |
experien | -7.808 |
ray | -7.784 |
� | -7.515 |
guiActiveUn | -7.505 |
Token | Purple |
Token ID | 17265 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
idth | +6.349 |
psey | +4.674 |
Spoiler | +4.595 |
ento | +4.074 |
uning | +3.985 |
Neg logit contributions | |
APH | -5.904 |
Pyro | -5.126 |
ray | -5.075 |
experien | -5.072 |
� | -5.060 |
Token | L |
Token ID | 406 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
idth | +2.026 |
psey | +1.519 |
Spoiler | +1.425 |
ento | +1.325 |
uning | +1.270 |
Neg logit contributions | |
APH | -1.969 |
Pyro | -1.751 |
ray | -1.745 |
� | -1.695 |
experien | -1.682 |
Token | Ps |
Token ID | 12016 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
idth | +0.302 |
psey | +0.239 |
Spoiler | +0.225 |
ento | +0.218 |
uning | +0.213 |
Neg logit contributions | |
APH | -0.176 |
Pyro | -0.158 |
ray | -0.152 |
� | -0.149 |
experien | -0.148 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
idth | +3.525 |
psey | +2.702 |
Spoiler | +2.542 |
ento | +2.304 |
uning | +2.208 |
Neg logit contributions | |
APH | -3.862 |
Pyro | -3.446 |
ray | -3.408 |
experien | -3.384 |
xual | -3.328 |
Token | . |
Token ID | 13 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
APH | +1.177 |
Pyro | +1.055 |
ray | +1.054 |
� | +1.021 |
ax | +0.986 |
Neg logit contributions | |
idth | -1.338 |
psey | -1.016 |
Spoiler | -0.935 |
ento | -0.880 |
uning | -0.849 |
Token | Follow |
Token ID | 7281 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
idth | +0.654 |
psey | +0.463 |
Spoiler | +0.448 |
ento | +0.405 |
uning | +0.388 |
Neg logit contributions | |
APH | -0.773 |
ray | -0.698 |
Pyro | -0.696 |
experien | -0.683 |
� | -0.678 |
Token | @ |
Token ID | 2488 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
APH | +0.684 |
ray | +0.615 |
Pyro | +0.613 |
� | +0.596 |
experien | +0.581 |
Neg logit contributions | |
idth | -0.703 |
psey | -0.530 |
Spoiler | -0.494 |
ento | -0.457 |
uning | -0.441 |
Token | Ste |
Token ID | 7447 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
idth | +1.795 |
psey | +1.366 |
Spoiler | +1.234 |
ento | +1.188 |
avis | +1.167 |
Neg logit contributions | |
APH | -1.603 |
Pyro | -1.486 |
ray | -1.400 |
experien | -1.391 |
� | -1.386 |
Token | fan |
Token ID | 24408 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
APH | +3.605 |
ray | +3.330 |
� | +3.081 |
Pyro | +3.013 |
ax | +2.952 |
Neg logit contributions | |
idth | -5.632 |
psey | -4.363 |
Spoiler | -4.353 |
ento | -3.933 |
aunch | -3.827 |
Token | K |
Token ID | 42 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
idth | +2.589 |
psey | +1.987 |
Spoiler | +1.819 |
ento | +1.739 |
avis | +1.686 |
Neg logit contributions | |
APH | -2.068 |
Pyro | -1.883 |
ray | -1.834 |
experien | -1.788 |
� | -1.778 |
Token | ert |
Token ID | 861 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
idth | +8.693 |
psey | +6.081 |
ento | +5.246 |
avis | +5.171 |
aunch | +4.877 |
Neg logit contributions | |
APH | -10.697 |
Pyro | -10.361 |
experien | -9.957 |
Cyrus | -9.734 |
xual | -9.642 |
Token | es |
Token ID | 274 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
APH | +1.220 |
Pyro | +1.104 |
experien | +1.075 |
� | +1.051 |
ray | +1.048 |
Neg logit contributions | |
idth | -1.309 |
psey | -0.977 |
Spoiler | -0.881 |
ento | -0.879 |
avis | -0.866 |
Token | z |
Token ID | 89 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
APH | +1.137 |
Pyro | +1.044 |
experien | +1.032 |
�醒 | +1.014 |
BuyableInstoreAndOnline | +0.986 |
Neg logit contributions | |
idth | -1.002 |
psey | -0.708 |
Spoiler | -0.659 |
ento | -0.623 |
avis | -0.606 |
Token | . |
Token ID | 13 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
APH | +1.919 |
Pyro | +1.746 |
ray | +1.733 |
� | +1.687 |
experien | +1.655 |
Neg logit contributions | |
idth | -1.713 |
psey | -1.249 |
Spoiler | -1.138 |
ento | -1.059 |
uning | -1.013 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
idth | +0.811 |
psey | +0.590 |
Spoiler | +0.544 |
ento | +0.500 |
uning | +0.480 |
Neg logit contributions | |
APH | -0.912 |
Pyro | -0.826 |
ray | -0.822 |
� | -0.799 |
experien | -0.788 |
Token | es |
Token ID | 274 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
idth | +4.785 |
psey | +3.523 |
Spoiler | +3.320 |
ento | +3.199 |
avis | +3.038 |
Neg logit contributions | |
APH | -4.766 |
experien | -4.142 |
ray | -4.091 |
Pyro | -4.088 |
xual | -4.048 |
Token | Benjamin |
Token ID | 14533 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
idth | +1.549 |
psey | +1.150 |
Spoiler | +1.123 |
ento | +1.043 |
avis | +1.008 |
Neg logit contributions | |
APH | -1.376 |
ray | -1.193 |
Pyro | -1.174 |
experien | -1.172 |
� | -1.165 |
Token | , |
Token ID | 11 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
APH | +0.232 |
Pyro | +0.207 |
ray | +0.206 |
� | +0.201 |
experien | +0.195 |
Neg logit contributions | |
idth | -0.259 |
psey | -0.196 |
Spoiler | -0.182 |
ento | -0.172 |
uning | -0.165 |
Token | MD |
Token ID | 10670 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
APH | +0.019 |
ray | +0.016 |
Pyro | +0.016 |
� | +0.016 |
xual | +0.016 |
Neg logit contributions | |
idth | -0.027 |
psey | -0.021 |
Spoiler | -0.021 |
ento | -0.019 |
uning | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
APH | +1.277 |
Pyro | +1.130 |
ray | +1.130 |
� | +1.074 |
ax | +1.044 |
Neg logit contributions | |
idth | -1.814 |
psey | -1.460 |
Spoiler | -1.315 |
ento | -1.257 |
aunch | -1.229 |
Token | American |
Token ID | 1605 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
APH | +0.975 |
ray | +0.865 |
Pyro | +0.849 |
� | +0.843 |
xual | +0.830 |
Neg logit contributions | |
idth | -1.135 |
psey | -0.863 |
Spoiler | -0.826 |
ento | -0.759 |
uning | -0.736 |
Token | Public |
Token ID | 5094 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
idth | +8.879 |
Spoiler | +6.971 |
psey | +6.482 |
ento | +5.991 |
avis | +5.897 |
Neg logit contributions | |
APH | -9.073 |
xual | -8.588 |
guiActiveUn | -8.283 |
experien | -8.093 |
BuyableInstoreAndOnline | -8.053 |
Token | Health |
Token ID | 3893 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
APH | +0.550 |
Pyro | +0.480 |
ray | +0.474 |
� | +0.464 |
experien | +0.455 |
Neg logit contributions | |
idth | -0.765 |
psey | -0.595 |
Spoiler | -0.567 |
ento | -0.534 |
uning | -0.519 |
Token | Ass |
Token ID | 2195 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
APH | +0.555 |
ray | +0.481 |
Pyro | +0.479 |
� | +0.465 |
experien | +0.461 |
Neg logit contributions | |
idth | -0.820 |
psey | -0.639 |
Spoiler | -0.611 |
ento | -0.579 |
avis | -0.557 |
Token | oc |
Token ID | 420 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
APH | +0.492 |
Pyro | +0.445 |
ray | +0.436 |
� | +0.428 |
experien | +0.420 |
Neg logit contributions | |
idth | -0.473 |
psey | -0.350 |
Spoiler | -0.319 |
ento | -0.302 |
uning | -0.291 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
idth | +7.816 |
psey | +5.846 |
Spoiler | +5.441 |
ento | +5.202 |
avis | +4.964 |
Neg logit contributions | |
APH | -7.208 |
Pyro | -6.457 |
ray | -6.370 |
� | -6.247 |
experien | -6.205 |
Token | assing |
Token ID | 19696 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
idth | +3.350 |
psey | +2.639 |
ento | +2.413 |
Spoiler | +2.408 |
aunch | +2.338 |
Neg logit contributions | |
APH | -1.905 |
Pyro | -1.628 |
� | -1.560 |
ray | -1.555 |
Cyrus | -1.536 |
Token | ( |
Token ID | 357 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
idth | +7.339 |
psey | +5.104 |
Spoiler | +4.638 |
ento | +4.612 |
uning | +4.297 |
Neg logit contributions | |
APH | -8.169 |
ray | -7.200 |
Pyro | -7.163 |
Cyrus | -7.088 |
� | -6.908 |
Token | t |
Token ID | 83 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
idth | +6.215 |
psey | +4.761 |
Spoiler | +4.406 |
ento | +4.246 |
uning | +4.081 |
Neg logit contributions | |
APH | -4.843 |
Pyro | -4.289 |
ray | -4.258 |
� | -4.099 |
experien | -4.008 |
Token | � |
Token ID | 447 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
idth | +5.622 |
psey | +4.182 |
Spoiler | +3.896 |
ento | +3.749 |
uning | +3.614 |
Neg logit contributions | |
APH | -4.870 |
Pyro | -4.312 |
ray | -4.293 |
� | -4.127 |
experien | -4.106 |
Token | � |
Token ID | 247 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
idth | +0.273 |
psey | +0.217 |
Spoiler | +0.206 |
ento | +0.195 |
uning | +0.193 |
Neg logit contributions | |
APH | -0.152 |
Pyro | -0.131 |
ray | -0.130 |
� | -0.125 |
experien | -0.121 |
Token | ) |
Token ID | 8 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
idth | +2.668 |
psey | +1.960 |
Spoiler | +1.824 |
ento | +1.792 |
uning | +1.669 |
Neg logit contributions | |
APH | -2.459 |
Pyro | -2.168 |
ray | -2.167 |
Cyrus | -2.121 |
� | -2.074 |
Token | + |
Token ID | 1343 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
idth | +8.864 |
psey | +6.214 |
Spoiler | +5.693 |
ento | +5.677 |
uning | +5.335 |
Neg logit contributions | |
APH | -9.690 |
ray | -8.615 |
Cyrus | -8.606 |
Pyro | -8.383 |
BuyableInstoreAndOnline | -8.381 |
Token | f |
Token ID | 277 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
idth | +8.408 |
psey | +5.711 |
Spoiler | +5.165 |
ento | +5.085 |
uning | +4.833 |
Neg logit contributions | |
APH | -9.373 |
ray | -8.386 |
Cyrus | -8.234 |
Pyro | -8.141 |
BuyableInstoreAndOnline | -8.005 |
Token | anthrop |
Token ID | 17911 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
idth | +4.838 |
psey | +3.611 |
Spoiler | +3.281 |
ento | +3.235 |
uning | +3.053 |
Neg logit contributions | |
APH | -4.211 |
ray | -3.810 |
Pyro | -3.721 |
Cyrus | -3.612 |
� | -3.598 |
Token | ic |
Token ID | 291 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
idth | +2.311 |
psey | +1.304 |
ento | +1.139 |
Spoiler | +1.048 |
avis | +1.037 |
Neg logit contributions | |
APH | -5.323 |
BuyableInstoreAndOnline | -5.147 |
Skydragon | -4.968 |
Pyro | -4.960 |
ray | -4.889 |
Token | ( |
Token ID | 357 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
idth | +8.081 |
psey | +6.069 |
Spoiler | +5.600 |
ento | +5.391 |
uning | +5.155 |
Neg logit contributions | |
APH | -6.995 |
ray | -6.244 |
Pyro | -6.222 |
� | -5.984 |
experien | -5.850 |
Token | aside |
Token ID | 7263 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
APH | +1.948 |
Pyro | +1.764 |
ray | +1.762 |
� | +1.712 |
experien | +1.669 |
Neg logit contributions | |
idth | -1.755 |
psey | -1.280 |
Spoiler | -1.171 |
ento | -1.090 |
uning | -1.042 |
Token | . |
Token ID | 13 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
APH | +3.171 |
Pyro | +2.854 |
ray | +2.843 |
� | +2.758 |
ax | +2.673 |
Neg logit contributions | |
idth | -3.581 |
psey | -2.715 |
Spoiler | -2.492 |
ento | -2.360 |
aunch | -2.266 |
Token |
|
Token ID | 198 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
APH | +9.102 |
Pyro | +8.520 |
ray | +8.183 |
� | +7.999 |
Cyrus | +7.720 |
Neg logit contributions | |
idth | -12.002 |
psey | -9.412 |
ento | -7.980 |
Spoiler | -7.797 |
uning | -7.672 |
Token |
|
Token ID | 198 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
APH | +7.000 |
Pyro | +6.263 |
ray | +6.252 |
� | +6.055 |
experien | +5.856 |
Neg logit contributions | |
idth | -8.051 |
psey | -6.130 |
Spoiler | -5.650 |
ento | -5.331 |
uning | -5.139 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
APH | +8.379 |
� | +7.598 |
ray | +7.590 |
Pyro | +7.158 |
ax | +7.109 |
Neg logit contributions | |
idth | -10.810 |
psey | -8.381 |
Spoiler | -7.348 |
ento | -7.053 |
uning | -6.721 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
APH | +5.916 |
Pyro | +5.310 |
ray | +5.287 |
� | +5.122 |
experien | +5.076 |
Neg logit contributions | |
idth | -6.233 |
psey | -4.658 |
Spoiler | -4.361 |
ento | -4.073 |
aunch | -3.923 |
Token | Steam |
Token ID | 9094 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
APH | +11.860 |
Pyro | +11.759 |
ray | +10.929 |
� | +10.657 |
Cyrus | +10.604 |
Neg logit contributions | |
idth | -16.512 |
psey | -13.136 |
ento | -11.017 |
uning | -10.514 |
ndum | -10.293 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
APH | +2.499 |
Pyro | +2.243 |
ray | +2.240 |
� | +2.184 |
experien | +2.134 |
Neg logit contributions | |
idth | -2.446 |
psey | -1.811 |
Spoiler | -1.684 |
ento | -1.563 |
aunch | -1.506 |
Token | broccoli |
Token ID | 44653 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
idth | +1.853 |
psey | +1.425 |
Spoiler | +1.391 |
ento | +1.255 |
aunch | +1.223 |
Neg logit contributions | |
APH | -1.676 |
ray | -1.467 |
� | -1.447 |
Pyro | -1.417 |
xual | -1.378 |
Token | for |
Token ID | 329 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
idth | +1.137 |
psey | +0.852 |
Spoiler | +0.805 |
ento | +0.730 |
aunch | +0.713 |
Neg logit contributions | |
APH | -1.152 |
ray | -1.017 |
Pyro | -1.015 |
� | -0.990 |
experien | -0.959 |
Token | a |
Token ID | 257 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
APH | +5.348 |
Pyro | +4.814 |
ray | +4.792 |
� | +4.648 |
experien | +4.508 |
Neg logit contributions | |
idth | -5.929 |
psey | -4.490 |
Spoiler | -4.132 |
ento | -3.896 |
aunch | -3.741 |
Token | destinations |
Token ID | 23982 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
APH | +2.700 |
Pyro | +2.397 |
ray | +2.384 |
� | +2.318 |
experien | +2.246 |
Neg logit contributions | |
idth | -3.410 |
psey | -2.636 |
Spoiler | -2.429 |
ento | -2.280 |
aunch | -2.237 |
Token | , |
Token ID | 11 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
APH | +6.183 |
Pyro | +5.560 |
ray | +5.529 |
� | +5.374 |
experien | +5.234 |
Neg logit contributions | |
idth | -6.617 |
psey | -4.982 |
Spoiler | -4.590 |
ento | -4.315 |
aunch | -4.153 |
Token | and |
Token ID | 290 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
APH | +5.488 |
Pyro | +4.918 |
ray | +4.909 |
� | +4.753 |
experien | +4.606 |
Neg logit contributions | |
idth | -6.165 |
psey | -4.677 |
Spoiler | -4.314 |
ento | -4.066 |
uning | -3.916 |
Token | explore |
Token ID | 7301 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
APH | +4.146 |
ray | +3.375 |
Pyro | +3.259 |
experien | +3.040 |
� | +3.009 |
Neg logit contributions | |
idth | -12.230 |
psey | -10.134 |
Spoiler | -9.638 |
ento | -9.227 |
uning | -9.109 |
Token | the |
Token ID | 262 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
APH | +8.937 |
Pyro | +8.019 |
ray | +7.794 |
� | +7.555 |
ax | +7.444 |
Neg logit contributions | |
idth | -10.679 |
psey | -8.225 |
Spoiler | -7.451 |
ento | -7.347 |
avis | -7.089 |
Token | world |
Token ID | 995 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
APH | +8.249 |
Pyro | +7.358 |
ray | +6.938 |
� | +6.848 |
experien | +6.752 |
Neg logit contributions | |
idth | -14.692 |
psey | -11.594 |
Spoiler | -10.767 |
ento | -10.608 |
avis | -10.547 |
Token | with |
Token ID | 351 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
APH | +10.170 |
ray | +9.321 |
� | +9.133 |
Pyro | +9.042 |
Cyrus | +8.138 |
Neg logit contributions | |
idth | -18.287 |
psey | -14.655 |
Spoiler | -13.191 |
ento | -12.851 |
uning | -12.512 |
Token | kindred |
Token ID | 46449 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
APH | +8.325 |
ray | +7.025 |
Pyro | +7.013 |
� | +6.900 |
experien | +6.662 |
Neg logit contributions | |
idth | -15.010 |
psey | -12.267 |
ento | -11.241 |
Spoiler | -11.117 |
avis | -10.474 |
Token | spirits |
Token ID | 13747 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
APH | +1.568 |
Pyro | +1.425 |
ray | +1.412 |
� | +1.361 |
ax | +1.334 |
Neg logit contributions | |
idth | -1.605 |
psey | -1.213 |
Spoiler | -1.121 |
ento | -1.049 |
avis | -1.017 |
Token | . |
Token ID | 13 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
APH | +5.763 |
Pyro | +5.170 |
ray | +5.157 |
� | +4.996 |
experien | +4.848 |
Neg logit contributions | |
idth | -6.410 |
psey | -4.855 |
Spoiler | -4.475 |
ento | -4.215 |
uning | -4.059 |
Token | Be |
Token ID | 1355 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
APH | +4.614 |
ray | +4.076 |
Pyro | +4.036 |
� | +3.885 |
experien | +3.800 |
Neg logit contributions | |
idth | -6.629 |
psey | -5.156 |
Spoiler | -4.908 |
ento | -4.623 |
aunch | -4.468 |
Token | destinations |
Token ID | 23982 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
APH | +2.119 |
ray | +1.882 |
Pyro | +1.882 |
� | +1.824 |
experien | +1.768 |
Neg logit contributions | |
idth | -2.574 |
psey | -1.989 |
Spoiler | -1.830 |
ento | -1.714 |
aunch | -1.678 |
Token | , |
Token ID | 11 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
APH | +6.115 |
Pyro | +5.481 |
ray | +5.474 |
� | +5.296 |
ax | +5.126 |
Neg logit contributions | |
idth | -6.968 |
psey | -5.307 |
Spoiler | -4.876 |
ento | -4.602 |
uning | -4.435 |
Token | and |
Token ID | 290 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
APH | +5.130 |
Pyro | +4.601 |
ray | +4.576 |
� | +4.440 |
experien | +4.346 |
Neg logit contributions | |
idth | -5.566 |
psey | -4.185 |
Spoiler | -3.892 |
ento | -3.655 |
uning | -3.514 |
Token | explore |
Token ID | 7301 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
APH | +3.137 |
Pyro | +2.716 |
ray | +2.672 |
� | +2.587 |
ax | +2.529 |
Neg logit contributions | |
idth | -5.412 |
psey | -4.347 |
Spoiler | -4.090 |
ento | -4.004 |
uning | -3.871 |
Token | the |
Token ID | 262 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
APH | +8.109 |
Pyro | +7.315 |
ray | +7.290 |
� | +7.071 |
ax | +6.858 |
Neg logit contributions | |
idth | -9.643 |
psey | -7.484 |
Spoiler | -6.588 |
ento | -6.361 |
uning | -6.204 |
Token | world |
Token ID | 995 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
APH | +7.421 |
Pyro | +6.777 |
ray | +6.583 |
� | +6.394 |
experien | +6.271 |
Neg logit contributions | |
idth | -13.936 |
psey | -11.157 |
Spoiler | -10.278 |
ento | -9.993 |
avis | -9.644 |
Token | with |
Token ID | 351 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
APH | +9.429 |
ray | +8.783 |
Pyro | +8.539 |
� | +8.421 |
ax | +8.096 |
Neg logit contributions | |
idth | -17.749 |
psey | -14.828 |
Spoiler | -12.810 |
ento | -12.624 |
eleph | -12.372 |
Token | kindred |
Token ID | 46449 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
APH | +7.224 |
Pyro | +6.398 |
ray | +6.340 |
� | +6.173 |
experien | +6.051 |
Neg logit contributions | |
idth | -10.990 |
psey | -8.639 |
Spoiler | -8.001 |
ento | -7.666 |
aunch | -7.387 |
Token | spirits |
Token ID | 13747 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
idth | +0.621 |
psey | +0.439 |
Spoiler | +0.422 |
ento | +0.389 |
avis | +0.369 |
Neg logit contributions | |
APH | -0.799 |
ray | -0.721 |
Pyro | -0.714 |
�醒 | -0.711 |
� | -0.701 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
APH | +2.991 |
Pyro | +2.711 |
ray | +2.665 |
experien | +2.661 |
xual | +2.599 |
Neg logit contributions | |
idth | -2.731 |
psey | -1.954 |
Spoiler | -1.900 |
ento | -1.747 |
avis | -1.689 |
Token |
|
Token ID | 198 |
Feature activation | -3.24e-04 |
Pos logit contributions | |
APH | +4.964 |
ray | +4.435 |
Pyro | +4.431 |
� | +4.290 |
experien | +4.274 |
Neg logit contributions | |
idth | -5.109 |
psey | -3.794 |
Spoiler | -3.615 |
ento | -3.332 |
avis | -3.210 |
Token | knife |
Token ID | 9845 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
idth | +1.388 |
psey | +1.038 |
Spoiler | +0.993 |
uning | +0.926 |
ento | +0.917 |
Neg logit contributions | |
APH | -1.217 |
Pyro | -1.063 |
ray | -1.063 |
� | -1.043 |
xual | -1.034 |
Token | . |
Token ID | 13 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
APH | +2.177 |
Pyro | +1.953 |
ray | +1.950 |
� | +1.889 |
experien | +1.839 |
Neg logit contributions | |
idth | -2.346 |
psey | -1.767 |
Spoiler | -1.631 |
ento | -1.527 |
uning | -1.477 |
Token |
|
Token ID | 198 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
APH | +8.828 |
Pyro | +8.305 |
ray | +8.027 |
� | +7.801 |
ax | +7.536 |
Neg logit contributions | |
idth | -11.710 |
psey | -9.257 |
ento | -7.906 |
Spoiler | -7.807 |
uning | -7.578 |
Token |
|
Token ID | 198 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
APH | +2.599 |
experien | +2.337 |
Pyro | +2.333 |
ray | +2.294 |
xual | +2.284 |
Neg logit contributions | |
idth | -2.296 |
Spoiler | -1.638 |
psey | -1.626 |
ento | -1.468 |
avis | -1.426 |
Token | 3 |
Token ID | 18 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
APH | +5.149 |
� | +4.707 |
ray | +4.693 |
ax | +4.264 |
Pyro | +4.106 |
Neg logit contributions | |
idth | -9.322 |
psey | -7.532 |
Spoiler | -6.685 |
ento | -6.439 |
uning | -6.328 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
APH | +2.631 |
experien | +2.394 |
Pyro | +2.378 |
ray | +2.338 |
xual | +2.317 |
Neg logit contributions | |
idth | -2.257 |
Spoiler | -1.586 |
psey | -1.579 |
ento | -1.419 |
avis | -1.396 |
Token | In |
Token ID | 554 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
APH | +10.928 |
Pyro | +10.723 |
ray | +10.005 |
� | +9.844 |
Cyrus | +9.630 |
Neg logit contributions | |
idth | -14.567 |
psey | -11.571 |
ento | -9.817 |
uning | -9.336 |
Spoiler | -9.295 |
Token | a |
Token ID | 257 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
APH | +2.931 |
Pyro | +2.650 |
ray | +2.646 |
� | +2.571 |
experien | +2.505 |
Neg logit contributions | |
idth | -2.736 |
psey | -2.010 |
Spoiler | -1.836 |
ento | -1.715 |
uning | -1.641 |
Token | large |
Token ID | 1588 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
APH | +1.491 |
ray | +1.303 |
Pyro | +1.299 |
� | +1.273 |
experien | +1.244 |
Neg logit contributions | |
idth | -1.698 |
psey | -1.296 |
Spoiler | -1.211 |
ento | -1.126 |
uning | -1.098 |
Token | bowl |
Token ID | 9396 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
idth | +1.748 |
psey | +1.166 |
Spoiler | +1.085 |
ento | +0.944 |
uning | +0.924 |
Neg logit contributions | |
APH | -2.782 |
ray | -2.478 |
� | -2.462 |
Pyro | -2.443 |
xual | -2.428 |
Token | , |
Token ID | 11 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
APH | +6.651 |
ray | +6.271 |
Pyro | +6.237 |
� | +5.960 |
ax | +5.866 |
Neg logit contributions | |
idth | -10.965 |
psey | -8.797 |
Spoiler | -7.846 |
ento | -7.680 |
uning | -7.281 |
Token | the |
Token ID | 262 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
APH | +6.074 |
ray | +5.148 |
ax | +5.119 |
Cyrus | +5.110 |
Pyro | +5.001 |
Neg logit contributions | |
idth | -8.581 |
psey | -6.678 |
avis | -6.135 |
Spoiler | -6.020 |
uning | -5.979 |
Token | 2020 |
Token ID | 12131 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
APH | +8.379 |
Pyro | +7.893 |
ray | +7.563 |
ax | +7.535 |
� | +7.228 |
Neg logit contributions | |
idth | -10.844 |
psey | -8.541 |
Spoiler | -7.492 |
aunch | -7.288 |
uning | -7.271 |
Token | race |
Token ID | 3234 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
APH | +5.374 |
Pyro | +5.093 |
ray | +5.035 |
Cyrus | +4.885 |
ax | +4.882 |
Neg logit contributions | |
idth | -6.441 |
psey | -4.866 |
ento | -4.474 |
Spoiler | -4.427 |
avis | -4.248 |
Token | Obama |
Token ID | 2486 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
APH | +6.297 |
Pyro | +5.924 |
Cyrus | +5.711 |
ray | +5.365 |
� | +5.338 |
Neg logit contributions | |
idth | -10.688 |
psey | -8.696 |
ento | -7.286 |
uning | -7.044 |
Spoiler | -7.024 |
Token | goes |
Token ID | 2925 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
APH | +4.971 |
Pyro | +4.443 |
ray | +4.396 |
ax | +4.249 |
� | +4.233 |
Neg logit contributions | |
idth | -6.189 |
psey | -4.821 |
Spoiler | -4.215 |
ento | -3.991 |
uning | -3.866 |
Token | viral |
Token ID | 14416 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
APH | +8.606 |
Pyro | +8.120 |
ray | +7.828 |
� | +7.464 |
Geo | +7.439 |
Neg logit contributions | |
idth | -13.480 |
psey | -10.662 |
Spoiler | -9.949 |
ento | -9.600 |
uning | -8.873 |
Token | after |
Token ID | 706 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
APH | +10.136 |
Pyro | +10.026 |
Cyrus | +8.985 |
� | +8.760 |
ray | +8.627 |
Neg logit contributions | |
idth | -15.193 |
psey | -12.367 |
uning | -10.197 |
ento | -10.163 |
Spoiler | -10.131 |
Token | sporting |
Token ID | 17702 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
APH | +6.393 |
ray | +5.748 |
Pyro | +5.671 |
ax | +5.442 |
� | +5.429 |
Neg logit contributions | |
idth | -7.874 |
psey | -6.114 |
Spoiler | -5.644 |
uning | -5.151 |
ento | -5.139 |
Token | black |
Token ID | 2042 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
APH | +5.193 |
Pyro | +4.814 |
ray | +4.541 |
� | +4.446 |
Cyrus | +4.444 |
Neg logit contributions | |
idth | -7.873 |
psey | -6.180 |
Spoiler | -5.520 |
ento | -5.410 |
netflix | -5.389 |
Token | bomber |
Token ID | 24065 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
APH | +5.773 |
Pyro | +5.468 |
ray | +5.405 |
� | +5.086 |
Cyrus | +4.990 |
Neg logit contributions | |
idth | -10.006 |
psey | -8.357 |
Spoiler | -7.400 |
avis | -7.056 |
ento | -7.030 |
Token | jacket |
Token ID | 15224 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
APH | +3.321 |
ray | +2.984 |
Pyro | +2.983 |
� | +2.894 |
experien | +2.842 |
Neg logit contributions | |
idth | -3.006 |
psey | -2.162 |
Spoiler | -2.049 |
ento | -1.869 |
avis | -1.800 |
Token | charge |
Token ID | 3877 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
APH | +4.528 |
Pyro | +4.094 |
� | +4.000 |
ray | +3.962 |
Cyrus | +3.860 |
Neg logit contributions | |
idth | -6.057 |
psey | -4.459 |
Spoiler | -4.105 |
ento | -3.812 |
avis | -3.768 |
Token | of |
Token ID | 286 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
APH | +5.838 |
Pyro | +5.301 |
ray | +5.276 |
� | +5.116 |
Cyrus | +4.824 |
Neg logit contributions | |
idth | -8.063 |
psey | -6.249 |
Spoiler | -5.588 |
ento | -5.440 |
uning | -5.293 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
APH | +2.205 |
Pyro | +2.064 |
ray | +2.012 |
� | +1.968 |
Geo | +1.870 |
Neg logit contributions | |
idth | -3.374 |
psey | -2.521 |
Spoiler | -2.396 |
uning | -2.244 |
avis | -2.240 |
Token | probe |
Token ID | 12774 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
APH | +4.489 |
Pyro | +3.983 |
ray | +3.980 |
� | +3.872 |
ax | +3.726 |
Neg logit contributions | |
idth | -5.562 |
psey | -4.288 |
Spoiler | -3.946 |
ento | -3.728 |
uning | -3.610 |
Token | : |
Token ID | 25 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
APH | +7.964 |
Pyro | +7.306 |
ray | +7.135 |
� | +6.996 |
Cyrus | +6.944 |
Neg logit contributions | |
idth | -11.440 |
psey | -9.445 |
ento | -8.129 |
Spoiler | -7.978 |
uning | -7.968 |
Token | report |
Token ID | 989 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
APH | +3.992 |
Pyro | +3.392 |
� | +3.364 |
ray | +3.361 |
ax | +3.224 |
Neg logit contributions | |
idth | -8.283 |
psey | -7.152 |
ento | -6.085 |
uning | -6.020 |
Spoiler | -6.005 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
APH | +9.513 |
Pyro | +8.897 |
Cyrus | +8.798 |
Kyl | +8.668 |
� | +8.479 |
Neg logit contributions | |
idth | -15.419 |
psey | -13.346 |
ento | -10.908 |
aunch | -10.674 |
uning | -10.580 |
Token | airline |
Token ID | 18091 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
APH | +1.778 |
Pyro | +1.592 |
ray | +1.587 |
� | +1.538 |
experien | +1.493 |
Neg logit contributions | |
idth | -1.956 |
psey | -1.479 |
Spoiler | -1.379 |
ento | -1.284 |
uning | -1.251 |
Token | takes |
Token ID | 2753 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
APH | +1.340 |
Pyro | +1.205 |
ray | +1.194 |
� | +1.164 |
experien | +1.123 |
Neg logit contributions | |
idth | -1.597 |
psey | -1.219 |
Spoiler | -1.139 |
ento | -1.064 |
aunch | -1.040 |
Token | steps |
Token ID | 4831 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
APH | +6.680 |
Kyl | +6.377 |
� | +6.035 |
Pyro | +5.908 |
Zy | +5.704 |
Neg logit contributions | |
idth | -14.551 |
psey | -11.742 |
ento | -10.780 |
avis | -10.274 |
olkien | -10.254 |
Token | to |
Token ID | 284 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
APH | +7.208 |
ray | +6.570 |
� | +6.422 |
Cyrus | +6.246 |
Pyro | +6.095 |
Neg logit contributions | |
idth | -13.790 |
psey | -10.899 |
Spoiler | -10.094 |
ento | -9.481 |
uning | -9.249 |
Token | fried |
Token ID | 23018 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
idth | +1.927 |
psey | +1.446 |
Spoiler | +1.373 |
ento | +1.303 |
aunch | +1.243 |
Neg logit contributions | |
APH | -1.746 |
Pyro | -1.542 |
ray | -1.530 |
� | -1.497 |
experien | -1.482 |
Token | . |
Token ID | 13 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
idth | +0.340 |
psey | +0.253 |
Spoiler | +0.233 |
ento | +0.220 |
avis | +0.210 |
Neg logit contributions | |
APH | -0.352 |
Pyro | -0.316 |
ray | -0.313 |
� | -0.305 |
experien | -0.303 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
APH | +5.764 |
ray | +5.131 |
Pyro | +5.128 |
� | +4.959 |
experien | +4.834 |
Neg logit contributions | |
idth | -6.689 |
psey | -5.089 |
Spoiler | -4.745 |
ento | -4.446 |
uning | -4.289 |
Token |
|
Token ID | 198 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
APH | +2.283 |
experien | +2.058 |
Pyro | +2.049 |
xual | +2.014 |
ray | +2.012 |
Neg logit contributions | |
idth | -1.969 |
Spoiler | -1.404 |
psey | -1.380 |
ento | -1.245 |
avis | -1.214 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
APH | +0.425 |
ray | +0.389 |
� | +0.380 |
Pyro | +0.373 |
ax | +0.362 |
Neg logit contributions | |
idth | -0.541 |
psey | -0.423 |
Spoiler | -0.378 |
ento | -0.372 |
uning | -0.349 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
APH | +2.457 |
experien | +2.236 |
Pyro | +2.204 |
ray | +2.183 |
xual | +2.162 |
Neg logit contributions | |
idth | -2.096 |
Spoiler | -1.477 |
psey | -1.466 |
ento | -1.317 |
avis | -1.289 |
Token | Drain |
Token ID | 36024 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
APH | +10.639 |
Pyro | +10.333 |
ray | +9.682 |
� | +9.540 |
Cyrus | +9.293 |
Neg logit contributions | |
idth | -14.565 |
psey | -11.630 |
ento | -9.888 |
uning | -9.528 |
Spoiler | -9.506 |
Token | on |
Token ID | 319 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
APH | +1.563 |
ray | +1.404 |
Pyro | +1.399 |
� | +1.355 |
experien | +1.323 |
Neg logit contributions | |
idth | -1.529 |
psey | -1.136 |
Spoiler | -1.054 |
ento | -0.982 |
uning | -0.940 |
Token | a |
Token ID | 257 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
APH | +3.486 |
Pyro | +3.111 |
ray | +3.105 |
� | +3.003 |
experien | +2.910 |
Neg logit contributions | |
idth | -4.172 |
psey | -3.194 |
Spoiler | -2.956 |
ento | -2.792 |
uning | -2.694 |
Token | paper |
Token ID | 3348 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
APH | +2.213 |
ray | +1.965 |
Pyro | +1.939 |
� | +1.900 |
experien | +1.877 |
Neg logit contributions | |
idth | -2.280 |
psey | -1.707 |
Spoiler | -1.602 |
ento | -1.482 |
uning | -1.459 |
Token | towel |
Token ID | 24808 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
APH | +0.900 |
Pyro | +0.810 |
ray | +0.808 |
� | +0.790 |
experien | +0.786 |
Neg logit contributions | |
idth | -0.737 |
psey | -0.524 |
Spoiler | -0.485 |
ento | -0.437 |
uning | -0.427 |
Token | Catholic |
Token ID | 7835 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
APH | +1.458 |
ray | +1.290 |
Pyro | +1.284 |
� | +1.243 |
experien | +1.215 |
Neg logit contributions | |
idth | -1.575 |
psey | -1.185 |
Spoiler | -1.101 |
ento | -1.033 |
aunch | -0.999 |
Token | church |
Token ID | 4928 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
idth | +0.970 |
psey | +0.715 |
Spoiler | +0.685 |
ento | +0.633 |
uning | +0.614 |
Neg logit contributions | |
APH | -0.992 |
ray | -0.866 |
Pyro | -0.854 |
� | -0.839 |
ax | -0.818 |
Token | of |
Token ID | 286 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
APH | +2.892 |
Pyro | +2.602 |
ray | +2.589 |
� | +2.509 |
experien | +2.456 |
Neg logit contributions | |
idth | -2.878 |
psey | -2.138 |
Spoiler | -1.968 |
ento | -1.842 |
uning | -1.772 |
Token | Saint |
Token ID | 9281 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
APH | +3.535 |
Pyro | +3.191 |
ray | +3.171 |
� | +3.068 |
experien | +2.974 |
Neg logit contributions | |
idth | -4.020 |
psey | -3.056 |
Spoiler | -2.805 |
ento | -2.653 |
uning | -2.556 |
Token | John |
Token ID | 1757 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
APH | +0.204 |
ray | +0.179 |
Pyro | +0.178 |
� | +0.175 |
experien | +0.172 |
Neg logit contributions | |
idth | -0.228 |
psey | -0.171 |
Spoiler | -0.161 |
ento | -0.151 |
aunch | -0.147 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
APH | +3.022 |
Pyro | +2.710 |
ray | +2.706 |
� | +2.622 |
experien | +2.545 |
Neg logit contributions | |
idth | -3.314 |
psey | -2.503 |
Spoiler | -2.310 |
ento | -2.174 |
uning | -2.091 |
Token | Baptist |
Token ID | 21724 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
APH | +7.198 |
Pyro | +6.647 |
ray | +6.472 |
Cyrus | +6.151 |
Kyl | +5.901 |
Neg logit contributions | |
idth | -17.376 |
psey | -14.067 |
Spoiler | -13.112 |
ento | -13.023 |
netflix | -12.794 |
Token | sits |
Token ID | 10718 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
APH | +2.898 |
Pyro | +2.599 |
ray | +2.590 |
� | +2.508 |
experien | +2.458 |
Neg logit contributions | |
idth | -2.861 |
psey | -2.130 |
Spoiler | -1.959 |
ento | -1.832 |
uning | -1.762 |
Token | in |
Token ID | 287 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
idth | +0.790 |
psey | +0.591 |
Spoiler | +0.545 |
ento | +0.492 |
uning | +0.483 |
Neg logit contributions | |
APH | -0.912 |
Pyro | -0.816 |
ray | -0.810 |
xual | -0.788 |
� | -0.784 |
Token | the |
Token ID | 262 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
APH | +0.260 |
ray | +0.232 |
Pyro | +0.231 |
� | +0.226 |
experien | +0.221 |
Neg logit contributions | |
idth | -0.240 |
psey | -0.177 |
Spoiler | -0.163 |
ento | -0.152 |
uning | -0.144 |
Token | Temple |
Token ID | 10857 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
APH | +2.605 |
ray | +2.313 |
Pyro | +2.303 |
� | +2.251 |
experien | +2.178 |
Neg logit contributions | |
idth | -2.688 |
psey | -2.030 |
Spoiler | -1.886 |
ento | -1.753 |
aunch | -1.683 |
Token | together |
Token ID | 1978 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
idth | +0.425 |
psey | +0.310 |
Spoiler | +0.290 |
ento | +0.267 |
aunch | +0.261 |
Neg logit contributions | |
APH | -0.440 |
Pyro | -0.393 |
ray | -0.392 |
� | -0.382 |
experien | -0.372 |
Token | . |
Token ID | 13 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
APH | +1.457 |
ray | +1.305 |
Pyro | +1.302 |
� | +1.258 |
experien | +1.228 |
Neg logit contributions | |
idth | -1.453 |
psey | -1.080 |
Spoiler | -1.008 |
ento | -0.934 |
aunch | -0.898 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
APH | +7.865 |
Pyro | +7.275 |
ray | +7.083 |
� | +6.899 |
ax | +6.657 |
Neg logit contributions | |
idth | -9.989 |
psey | -7.801 |
Spoiler | -6.788 |
ento | -6.726 |
uning | -6.440 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
APH | +1.601 |
experien | +1.455 |
Pyro | +1.436 |
xual | +1.424 |
ray | +1.410 |
Neg logit contributions | |
idth | -1.328 |
Spoiler | -0.952 |
psey | -0.920 |
ento | -0.837 |
avis | -0.817 |
Token | 4 |
Token ID | 19 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
idth | +1.780 |
psey | +1.336 |
Spoiler | +1.197 |
ento | +1.137 |
aunch | +1.088 |
Neg logit contributions | |
APH | -1.704 |
ray | -1.533 |
� | -1.517 |
Pyro | -1.515 |
ax | -1.464 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
APH | +1.065 |
experien | +0.987 |
Pyro | +0.961 |
BuyableInstoreAndOnline | +0.957 |
xual | +0.954 |
Neg logit contributions | |
idth | -0.831 |
Spoiler | -0.584 |
psey | -0.562 |
ento | -0.512 |
avis | -0.506 |
Token | Make |
Token ID | 6889 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
APH | +10.752 |
Pyro | +10.465 |
ray | +9.790 |
� | +9.690 |
Cyrus | +9.431 |
Neg logit contributions | |
idth | -14.247 |
psey | -11.308 |
ento | -9.652 |
Spoiler | -9.180 |
uning | -9.175 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
idth | +0.803 |
psey | +0.564 |
Spoiler | +0.534 |
ento | +0.494 |
avis | +0.474 |
Neg logit contributions | |
APH | -0.961 |
ray | -0.859 |
Pyro | -0.854 |
� | -0.836 |
experien | -0.824 |
Token | p |
Token ID | 279 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
APH | +2.209 |
Pyro | +1.973 |
ray | +1.954 |
� | +1.902 |
experien | +1.868 |
Neg logit contributions | |
idth | -2.373 |
psey | -1.792 |
Spoiler | -1.646 |
ento | -1.546 |
uning | -1.498 |
Token | att |
Token ID | 1078 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
APH | +1.371 |
Pyro | +1.223 |
ray | +1.213 |
� | +1.180 |
experien | +1.146 |
Neg logit contributions | |
idth | -1.661 |
psey | -1.272 |
Spoiler | -1.176 |
ento | -1.114 |
aunch | -1.079 |
Token | ies |
Token ID | 444 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
idth | +0.165 |
psey | +0.116 |
Spoiler | +0.105 |
ento | +0.098 |
uning | +0.094 |
Neg logit contributions | |
APH | -0.217 |
Pyro | -0.197 |
ray | -0.194 |
� | -0.192 |
experien | -0.187 |
Token | charge |
Token ID | 3877 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
APH | +4.443 |
Pyro | +4.022 |
� | +3.937 |
ray | +3.927 |
ax | +3.798 |
Neg logit contributions | |
idth | -5.382 |
psey | -3.942 |
Spoiler | -3.613 |
ento | -3.367 |
avis | -3.298 |
Token | of |
Token ID | 286 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
APH | +5.318 |
Pyro | +4.805 |
ray | +4.780 |
� | +4.649 |
Cyrus | +4.386 |
Neg logit contributions | |
idth | -6.884 |
psey | -5.309 |
Spoiler | -4.789 |
ento | -4.619 |
uning | -4.483 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
APH | +1.605 |
Pyro | +1.489 |
ray | +1.452 |
� | +1.429 |
Geo | +1.337 |
Neg logit contributions | |
idth | -2.425 |
psey | -1.827 |
Spoiler | -1.722 |
uning | -1.629 |
avis | -1.617 |
Token | probe |
Token ID | 12774 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
APH | +3.969 |
Pyro | +3.522 |
ray | +3.514 |
� | +3.417 |
ax | +3.286 |
Neg logit contributions | |
idth | -5.026 |
psey | -3.887 |
Spoiler | -3.586 |
ento | -3.390 |
uning | -3.288 |
Token | : |
Token ID | 25 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
APH | +6.853 |
Pyro | +6.222 |
ray | +6.103 |
� | +5.931 |
Cyrus | +5.826 |
Neg logit contributions | |
idth | -10.518 |
psey | -8.642 |
ento | -7.497 |
Spoiler | -7.497 |
uning | -7.371 |
Token | report |
Token ID | 989 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
APH | +3.466 |
Pyro | +2.957 |
ray | +2.954 |
� | +2.934 |
Cyrus | +2.829 |
Neg logit contributions | |
idth | -6.738 |
psey | -5.712 |
ento | -4.935 |
Spoiler | -4.820 |
uning | -4.804 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
APH | +9.350 |
Pyro | +8.739 |
Cyrus | +8.467 |
Kyl | +8.445 |
� | +8.272 |
Neg logit contributions | |
idth | -15.007 |
psey | -12.981 |
ento | -10.644 |
aunch | -10.423 |
uning | -10.386 |
Token | airline |
Token ID | 18091 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
APH | +0.711 |
Pyro | +0.636 |
ray | +0.632 |
� | +0.614 |
experien | +0.597 |
Neg logit contributions | |
idth | -0.777 |
psey | -0.586 |
Spoiler | -0.552 |
ento | -0.509 |
aunch | -0.501 |
Token | takes |
Token ID | 2753 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
APH | +1.279 |
Pyro | +1.153 |
ray | +1.148 |
� | +1.115 |
experien | +1.082 |
Neg logit contributions | |
idth | -1.367 |
psey | -1.028 |
Spoiler | -0.949 |
ento | -0.889 |
uning | -0.858 |
Token | steps |
Token ID | 4831 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
APH | +6.526 |
Kyl | +6.066 |
� | +5.827 |
Pyro | +5.616 |
Zy | +5.459 |
Neg logit contributions | |
idth | -13.484 |
psey | -10.856 |
ento | -9.933 |
avis | -9.499 |
ndum | -9.441 |
Token | to |
Token ID | 284 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
APH | +6.871 |
ray | +6.227 |
� | +6.092 |
Cyrus | +5.954 |
Pyro | +5.775 |
Neg logit contributions | |
idth | -12.710 |
psey | -10.166 |
Spoiler | -9.291 |
ento | -8.687 |
uning | -8.593 |
Token | needed |
Token ID | 2622 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
idth | +0.414 |
psey | +0.303 |
Spoiler | +0.285 |
ento | +0.257 |
avis | +0.254 |
Neg logit contributions | |
APH | -0.437 |
ray | -0.388 |
Pyro | -0.384 |
� | -0.383 |
xual | -0.372 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
idth | +0.425 |
psey | +0.319 |
Spoiler | +0.296 |
ento | +0.274 |
uning | +0.265 |
Neg logit contributions | |
APH | -0.447 |
Pyro | -0.401 |
ray | -0.397 |
� | -0.388 |
experien | -0.380 |
Token | Hare |
Token ID | 42285 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
APH | +2.224 |
Pyro | +1.992 |
ray | +1.989 |
� | +1.933 |
experien | +1.900 |
Neg logit contributions | |
idth | -2.236 |
psey | -1.661 |
Spoiler | -1.561 |
ento | -1.441 |
uning | -1.390 |
Token | wood |
Token ID | 3822 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
APH | +0.633 |
Pyro | +0.585 |
experien | +0.565 |
� | +0.565 |
BuyableInstoreAndOnline | +0.563 |
Neg logit contributions | |
idth | -0.460 |
psey | -0.312 |
Spoiler | -0.268 |
uning | -0.267 |
ento | -0.261 |
Token | has |
Token ID | 468 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
APH | +2.310 |
Pyro | +2.076 |
ray | +2.060 |
� | +2.020 |
experien | +1.967 |
Neg logit contributions | |
idth | -1.894 |
psey | -1.352 |
Spoiler | -1.244 |
ento | -1.145 |
uning | -1.114 |
Token | excellent |
Token ID | 6275 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
APH | +8.989 |
Pyro | +8.318 |
ray | +8.209 |
� | +7.932 |
experien | +7.919 |
Neg logit contributions | |
idth | -8.524 |
psey | -6.306 |
Spoiler | -5.733 |
ento | -5.367 |
uning | -5.134 |
Token | size |
Token ID | 2546 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
APH | +10.017 |
Pyro | +9.279 |
ray | +9.140 |
experien | +8.706 |
ax | +8.592 |
Neg logit contributions | |
idth | -14.401 |
psey | -11.108 |
Spoiler | -10.157 |
ento | -9.754 |
avis | -9.696 |
Token | at |
Token ID | 379 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
APH | +3.070 |
Pyro | +2.755 |
ray | +2.746 |
� | +2.661 |
experien | +2.578 |
Neg logit contributions | |
idth | -3.474 |
psey | -2.640 |
Spoiler | -2.432 |
ento | -2.295 |
uning | -2.208 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
APH | +5.825 |
Pyro | +5.180 |
ray | +5.174 |
� | +4.954 |
ax | +4.832 |
Neg logit contributions | |
idth | -7.919 |
psey | -6.176 |
Spoiler | -5.712 |
ento | -5.440 |
uning | -5.251 |
Token | - |
Token ID | 12 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
APH | +2.102 |
Pyro | +1.862 |
ray | +1.857 |
� | +1.795 |
experien | +1.740 |
Neg logit contributions | |
idth | -2.727 |
psey | -2.109 |
Spoiler | -1.959 |
ento | -1.855 |
uning | -1.795 |
Token | foot |
Token ID | 5898 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
APH | +3.502 |
Pyro | +3.163 |
ray | +3.139 |
� | +3.063 |
experien | +2.984 |
Neg logit contributions | |
idth | -3.450 |
psey | -2.566 |
Spoiler | -2.344 |
ento | -2.202 |
uning | -2.110 |
Token | charge |
Token ID | 3877 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
APH | +4.717 |
Pyro | +4.254 |
ray | +4.181 |
� | +4.175 |
ax | +4.032 |
Neg logit contributions | |
idth | -5.480 |
psey | -3.988 |
Spoiler | -3.657 |
ento | -3.371 |
avis | -3.327 |
Token | of |
Token ID | 286 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
APH | +5.690 |
ray | +5.128 |
Pyro | +5.119 |
� | +4.947 |
Cyrus | +4.674 |
Neg logit contributions | |
idth | -7.769 |
psey | -6.005 |
Spoiler | -5.414 |
ento | -5.245 |
uning | -5.102 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
APH | +2.351 |
Pyro | +2.184 |
ray | +2.146 |
� | +2.090 |
Geo | +1.991 |
Neg logit contributions | |
idth | -3.526 |
psey | -2.617 |
Spoiler | -2.504 |
uning | -2.346 |
avis | -2.336 |
Token | probe |
Token ID | 12774 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
APH | +4.180 |
Pyro | +3.679 |
ray | +3.678 |
� | +3.562 |
ax | +3.427 |
Neg logit contributions | |
idth | -5.749 |
psey | -4.487 |
Spoiler | -4.155 |
ento | -3.940 |
uning | -3.820 |
Token | : |
Token ID | 25 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
APH | +8.238 |
Pyro | +7.508 |
ray | +7.436 |
� | +7.197 |
Cyrus | +7.158 |
Neg logit contributions | |
idth | -11.223 |
psey | -9.121 |
Spoiler | -7.850 |
ento | -7.828 |
uning | -7.707 |
Token | report |
Token ID | 989 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
APH | +4.554 |
ray | +3.986 |
Pyro | +3.935 |
ax | +3.903 |
� | +3.784 |
Neg logit contributions | |
idth | -8.838 |
psey | -7.599 |
Spoiler | -6.463 |
ento | -6.430 |
uning | -6.343 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
APH | +9.269 |
Pyro | +8.599 |
Cyrus | +8.475 |
Kyl | +8.278 |
� | +8.272 |
Neg logit contributions | |
idth | -14.746 |
psey | -12.411 |
ento | -10.254 |
uning | -10.170 |
aunch | -10.131 |
Token | airline |
Token ID | 18091 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
APH | +1.949 |
Pyro | +1.744 |
ray | +1.740 |
� | +1.685 |
experien | +1.633 |
Neg logit contributions | |
idth | -2.237 |
psey | -1.703 |
Spoiler | -1.572 |
ento | -1.483 |
uning | -1.429 |
Token | takes |
Token ID | 2753 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
APH | +1.504 |
Pyro | +1.345 |
ray | +1.334 |
� | +1.297 |
experien | +1.251 |
Neg logit contributions | |
idth | -1.927 |
psey | -1.486 |
Spoiler | -1.389 |
ento | -1.306 |
aunch | -1.272 |
Token | steps |
Token ID | 4831 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
APH | +6.903 |
Kyl | +6.501 |
� | +6.138 |
Pyro | +6.037 |
Cyrus | +5.870 |
Neg logit contributions | |
idth | -14.642 |
psey | -11.870 |
ento | -10.752 |
ndum | -10.348 |
Spoiler | -10.287 |
Token | to |
Token ID | 284 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
APH | +7.101 |
ray | +6.495 |
� | +6.326 |
Pyro | +6.067 |
Cyrus | +6.021 |
Neg logit contributions | |
idth | -12.685 |
psey | -9.939 |
Spoiler | -9.204 |
ento | -8.600 |
uning | -8.401 |
Token | transparent |
Token ID | 13245 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
APH | +6.742 |
Pyro | +6.133 |
ray | +6.111 |
� | +5.897 |
ax | +5.745 |
Neg logit contributions | |
idth | -7.657 |
psey | -5.890 |
Spoiler | -5.324 |
ento | -5.004 |
avis | -4.794 |
Token | . |
Token ID | 13 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
APH | +3.496 |
Pyro | +3.166 |
ray | +3.164 |
� | +3.037 |
ax | +2.962 |
Neg logit contributions | |
idth | -4.333 |
psey | -3.354 |
Spoiler | -3.047 |
ento | -2.900 |
aunch | -2.796 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
APH | +8.591 |
Pyro | +7.920 |
ray | +7.758 |
� | +7.483 |
ax | +7.248 |
Neg logit contributions | |
idth | -11.068 |
psey | -8.644 |
Spoiler | -7.527 |
ento | -7.478 |
uning | -7.173 |
Token |
|
Token ID | 198 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
APH | +1.351 |
experien | +1.238 |
Pyro | +1.213 |
xual | +1.206 |
ray | +1.187 |
Neg logit contributions | |
idth | -1.089 |
Spoiler | -0.780 |
psey | -0.746 |
ento | -0.684 |
avis | -0.670 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
APH | +6.885 |
ray | +6.254 |
� | +6.152 |
Pyro | +5.819 |
ax | +5.739 |
Neg logit contributions | |
idth | -9.868 |
psey | -7.727 |
Spoiler | -6.918 |
ento | -6.678 |
uning | -6.465 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
APH | +1.566 |
experien | +1.452 |
Pyro | +1.408 |
xual | +1.398 |
BuyableInstoreAndOnline | +1.398 |
Neg logit contributions | |
idth | -1.233 |
Spoiler | -0.877 |
psey | -0.837 |
ento | -0.764 |
avis | -0.755 |
Token | Now |
Token ID | 2735 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
APH | +10.486 |
Pyro | +10.029 |
ray | +9.573 |
� | +9.295 |
Cyrus | +9.062 |
Neg logit contributions | |
idth | -13.844 |
psey | -10.945 |
ento | -9.342 |
Spoiler | -8.969 |
uning | -8.928 |
Token | throw |
Token ID | 3714 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
APH | +4.189 |
ray | +3.717 |
Pyro | +3.708 |
� | +3.615 |
experien | +3.532 |
Neg logit contributions | |
idth | -4.400 |
psey | -3.294 |
Spoiler | -3.083 |
ento | -2.872 |
aunch | -2.772 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
APH | +3.766 |
Pyro | +3.398 |
ray | +3.396 |
� | +3.298 |
ax | +3.206 |
Neg logit contributions | |
idth | -3.994 |
psey | -3.002 |
Spoiler | -2.728 |
ento | -2.577 |
uning | -2.483 |
Token | ready |
Token ID | 3492 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
idth | +1.542 |
psey | +1.162 |
Spoiler | +1.103 |
ento | +1.010 |
uning | +0.973 |
Neg logit contributions | |
APH | -1.506 |
ray | -1.326 |
Pyro | -1.323 |
� | -1.284 |
xual | -1.253 |
Token | garlic |
Token ID | 17644 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
idth | +2.456 |
psey | +1.817 |
Spoiler | +1.722 |
ento | +1.586 |
uning | +1.547 |
Neg logit contributions | |
APH | -2.352 |
ray | -2.109 |
Pyro | -2.108 |
experien | -2.030 |
� | -2.004 |
Token | Le |
Token ID | 1004 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
APH | +3.031 |
Pyro | +2.738 |
ray | +2.719 |
� | +2.625 |
ax | +2.542 |
Neg logit contributions | |
idth | -3.493 |
psey | -2.682 |
Spoiler | -2.402 |
ento | -2.313 |
uning | -2.230 |
Token | a |
Token ID | 64 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
APH | +2.991 |
Pyro | +2.702 |
ray | +2.659 |
experien | +2.643 |
� | +2.586 |
Neg logit contributions | |
idth | -2.815 |
psey | -2.055 |
Spoiler | -1.958 |
ento | -1.839 |
avis | -1.816 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
APH | +1.102 |
ray | +0.989 |
experien | +0.961 |
xual | +0.943 |
� | +0.939 |
Neg logit contributions | |
idth | -0.913 |
Spoiler | -0.689 |
psey | -0.642 |
ento | -0.586 |
Flores | -0.579 |
Token | , |
Token ID | 11 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
APH | +1.370 |
ray | +1.236 |
experien | +1.234 |
xual | +1.220 |
Pyro | +1.219 |
Neg logit contributions | |
idth | -1.082 |
Spoiler | -0.778 |
psey | -0.717 |
ento | -0.670 |
Flores | -0.644 |
Token | The |
Token ID | 383 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
APH | +2.639 |
experien | +2.394 |
xual | +2.369 |
ray | +2.368 |
Pyro | +2.321 |
Neg logit contributions | |
idth | -2.447 |
Spoiler | -1.848 |
psey | -1.682 |
ento | -1.584 |
avis | -1.536 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
idth | +2.783 |
Spoiler | +2.371 |
psey | +2.095 |
ento | +2.051 |
Flores | +2.042 |
Neg logit contributions | |
APH | -2.216 |
experien | -2.048 |
xual | -2.045 |
BuyableInstoreAndOnline | -2.034 |
�醒 | -1.963 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
APH | +6.000 |
ray | +4.786 |
VIDEOS | +4.591 |
Pyro | +4.519 |
Geo | +4.516 |
Neg logit contributions | |
idth | -17.306 |
psey | -14.217 |
uning | -12.763 |
Spoiler | -12.623 |
abase | -12.296 |
Token | of |
Token ID | 286 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
idth | +1.362 |
Spoiler | +0.981 |
psey | +0.941 |
ento | +0.851 |
aunch | +0.824 |
Neg logit contributions | |
APH | -1.803 |
BuyableInstoreAndOnline | -1.748 |
experien | -1.657 |
Pyro | -1.625 |
�醒 | -1.614 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
APH | +0.551 |
Pyro | +0.497 |
ray | +0.489 |
� | +0.482 |
BuyableInstoreAndOnline | +0.480 |
Neg logit contributions | |
idth | -0.512 |
Spoiler | -0.368 |
psey | -0.351 |
ento | -0.328 |
aunch | -0.315 |
Token | Photo |
Token ID | 5555 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
APH | +3.563 |
Pyro | +3.146 |
ray | +3.133 |
� | +3.005 |
ax | +2.897 |
Neg logit contributions | |
idth | -5.196 |
psey | -4.082 |
Spoiler | -3.774 |
ento | -3.602 |
uning | -3.499 |
Token | : |
Token ID | 25 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
idth | +2.536 |
Spoiler | +1.876 |
avis | +1.567 |
ento | +1.558 |
psey | +1.498 |
Neg logit contributions | |
APH | -3.452 |
experien | -3.350 |
BuyableInstoreAndOnline | -3.348 |
thous | -3.300 |
�醒 | -3.295 |
Token | on |
Token ID | 319 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
APH | +6.166 |
ray | +5.369 |
Cyrus | +5.176 |
Pyro | +5.096 |
Geo | +5.026 |
Neg logit contributions | |
idth | -9.288 |
psey | -7.741 |
ento | -6.949 |
abase | -6.503 |
Spoiler | -6.302 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
APH | +6.717 |
Pyro | +5.859 |
ray | +5.721 |
ax | +5.716 |
� | +5.610 |
Neg logit contributions | |
idth | -8.583 |
psey | -6.847 |
Spoiler | -6.115 |
ento | -5.862 |
aunch | -5.655 |
Token | of |
Token ID | 286 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
APH | +2.306 |
ray | +2.090 |
Pyro | +2.054 |
experien | +2.048 |
xual | +2.022 |
Neg logit contributions | |
idth | -2.308 |
psey | -1.695 |
Spoiler | -1.631 |
ento | -1.505 |
aunch | -1.452 |
Token | Trump |
Token ID | 1301 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
APH | +5.301 |
Pyro | +4.800 |
Cyrus | +4.534 |
ray | +4.508 |
ax | +4.450 |
Neg logit contributions | |
idth | -7.033 |
psey | -5.598 |
Spoiler | -5.224 |
ento | -5.026 |
uning | -4.998 |
Token | - |
Token ID | 12 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
APH | +6.561 |
Pyro | +5.841 |
ray | +5.832 |
� | +5.632 |
ax | +5.443 |
Neg logit contributions | |
idth | -8.339 |
psey | -6.407 |
Spoiler | -5.933 |
ento | -5.620 |
avis | -5.421 |
Token | Kim |
Token ID | 26374 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
APH | +7.149 |
ray | +6.369 |
Pyro | +6.024 |
� | +5.708 |
ax | +5.649 |
Neg logit contributions | |
idth | -11.148 |
psey | -8.827 |
Spoiler | -8.322 |
ento | -7.602 |
avis | -7.599 |
Token | summit |
Token ID | 14237 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
APH | +7.368 |
ray | +6.361 |
Pyro | +5.925 |
� | +5.661 |
ax | +5.558 |
Neg logit contributions | |
idth | -17.057 |
psey | -12.723 |
avis | -12.384 |
abase | -12.364 |
Spoiler | -12.345 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
APH | +8.223 |
Pyro | +7.153 |
ray | +7.009 |
Cyrus | +6.970 |
� | +6.741 |
Neg logit contributions | |
idth | -11.502 |
psey | -9.321 |
Spoiler | -7.768 |
ento | -7.698 |
uning | -7.668 |
Token | 's |
Token ID | 338 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
APH | +5.418 |
ray | +4.863 |
Pyro | +4.855 |
� | +4.736 |
ax | +4.600 |
Neg logit contributions | |
idth | -5.794 |
psey | -4.368 |
Spoiler | -3.921 |
ento | -3.759 |
uning | -3.598 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
APH | +2.325 |
Pyro | +2.098 |
ray | +2.070 |
� | +2.011 |
experien | +1.979 |
Neg logit contributions | |
idth | -2.427 |
psey | -1.823 |
Spoiler | -1.688 |
ento | -1.566 |
aunch | -1.521 |
Token | say |
Token ID | 910 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
APH | +5.956 |
ray | +5.403 |
Pyro | +5.393 |
� | +5.253 |
ax | +5.140 |
Neg logit contributions | |
idth | -5.682 |
psey | -4.254 |
Spoiler | -3.818 |
ento | -3.626 |
avis | -3.466 |
Token | on |
Token ID | 319 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
APH | +5.860 |
ray | +5.140 |
Cyrus | +4.750 |
ax | +4.750 |
Pyro | +4.702 |
Neg logit contributions | |
idth | -9.088 |
psey | -7.664 |
ento | -6.837 |
abase | -6.361 |
Spoiler | -6.286 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
APH | +6.105 |
Pyro | +5.371 |
ray | +5.242 |
ax | +5.182 |
� | +5.139 |
Neg logit contributions | |
idth | -7.623 |
psey | -6.036 |
Spoiler | -5.397 |
ento | -5.176 |
aunch | -4.987 |
Token | of |
Token ID | 286 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
APH | +2.792 |
ray | +2.514 |
Pyro | +2.485 |
experien | +2.455 |
xual | +2.414 |
Neg logit contributions | |
idth | -2.857 |
psey | -2.102 |
Spoiler | -2.027 |
ento | -1.869 |
aunch | -1.809 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
APH | +5.162 |
Pyro | +4.660 |
Cyrus | +4.430 |
ray | +4.383 |
ax | +4.348 |
Neg logit contributions | |
idth | -7.023 |
psey | -5.646 |
Spoiler | -5.274 |
uning | -5.053 |
ento | -5.045 |
Token | - |
Token ID | 12 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
APH | +5.941 |
Pyro | +5.270 |
ray | +5.256 |
� | +5.074 |
experien | +4.906 |
Neg logit contributions | |
idth | -7.814 |
psey | -6.058 |
Spoiler | -5.628 |
ento | -5.334 |
uning | -5.158 |
Token | Kim |
Token ID | 26374 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
APH | +7.375 |
ray | +6.574 |
Pyro | +6.245 |
� | +5.915 |
ax | +5.850 |
Neg logit contributions | |
idth | -11.565 |
psey | -9.154 |
Spoiler | -8.578 |
ento | -7.866 |
avis | -7.830 |
Token | summit |
Token ID | 14237 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
APH | +7.329 |
ray | +6.317 |
Pyro | +5.854 |
� | +5.712 |
ax | +5.542 |
Neg logit contributions | |
idth | -16.995 |
psey | -12.745 |
avis | -12.325 |
abase | -12.305 |
netflix | -12.297 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
APH | +7.291 |
Pyro | +6.172 |
Cyrus | +5.992 |
ray | +5.912 |
Geo | +5.817 |
Neg logit contributions | |
idth | -13.320 |
psey | -11.205 |
uning | -9.371 |
aunch | -9.314 |
ento | -9.270 |
Token | 's |
Token ID | 338 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
APH | +5.374 |
ray | +4.820 |
Pyro | +4.810 |
� | +4.695 |
ax | +4.560 |
Neg logit contributions | |
idth | -5.695 |
psey | -4.284 |
Spoiler | -3.860 |
ento | -3.692 |
uning | -3.528 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
APH | +2.223 |
Pyro | +2.007 |
ray | +1.987 |
� | +1.927 |
experien | +1.894 |
Neg logit contributions | |
idth | -2.282 |
psey | -1.710 |
Spoiler | -1.582 |
ento | -1.467 |
aunch | -1.422 |
Token | say |
Token ID | 910 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
APH | +6.221 |
ray | +5.644 |
Pyro | +5.643 |
� | +5.491 |
ax | +5.361 |
Neg logit contributions | |
idth | -5.792 |
psey | -4.297 |
Spoiler | -3.868 |
ento | -3.661 |
avis | -3.492 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
APH | +0.520 |
ray | +0.468 |
Pyro | +0.452 |
experien | +0.452 |
xual | +0.447 |
Neg logit contributions | |
idth | -0.495 |
Spoiler | -0.361 |
psey | -0.357 |
ento | -0.320 |
uning | -0.311 |
Token |
|
Token ID | 198 |
Feature activation | +9.64e-03 |
Pos logit contributions | |
APH | +0.202 |
experien | +0.186 |
xual | +0.182 |
Pyro | +0.180 |
�醒 | +0.180 |
Neg logit contributions | |
idth | -0.151 |
Spoiler | -0.108 |
psey | -0.100 |
ento | -0.094 |
avis | -0.092 |
Token | 「 |
Token ID | 13697 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
idth | +0.111 |
psey | +0.078 |
Spoiler | +0.075 |
ento | +0.071 |
uning | +0.069 |
Neg logit contributions | |
APH | -0.122 |
Pyro | -0.114 |
xual | -0.112 |
ray | -0.110 |
experien | -0.110 |
Token | Ste |
Token ID | 7447 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
APH | +6.056 |
Pyro | +5.454 |
ray | +5.443 |
� | +5.273 |
experien | +5.140 |
Neg logit contributions | |
idth | -6.223 |
psey | -4.646 |
Spoiler | -4.278 |
ento | -4.014 |
uning | -3.853 |
Token | lla |
Token ID | 8466 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
APH | +5.438 |
ray | +4.907 |
Pyro | +4.884 |
� | +4.737 |
ax | +4.612 |
Neg logit contributions | |
idth | -6.012 |
psey | -4.536 |
Spoiler | -4.215 |
ento | -3.947 |
aunch | -3.781 |
Token | - |
Token ID | 12 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
APH | +2.499 |
Pyro | +2.232 |
ray | +2.228 |
� | +2.151 |
experien | +2.103 |
Neg logit contributions | |
idth | -2.774 |
psey | -2.094 |
Spoiler | -1.943 |
ento | -1.828 |
uning | -1.764 |
Token | san |
Token ID | 12807 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
APH | +9.800 |
ray | +9.389 |
Pyro | +8.812 |
� | +8.641 |
ax | +8.525 |
Neg logit contributions | |
idth | -13.326 |
psey | -10.509 |
Spoiler | -9.764 |
aunch | -8.899 |
ento | -8.898 |
Token | collapsed |
Token ID | 14707 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
APH | +5.252 |
ray | +4.735 |
Pyro | +4.712 |
� | +4.578 |
ax | +4.423 |
Neg logit contributions | |
idth | -6.387 |
psey | -4.938 |
Spoiler | -4.524 |
ento | -4.271 |
aunch | -4.137 |
Token | ?」 |
Token ID | 42943 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
APH | +2.681 |
Pyro | +2.401 |
ray | +2.386 |
� | +2.302 |
experien | +2.267 |
Neg logit contributions | |
idth | -2.560 |
psey | -1.918 |
Spoiler | -1.767 |
ento | -1.648 |
avis | -1.592 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
APH | +1.518 |
Pyro | +1.379 |
ray | +1.361 |
� | +1.323 |
ax | +1.276 |
Neg logit contributions | |
idth | -1.990 |
psey | -1.545 |
Spoiler | -1.404 |
ento | -1.336 |
aunch | -1.313 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
APH | +1.395 |
experien | +1.273 |
Pyro | +1.245 |
xual | +1.244 |
ray | +1.229 |
Neg logit contributions | |
idth | -1.126 |
Spoiler | -0.802 |
psey | -0.763 |
ento | -0.711 |
avis | -0.688 |
Token | call |
Token ID | 869 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
APH | +3.713 |
Pyro | +3.336 |
ray | +3.313 |
� | +3.233 |
experien | +3.135 |
Neg logit contributions | |
idth | -3.794 |
psey | -2.851 |
Spoiler | -2.642 |
ento | -2.462 |
aunch | -2.383 |
Token | NYPD |
Token ID | 27615 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
APH | +3.603 |
Pyro | +3.240 |
ray | +3.234 |
� | +3.135 |
experien | +3.042 |
Neg logit contributions | |
idth | -3.829 |
psey | -2.877 |
Spoiler | -2.640 |
ento | -2.487 |
uning | -2.391 |
Token | Crime |
Token ID | 10003 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
APH | +4.365 |
Pyro | +3.907 |
ray | +3.900 |
� | +3.779 |
experien | +3.654 |
Neg logit contributions | |
idth | -5.017 |
psey | -3.811 |
Spoiler | -3.510 |
ento | -3.317 |
uning | -3.197 |
Token | St |
Token ID | 520 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
APH | +3.491 |
Pyro | +3.022 |
ray | +3.005 |
� | +2.886 |
experien | +2.783 |
Neg logit contributions | |
idth | -5.555 |
psey | -4.452 |
Spoiler | -4.205 |
ento | -3.997 |
avis | -3.871 |
Token | oppers |
Token ID | 37186 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
APH | +4.335 |
ray | +3.769 |
Pyro | +3.653 |
� | +3.528 |
ax | +3.460 |
Neg logit contributions | |
idth | -9.008 |
psey | -7.227 |
Spoiler | -6.808 |
ento | -6.528 |
avis | -6.250 |
Token | at |
Token ID | 379 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
APH | +5.829 |
ray | +5.235 |
Pyro | +5.226 |
� | +5.090 |
ax | +4.910 |
Neg logit contributions | |
idth | -6.394 |
psey | -4.806 |
Spoiler | -4.417 |
ento | -4.166 |
uning | -3.990 |
Token | ( |
Token ID | 357 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
APH | +9.779 |
ray | +8.415 |
Pyro | +8.381 |
� | +8.347 |
Cyrus | +8.061 |
Neg logit contributions | |
idth | -14.062 |
psey | -10.988 |
Spoiler | -10.001 |
ento | -9.886 |
avis | -9.524 |
Token | 800 |
Token ID | 7410 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
APH | +3.342 |
Pyro | +3.047 |
ray | +2.988 |
� | +2.901 |
experien | +2.838 |
Neg logit contributions | |
idth | -4.260 |
psey | -3.279 |
Spoiler | -3.069 |
ento | -2.883 |
uning | -2.824 |
Token | ) |
Token ID | 8 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
APH | +4.031 |
ray | +3.665 |
Pyro | +3.623 |
xual | +3.592 |
experien | +3.589 |
Neg logit contributions | |
idth | -3.893 |
psey | -2.853 |
Spoiler | -2.786 |
ento | -2.530 |
aunch | -2.463 |
Token | 5 |
Token ID | 642 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
idth | +3.679 |
Spoiler | +2.733 |
psey | +2.699 |
aunch | +2.370 |
ento | +2.364 |
Neg logit contributions | |
APH | -3.569 |
ray | -3.318 |
xual | -3.297 |
Pyro | -3.271 |
experien | -3.226 |
Token | 77 |
Token ID | 3324 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
APH | +0.766 |
xual | +0.737 |
Pyro | +0.729 |
ray | +0.724 |
experien | +0.719 |
Neg logit contributions | |
idth | -0.687 |
Spoiler | -0.472 |
psey | -0.456 |
aunch | -0.419 |
ento | -0.407 |
Token | such |
Token ID | 884 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
APH | +1.078 |
ray | +0.962 |
Pyro | +0.950 |
� | +0.946 |
experien | +0.898 |
Neg logit contributions | |
idth | -1.026 |
psey | -0.753 |
Spoiler | -0.700 |
ento | -0.644 |
aunch | -0.631 |
Token | music |
Token ID | 2647 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
APH | +2.829 |
ray | +2.541 |
Pyro | +2.534 |
� | +2.468 |
ax | +2.383 |
Neg logit contributions | |
idth | -2.804 |
psey | -2.090 |
Spoiler | -1.923 |
ento | -1.796 |
uning | -1.730 |
Token | ( |
Token ID | 357 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
APH | +0.455 |
Pyro | +0.415 |
ray | +0.412 |
� | +0.404 |
experien | +0.387 |
Neg logit contributions | |
idth | -0.454 |
psey | -0.341 |
Spoiler | -0.315 |
ento | -0.294 |
uning | -0.283 |
Token | Ne |
Token ID | 8199 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
APH | +1.786 |
Pyro | +1.601 |
ray | +1.582 |
� | +1.532 |
experien | +1.507 |
Neg logit contributions | |
idth | -2.194 |
psey | -1.676 |
Spoiler | -1.559 |
ento | -1.488 |
uning | -1.438 |
Token | h |
Token ID | 71 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
APH | +1.820 |
Pyro | +1.623 |
ray | +1.579 |
� | +1.549 |
experien | +1.533 |
Neg logit contributions | |
idth | -2.309 |
psey | -1.789 |
Spoiler | -1.638 |
ento | -1.578 |
uning | -1.539 |
Token | ring |
Token ID | 1806 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
APH | +1.009 |
Pyro | +0.918 |
BuyableInstoreAndOnline | +0.901 |
experien | +0.900 |
�醒 | +0.873 |
Neg logit contributions | |
idth | -0.747 |
psey | -0.526 |
Spoiler | -0.465 |
uning | -0.460 |
avis | -0.437 |
Token | 99 |
Token ID | 7388 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
APH | +8.439 |
Pyro | +7.480 |
ray | +7.439 |
� | +7.360 |
ax | +7.181 |
Neg logit contributions | |
idth | -13.675 |
psey | -11.105 |
Spoiler | -9.964 |
ento | -9.424 |
aunch | -9.266 |
Token | ). |
Token ID | 737 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
APH | +3.183 |
Pyro | +2.843 |
ray | +2.835 |
� | +2.743 |
experien | +2.660 |
Neg logit contributions | |
idth | -3.796 |
psey | -2.903 |
Spoiler | -2.686 |
ento | -2.538 |
uning | -2.449 |
Token |
|
Token ID | 198 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
APH | +1.150 |
ray | +1.032 |
� | +0.990 |
experien | +0.989 |
Pyro | +0.989 |
Neg logit contributions | |
idth | -1.122 |
Spoiler | -0.834 |
psey | -0.814 |
ento | -0.729 |
uning | -0.717 |
Token |
|
Token ID | 198 |
Feature activation | -5.42e-03 |
Pos logit contributions | |
APH | +0.643 |
Pyro | +0.578 |
ray | +0.577 |
� | +0.557 |
experien | +0.545 |
Neg logit contributions | |
idth | -0.719 |
psey | -0.543 |
Spoiler | -0.504 |
ento | -0.474 |
uning | -0.457 |
Token | P |
Token ID | 47 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
APH | +0.065 |
Pyro | +0.061 |
ray | +0.059 |
experien | +0.059 |
xual | +0.059 |
Neg logit contributions | |
idth | -0.064 |
psey | -0.046 |
Spoiler | -0.045 |
ento | -0.042 |
uning | -0.041 |
Token | on |
Token ID | 319 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
APH | +5.098 |
ray | +4.506 |
ax | +4.175 |
� | +4.120 |
Pyro | +4.103 |
Neg logit contributions | |
idth | -7.973 |
psey | -6.634 |
ento | -5.974 |
abase | -5.541 |
Spoiler | -5.500 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
APH | +5.656 |
Pyro | +4.968 |
ray | +4.859 |
ax | +4.786 |
� | +4.778 |
Neg logit contributions | |
idth | -7.195 |
psey | -5.712 |
Spoiler | -5.126 |
ento | -4.933 |
aunch | -4.748 |
Token | of |
Token ID | 286 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
APH | +2.712 |
ray | +2.446 |
Pyro | +2.422 |
experien | +2.381 |
xual | +2.335 |
Neg logit contributions | |
idth | -2.768 |
psey | -2.050 |
Spoiler | -1.954 |
ento | -1.810 |
aunch | -1.751 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
APH | +4.988 |
Pyro | +4.473 |
Cyrus | +4.240 |
ray | +4.216 |
ax | +4.153 |
Neg logit contributions | |
idth | -6.994 |
psey | -5.663 |
Spoiler | -5.268 |
ento | -5.068 |
uning | -5.061 |
Token | - |
Token ID | 12 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
APH | +5.929 |
Pyro | +5.278 |
ray | +5.254 |
� | +5.082 |
experien | +4.947 |
Neg logit contributions | |
idth | -7.278 |
psey | -5.625 |
Spoiler | -5.227 |
ento | -4.925 |
uning | -4.770 |
Token | Kim |
Token ID | 26374 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
APH | +6.929 |
ray | +6.189 |
Pyro | +5.937 |
� | +5.603 |
ax | +5.531 |
Neg logit contributions | |
idth | -10.791 |
psey | -8.507 |
Spoiler | -8.014 |
ento | -7.327 |
avis | -7.257 |
Token | summit |
Token ID | 14237 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
APH | +7.025 |
ray | +6.009 |
Pyro | +5.661 |
� | +5.535 |
ax | +5.329 |
Neg logit contributions | |
idth | -16.435 |
psey | -12.384 |
avis | -11.978 |
netflix | -11.938 |
Spoiler | -11.886 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
APH | +6.221 |
Pyro | +5.293 |
ray | +5.080 |
Cyrus | +5.055 |
Geo | +4.917 |
Neg logit contributions | |
idth | -11.799 |
psey | -9.834 |
uning | -8.323 |
Spoiler | -8.287 |
aunch | -8.285 |
Token | 's |
Token ID | 338 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
APH | +4.528 |
ray | +4.064 |
Pyro | +4.059 |
� | +3.960 |
ax | +3.841 |
Neg logit contributions | |
idth | -4.752 |
psey | -3.570 |
Spoiler | -3.224 |
ento | -3.069 |
uning | -2.940 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
APH | +1.770 |
Pyro | +1.601 |
ray | +1.584 |
� | +1.535 |
experien | +1.513 |
Neg logit contributions | |
idth | -1.758 |
psey | -1.309 |
Spoiler | -1.211 |
ento | -1.121 |
aunch | -1.084 |
Token | say |
Token ID | 910 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
APH | +5.594 |
Pyro | +5.068 |
ray | +5.063 |
� | +4.923 |
ax | +4.786 |
Neg logit contributions | |
idth | -5.244 |
psey | -3.874 |
Spoiler | -3.513 |
ento | -3.299 |
uning | -3.156 |
Token | CLI |
Token ID | 43749 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
APH | +0.245 |
Pyro | +0.215 |
ray | +0.214 |
� | +0.212 |
xual | +0.208 |
Neg logit contributions | |
idth | -0.240 |
psey | -0.178 |
Spoiler | -0.167 |
ento | -0.160 |
uning | -0.152 |
Token | and |
Token ID | 290 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
APH | +0.967 |
Pyro | +0.862 |
ray | +0.856 |
� | +0.842 |
experien | +0.819 |
Neg logit contributions | |
idth | -0.896 |
psey | -0.658 |
Spoiler | -0.610 |
ento | -0.581 |
aunch | -0.558 |
Token | it |
Token ID | 340 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
idth | +0.769 |
psey | +0.552 |
Spoiler | +0.539 |
ento | +0.501 |
aunch | +0.479 |
Neg logit contributions | |
APH | -0.857 |
ray | -0.760 |
� | -0.747 |
xual | -0.739 |
Pyro | -0.739 |
Token | is |
Token ID | 318 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
idth | +1.461 |
psey | +1.035 |
Spoiler | +1.003 |
ento | +0.919 |
uning | +0.898 |
Neg logit contributions | |
APH | -1.897 |
Pyro | -1.689 |
ray | -1.676 |
� | -1.646 |
xual | -1.621 |
Token | available |
Token ID | 1695 |
Feature activation | +9.79e-03 |
Pos logit contributions | |
idth | +2.037 |
psey | +1.497 |
Spoiler | +1.421 |
ento | +1.304 |
aunch | +1.278 |
Neg logit contributions | |
APH | -2.740 |
ray | -2.456 |
Pyro | -2.418 |
xual | -2.393 |
� | -2.389 |
Token | as |
Token ID | 355 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
idth | +0.114 |
psey | +0.084 |
Spoiler | +0.078 |
ento | +0.073 |
uning | +0.070 |
Neg logit contributions | |
APH | -0.126 |
ray | -0.114 |
Pyro | -0.113 |
� | -0.109 |
experien | -0.109 |
Token | a |
Token ID | 257 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
idth | +4.798 |
Spoiler | +3.230 |
psey | +3.084 |
ento | +2.951 |
aunch | +2.761 |
Neg logit contributions | |
APH | -6.778 |
xual | -6.210 |
ray | -6.058 |
� | -6.026 |
Pyro | -5.903 |
Token | N |
Token ID | 399 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
idth | +2.865 |
Spoiler | +2.150 |
psey | +2.098 |
ento | +1.914 |
aunch | +1.835 |
Neg logit contributions | |
APH | -3.145 |
xual | -2.784 |
ray | -2.757 |
� | -2.720 |
�醒 | -2.650 |
Token | PM |
Token ID | 5868 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
idth | +0.844 |
psey | +0.590 |
Spoiler | +0.536 |
ento | +0.524 |
uning | +0.516 |
Neg logit contributions | |
APH | -0.950 |
Pyro | -0.884 |
xual | -0.864 |
experien | -0.862 |
ray | -0.861 |
Token | package |
Token ID | 5301 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
idth | +2.774 |
psey | +2.011 |
Spoiler | +1.921 |
ento | +1.811 |
uning | +1.762 |
Neg logit contributions | |
APH | -3.511 |
xual | -3.235 |
Pyro | -3.121 |
experien | -3.048 |
� | -3.038 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
APH | +0.632 |
Pyro | +0.562 |
ray | +0.552 |
� | +0.542 |
experien | +0.534 |
Neg logit contributions | |
idth | -0.587 |
psey | -0.434 |
Spoiler | -0.407 |
ento | -0.379 |
uning | -0.371 |
Token | the |
Token ID | 262 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
idth | +0.494 |
psey | +0.362 |
Spoiler | +0.339 |
ento | +0.302 |
uning | +0.301 |
Neg logit contributions | |
APH | -0.531 |
Pyro | -0.480 |
ray | -0.476 |
� | -0.465 |
experien | -0.458 |
Token | quo |
Token ID | 18658 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
idth | +2.918 |
psey | +2.167 |
Spoiler | +2.085 |
uning | +1.874 |
ento | +1.869 |
Neg logit contributions | |
APH | -3.007 |
� | -2.630 |
xual | -2.597 |
ray | -2.580 |
Pyro | -2.579 |
Token | – |
Token ID | 784 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
idth | +2.190 |
psey | +1.537 |
Spoiler | +1.499 |
ento | +1.306 |
avis | +1.300 |
Neg logit contributions | |
APH | -2.754 |
Pyro | -2.448 |
ray | -2.405 |
� | -2.387 |
experien | -2.376 |
Token | the |
Token ID | 262 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
APH | +1.580 |
Pyro | +1.426 |
ray | +1.409 |
� | +1.385 |
experien | +1.349 |
Neg logit contributions | |
idth | -1.561 |
psey | -1.165 |
Spoiler | -1.071 |
ento | -0.993 |
uning | -0.971 |
Token | actions |
Token ID | 4028 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
idth | +4.070 |
psey | +3.047 |
Spoiler | +2.934 |
uning | +2.617 |
ento | +2.608 |
Neg logit contributions | |
APH | -4.433 |
� | -3.872 |
Pyro | -3.791 |
xual | -3.782 |
ray | -3.775 |
Token | taken |
Token ID | 2077 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
idth | +1.996 |
psey | +1.479 |
Spoiler | +1.362 |
ento | +1.237 |
avis | +1.200 |
Neg logit contributions | |
APH | -2.346 |
Pyro | -2.094 |
ray | -2.073 |
� | -2.054 |
experien | -2.021 |
Token | by |
Token ID | 416 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
idth | +5.549 |
psey | +3.974 |
Spoiler | +3.817 |
ento | +3.319 |
avis | +3.266 |
Neg logit contributions | |
APH | -7.691 |
Pyro | -6.818 |
ray | -6.802 |
experien | -6.731 |
BuyableInstoreAndOnline | -6.670 |
Token | McDonnell |
Token ID | 39441 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
idth | +0.043 |
psey | +0.034 |
Spoiler | +0.032 |
ento | +0.030 |
uning | +0.030 |
Neg logit contributions | |
APH | -0.027 |
Pyro | -0.024 |
ray | -0.023 |
� | -0.023 |
experien | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
idth | +4.655 |
psey | +3.430 |
Spoiler | +3.286 |
ento | +2.930 |
uning | +2.846 |
Neg logit contributions | |
APH | -5.161 |
Pyro | -4.606 |
ray | -4.480 |
experien | -4.458 |
� | -4.347 |
Token | exchange |
Token ID | 5163 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
APH | +0.575 |
Pyro | +0.503 |
ray | +0.500 |
� | +0.496 |
experien | +0.478 |
Neg logit contributions | |
idth | -0.673 |
psey | -0.518 |
Spoiler | -0.482 |
ento | -0.451 |
uning | -0.441 |
Token | – |
Token ID | 784 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
idth | +3.508 |
psey | +2.642 |
Spoiler | +2.434 |
ento | +2.283 |
uning | +2.207 |
Neg logit contributions | |
APH | -3.270 |
Pyro | -2.935 |
ray | -2.923 |
� | -2.836 |
experien | -2.766 |
Token |
|
Token ID | 198 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
APH | +1.735 |
ray | +1.568 |
Pyro | +1.549 |
experien | +1.515 |
� | +1.495 |
Neg logit contributions | |
idth | -1.738 |
psey | -1.271 |
Spoiler | -1.269 |
ento | -1.122 |
avis | -1.081 |
Token |
|
Token ID | 198 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
idth | +0.577 |
Spoiler | +0.415 |
psey | +0.377 |
ento | +0.355 |
uning | +0.346 |
Neg logit contributions | |
APH | -0.813 |
experien | -0.763 |
xual | -0.749 |
thous | -0.742 |
�醒 | -0.740 |
Token | From |
Token ID | 4863 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
idth | +0.937 |
psey | +0.671 |
Spoiler | +0.667 |
ento | +0.604 |
uning | +0.584 |
Neg logit contributions | |
APH | -0.965 |
Pyro | -0.937 |
xual | -0.896 |
experien | -0.893 |
ray | -0.884 |
Token | John |
Token ID | 1757 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
idth | +0.162 |
psey | +0.120 |
Spoiler | +0.114 |
ento | +0.104 |
uning | +0.100 |
Neg logit contributions | |
APH | -0.165 |
ray | -0.149 |
Pyro | -0.149 |
� | -0.144 |
experien | -0.140 |
Token | Brian |
Token ID | 8403 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
idth | +1.680 |
psey | +1.213 |
Spoiler | +1.086 |
ento | +1.017 |
aunch | +0.968 |
Neg logit contributions | |
APH | -1.955 |
Pyro | -1.782 |
ray | -1.780 |
� | -1.739 |
ax | -1.683 |
Token | King |
Token ID | 2677 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
APH | +1.474 |
ray | +1.223 |
Pyro | +1.205 |
experien | +1.137 |
� | +1.114 |
Neg logit contributions | |
idth | -3.186 |
psey | -2.594 |
Spoiler | -2.538 |
ento | -2.349 |
uning | -2.324 |
Token | � |
Token ID | 447 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
idth | +5.532 |
psey | +3.994 |
Spoiler | +3.824 |
ento | +3.484 |
uning | +3.382 |
Neg logit contributions | |
APH | -6.073 |
Pyro | -5.611 |
ray | -5.446 |
experien | -5.303 |
� | -5.242 |
Token | � |
Token ID | 247 |
Feature activation | +9.14e-03 |
Pos logit contributions | |
idth | +1.746 |
psey | +1.360 |
Spoiler | +1.332 |
uning | +1.272 |
aunch | +1.239 |
Neg logit contributions | |
APH | -1.252 |
Skydragon | -1.105 |
Pyro | -1.097 |
ray | -1.053 |
BuyableInstoreAndOnline | -1.040 |
Token | s |
Token ID | 82 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
idth | +0.102 |
Spoiler | +0.072 |
psey | +0.072 |
ento | +0.065 |
aunch | +0.063 |
Neg logit contributions | |
APH | -0.121 |
Pyro | -0.108 |
BuyableInstoreAndOnline | -0.106 |
experien | -0.105 |
ray | -0.105 |
Token | book |
Token ID | 1492 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
idth | +3.246 |
psey | +2.263 |
Spoiler | +2.052 |
ento | +1.863 |
aunch | +1.776 |
Neg logit contributions | |
APH | -4.398 |
Pyro | -4.026 |
ray | -4.018 |
� | -3.904 |
experien | -3.830 |
Token | , |
Token ID | 11 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
idth | +2.494 |
psey | +1.915 |
Spoiler | +1.742 |
ento | +1.666 |
uning | +1.608 |
Neg logit contributions | |
APH | -2.098 |
ray | -1.866 |
Pyro | -1.865 |
� | -1.817 |
ax | -1.746 |
Token | ojure |
Token ID | 32511 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
APH | +4.016 |
Pyro | +3.608 |
ray | +3.547 |
� | +3.495 |
experien | +3.471 |
Neg logit contributions | |
idth | -3.700 |
psey | -2.706 |
Spoiler | -2.454 |
ento | -2.354 |
avis | -2.261 |
Token | / |
Token ID | 1220 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
idth | +0.645 |
psey | +0.432 |
Spoiler | +0.429 |
ento | +0.395 |
aunch | +0.371 |
Neg logit contributions | |
APH | -0.925 |
BuyableInstoreAndOnline | -0.812 |
Pyro | -0.805 |
experien | -0.804 |
Skydragon | -0.803 |
Token | tools |
Token ID | 4899 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
idth | +3.820 |
psey | +2.817 |
Spoiler | +2.730 |
ento | +2.474 |
uning | +2.426 |
Neg logit contributions | |
APH | -3.906 |
ray | -3.397 |
� | -3.391 |
Pyro | -3.356 |
xual | -3.350 |
Token | . |
Token ID | 764 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
idth | +0.253 |
psey | +0.204 |
Spoiler | +0.186 |
ento | +0.174 |
avis | +0.171 |
Neg logit contributions | |
APH | -0.167 |
Pyro | -0.149 |
ray | -0.148 |
� | -0.140 |
ax | -0.137 |
Token | cl |
Token ID | 537 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
idth | +4.336 |
psey | +3.254 |
Spoiler | +3.189 |
ento | +2.840 |
uning | +2.812 |
Neg logit contributions | |
APH | -4.185 |
ray | -3.618 |
� | -3.617 |
Pyro | -3.551 |
xual | -3.532 |
Token | i |
Token ID | 72 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
idth | +3.705 |
psey | +2.614 |
Spoiler | +2.349 |
ento | +2.325 |
aunch | +2.291 |
Neg logit contributions | |
APH | -4.357 |
Pyro | -3.927 |
� | -3.859 |
experien | -3.825 |
VIDEOS | -3.753 |
Token | | |
Token ID | 930 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
idth | +5.872 |
psey | +4.361 |
Spoiler | +4.024 |
aunch | +3.921 |
ento | +3.885 |
Neg logit contributions | |
APH | -5.389 |
� | -4.832 |
Pyro | -4.802 |
xual | -4.716 |
experien | -4.698 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
idth | +1.342 |
Spoiler | +0.959 |
psey | +0.893 |
ento | +0.837 |
Flores | +0.818 |
Neg logit contributions | |
APH | -1.651 |
ray | -1.471 |
xual | -1.465 |
Pyro | -1.444 |
experien | -1.436 |
Token | 53 |
Token ID | 4310 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
APH | +2.348 |
experien | +2.188 |
Pyro | +2.159 |
xual | +2.136 |
ray | +2.127 |
Neg logit contributions | |
idth | -1.992 |
Spoiler | -1.355 |
psey | -1.313 |
ento | -1.209 |
aunch | -1.189 |
Token | | |
Token ID | 930 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
idth | +0.444 |
Spoiler | +0.326 |
psey | +0.302 |
ento | +0.287 |
avis | +0.276 |
Neg logit contributions | |
APH | -0.486 |
experien | -0.455 |
BuyableInstoreAndOnline | -0.446 |
xual | -0.443 |
Pyro | -0.439 |
Token | | |
Token ID | 930 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
APH | +1.165 |
ray | +1.004 |
Pyro | +0.996 |
� | +0.947 |
ax | +0.930 |
Neg logit contributions | |
idth | -2.115 |
psey | -1.710 |
Spoiler | -1.538 |
ento | -1.525 |
avis | -1.476 |
Token | — |
Token ID | 851 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
APH | +2.125 |
Pyro | +1.915 |
ray | +1.903 |
� | +1.842 |
experien | +1.798 |
Neg logit contributions | |
idth | -2.039 |
psey | -1.514 |
Spoiler | -1.397 |
ento | -1.304 |
uning | -1.252 |
Token | whether |
Token ID | 1771 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
idth | +0.680 |
psey | +0.513 |
Spoiler | +0.482 |
ento | +0.450 |
aunch | +0.437 |
Neg logit contributions | |
APH | -0.624 |
Pyro | -0.561 |
ray | -0.552 |
� | -0.531 |
experien | -0.522 |
Token | it |
Token ID | 340 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
idth | +2.991 |
psey | +2.144 |
Spoiler | +2.091 |
ento | +1.908 |
clicked | +1.851 |
Neg logit contributions | |
APH | -3.564 |
Pyro | -3.153 |
ray | -3.146 |
者 | -3.097 |
� | -3.083 |
Token | is |
Token ID | 318 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
APH | +0.426 |
ray | +0.383 |
Pyro | +0.375 |
� | +0.363 |
ax | +0.360 |
Neg logit contributions | |
idth | -0.505 |
psey | -0.388 |
Spoiler | -0.354 |
ento | -0.330 |
aunch | -0.323 |
Token | food |
Token ID | 2057 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
idth | +1.166 |
psey | +0.891 |
Spoiler | +0.846 |
ento | +0.790 |
aunch | +0.762 |
Neg logit contributions | |
APH | -1.051 |
Pyro | -0.920 |
ray | -0.916 |
� | -0.891 |
experien | -0.871 |
Token | or |
Token ID | 393 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
idth | +1.576 |
psey | +1.195 |
Spoiler | +1.096 |
ento | +1.035 |
uning | +0.988 |
Neg logit contributions | |
APH | -1.506 |
Pyro | -1.354 |
ray | -1.347 |
� | -1.303 |
experien | -1.279 |
Token | space |
Token ID | 2272 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
idth | +5.645 |
psey | +4.121 |
Spoiler | +3.921 |
ento | +3.566 |
clicked | +3.515 |
Neg logit contributions | |
APH | -6.915 |
Pyro | -6.110 |
ray | -5.992 |
者 | -5.938 |
� | -5.910 |
Token | — |
Token ID | 851 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
idth | +3.022 |
psey | +2.198 |
Spoiler | +2.032 |
ento | +1.888 |
avis | +1.804 |
Neg logit contributions | |
APH | -3.452 |
ray | -3.111 |
Pyro | -3.109 |
experien | -2.953 |
� | -2.942 |
Token | your |
Token ID | 534 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
APH | +0.379 |
Pyro | +0.346 |
ray | +0.339 |
� | +0.333 |
experien | +0.324 |
Neg logit contributions | |
idth | -0.337 |
psey | -0.245 |
Spoiler | -0.225 |
ento | -0.208 |
uning | -0.201 |
Token | masters |
Token ID | 18159 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
idth | +1.089 |
psey | +0.798 |
Spoiler | +0.761 |
ento | +0.682 |
clicked | +0.656 |
Neg logit contributions | |
APH | -1.124 |
Pyro | -1.003 |
ray | -0.998 |
� | -0.971 |
xual | -0.944 |
Token | regard |
Token ID | 2754 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
APH | +0.295 |
Pyro | +0.266 |
ray | +0.262 |
� | +0.260 |
experien | +0.250 |
Neg logit contributions | |
idth | -0.271 |
psey | -0.201 |
Spoiler | -0.186 |
ento | -0.171 |
avis | -0.163 |
Token | was |
Token ID | 373 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
APH | +2.028 |
Pyro | +1.844 |
ray | +1.825 |
� | +1.780 |
experien | +1.733 |
Neg logit contributions | |
idth | -1.806 |
psey | -1.319 |
Spoiler | -1.211 |
ento | -1.126 |
uning | -1.089 |
Token | going |
Token ID | 1016 |
Feature activation | +2.04e-03 |
Pos logit contributions | |
idth | +1.722 |
psey | +1.263 |
Spoiler | +1.205 |
ento | +1.064 |
uning | +1.050 |
Neg logit contributions | |
APH | -2.169 |
ray | -1.906 |
Pyro | -1.896 |
� | -1.896 |
xual | -1.855 |
Token | to |
Token ID | 284 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
idth | +0.028 |
psey | +0.022 |
Spoiler | +0.020 |
ento | +0.019 |
uning | +0.019 |
Neg logit contributions | |
APH | -0.023 |
ray | -0.020 |
Pyro | -0.020 |
� | -0.019 |
ax | -0.019 |
Token | be |
Token ID | 307 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
APH | +1.677 |
Pyro | +1.505 |
ray | +1.496 |
� | +1.459 |
experien | +1.413 |
Neg logit contributions | |
idth | -1.780 |
psey | -1.342 |
Spoiler | -1.237 |
ento | -1.158 |
aunch | -1.120 |
Token | very |
Token ID | 845 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
idth | +3.711 |
psey | +2.722 |
Spoiler | +2.691 |
ento | +2.389 |
aunch | +2.325 |
Neg logit contributions | |
APH | -4.367 |
ray | -3.762 |
� | -3.758 |
Pyro | -3.743 |
xual | -3.666 |
Token | quiet |
Token ID | 5897 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
idth | +4.311 |
psey | +3.308 |
Spoiler | +3.196 |
ento | +2.825 |
aunch | +2.811 |
Neg logit contributions | |
APH | -4.954 |
ray | -4.343 |
� | -4.290 |
Pyro | -4.222 |
xual | -4.155 |
Token | and |
Token ID | 290 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
APH | +0.167 |
ray | +0.150 |
Pyro | +0.150 |
� | +0.146 |
experien | +0.141 |
Neg logit contributions | |
idth | -0.169 |
psey | -0.127 |
Spoiler | -0.117 |
ento | -0.109 |
uning | -0.106 |
Token | acoustic |
Token ID | 26071 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
idth | +0.965 |
psey | +0.725 |
Spoiler | +0.693 |
ento | +0.625 |
aunch | +0.609 |
Neg logit contributions | |
APH | -1.086 |
ray | -0.967 |
Pyro | -0.953 |
� | -0.945 |
xual | -0.918 |
Token | , |
Token ID | 11 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
APH | +0.987 |
Pyro | +0.885 |
ray | +0.883 |
� | +0.857 |
experien | +0.832 |
Neg logit contributions | |
idth | -1.059 |
psey | -0.800 |
Spoiler | -0.738 |
ento | -0.692 |
uning | -0.669 |
Token | with |
Token ID | 351 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
idth | +1.093 |
psey | +0.812 |
Spoiler | +0.768 |
ento | +0.688 |
uning | +0.681 |
Neg logit contributions | |
APH | -1.244 |
ray | -1.123 |
Pyro | -1.106 |
� | -1.091 |
xual | -1.062 |
Token | lots |
Token ID | 6041 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
idth | +1.971 |
psey | +1.443 |
Spoiler | +1.386 |
ento | +1.241 |
uning | +1.223 |
Neg logit contributions | |
APH | -2.278 |
ray | -2.021 |
� | -2.001 |
Pyro | -1.979 |
xual | -1.950 |
Token | support |
Token ID | 1104 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
APH | +3.550 |
Pyro | +3.187 |
ray | +3.178 |
� | +3.076 |
experien | +2.993 |
Neg logit contributions | |
idth | -3.856 |
psey | -2.913 |
Spoiler | -2.684 |
ento | -2.520 |
uning | -2.430 |
Token | in |
Token ID | 287 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
idth | +0.672 |
psey | +0.485 |
Spoiler | +0.453 |
ento | +0.418 |
avis | +0.407 |
Neg logit contributions | |
APH | -0.766 |
Pyro | -0.689 |
ray | -0.682 |
� | -0.663 |
experien | -0.651 |
Token | the |
Token ID | 262 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
idth | +0.910 |
psey | +0.659 |
Spoiler | +0.605 |
ento | +0.549 |
avis | +0.533 |
Neg logit contributions | |
APH | -1.108 |
ray | -1.009 |
Pyro | -1.001 |
� | -0.972 |
experien | -0.950 |
Token | House |
Token ID | 2097 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
APH | +1.051 |
ray | +0.933 |
Pyro | +0.926 |
� | +0.894 |
experien | +0.873 |
Neg logit contributions | |
idth | -1.211 |
psey | -0.940 |
Spoiler | -0.881 |
ento | -0.821 |
avis | -0.802 |
Token | of |
Token ID | 286 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
idth | +0.187 |
psey | +0.141 |
Spoiler | +0.133 |
ento | +0.124 |
avis | +0.120 |
Neg logit contributions | |
APH | -0.173 |
Pyro | -0.154 |
ray | -0.153 |
� | -0.148 |
experien | -0.145 |
Token | Representatives |
Token ID | 17132 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
APH | +1.600 |
Pyro | +1.387 |
ray | +1.383 |
� | +1.329 |
experien | +1.277 |
Neg logit contributions | |
idth | -2.664 |
psey | -2.119 |
Spoiler | -1.995 |
ento | -1.900 |
uning | -1.844 |
Token | forms |
Token ID | 5107 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
idth | +0.835 |
psey | +0.604 |
Spoiler | +0.585 |
ento | +0.530 |
aunch | +0.507 |
Neg logit contributions | |
APH | -0.989 |
Pyro | -0.881 |
ray | -0.879 |
� | -0.861 |
experien | -0.846 |
Token | the |
Token ID | 262 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
APH | +1.178 |
Pyro | +1.062 |
ray | +1.061 |
� | +1.035 |
experien | +1.010 |
Neg logit contributions | |
idth | -1.073 |
psey | -0.781 |
Spoiler | -0.719 |
ento | -0.666 |
avis | -0.643 |
Token | government |
Token ID | 1230 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
APH | +3.485 |
Pyro | +3.090 |
ray | +3.088 |
� | +3.013 |
experien | +2.922 |
Neg logit contributions | |
idth | -3.474 |
psey | -2.595 |
Spoiler | -2.444 |
ento | -2.240 |
avis | -2.186 |
Token | and |
Token ID | 290 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
APH | +0.555 |
Pyro | +0.501 |
ray | +0.491 |
� | +0.485 |
experien | +0.477 |
Neg logit contributions | |
idth | -0.518 |
psey | -0.381 |
Spoiler | -0.360 |
ento | -0.330 |
avis | -0.324 |
Token | its |
Token ID | 663 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
APH | +1.612 |
Pyro | +1.443 |
ray | +1.438 |
� | +1.416 |
experien | +1.364 |
Neg logit contributions | |
idth | -1.409 |
psey | -1.028 |
Spoiler | -0.961 |
ento | -0.879 |
avis | -0.852 |
Token | food |
Token ID | 2057 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
idth | +1.969 |
psey | +1.441 |
Spoiler | +1.409 |
ento | +1.275 |
avis | +1.204 |
Neg logit contributions | |
APH | -2.071 |
Pyro | -1.869 |
ray | -1.811 |
experien | -1.790 |
xual | -1.764 |
Token | . |
Token ID | 13 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
idth | +3.372 |
psey | +2.495 |
Spoiler | +2.401 |
ento | +2.179 |
uning | +2.055 |
Neg logit contributions | |
APH | -3.688 |
ray | -3.326 |
Pyro | -3.322 |
� | -3.177 |
experien | -3.176 |
Token | What |
Token ID | 1867 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
idth | +3.541 |
Spoiler | +2.855 |
psey | +2.557 |
ento | +2.353 |
Flores | +2.300 |
Neg logit contributions | |
APH | -3.816 |
experien | -3.427 |
ray | -3.402 |
Pyro | -3.307 |
xual | -3.302 |
Token | were |
Token ID | 547 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
APH | +2.597 |
ray | +2.345 |
Pyro | +2.332 |
� | +2.243 |
experien | +2.216 |
Neg logit contributions | |
idth | -2.339 |
psey | -1.690 |
Spoiler | -1.595 |
ento | -1.441 |
aunch | -1.405 |
Token | we |
Token ID | 356 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
APH | +0.412 |
Pyro | +0.372 |
ray | +0.372 |
� | +0.357 |
ax | +0.354 |
Neg logit contributions | |
idth | -0.369 |
psey | -0.265 |
Spoiler | -0.248 |
ento | -0.222 |
aunch | -0.217 |
Token | supposed |
Token ID | 4385 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
APH | +2.904 |
Pyro | +2.639 |
ray | +2.619 |
ax | +2.505 |
� | +2.495 |
Neg logit contributions | |
idth | -2.332 |
psey | -1.655 |
Spoiler | -1.548 |
ento | -1.392 |
uning | -1.334 |
Token | to |
Token ID | 284 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
idth | +1.957 |
psey | +1.251 |
Spoiler | +1.244 |
ento | +1.096 |
aunch | +1.042 |
Neg logit contributions | |
APH | -2.935 |
BuyableInstoreAndOnline | -2.755 |
experien | -2.725 |
Pyro | -2.719 |
ray | -2.670 |
Token | do |
Token ID | 466 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
APH | +0.886 |
ray | +0.787 |
Pyro | +0.785 |
� | +0.756 |
experien | +0.741 |
Neg logit contributions | |
idth | -0.805 |
psey | -0.575 |
Spoiler | -0.540 |
ento | -0.499 |
aunch | -0.481 |
Token | ? |
Token ID | 30 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
APH | +1.293 |
ray | +1.157 |
Pyro | +1.156 |
� | +1.105 |
experien | +1.101 |
Neg logit contributions | |
idth | -1.244 |
psey | -0.913 |
Spoiler | -0.858 |
ento | -0.796 |
aunch | -0.760 |
Token | Force |
Token ID | 5221 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
idth | +1.093 |
Spoiler | +0.849 |
psey | +0.787 |
ento | +0.701 |
aunch | +0.691 |
Neg logit contributions | |
APH | -1.145 |
ray | -0.999 |
experien | -0.984 |
Pyro | -0.976 |
xual | -0.975 |
Token | our |
Token ID | 674 |
Feature activation | +4.23e-03 |
Pos logit contributions | |
idth | +1.269 |
psey | +0.930 |
Spoiler | +0.895 |
ento | +0.813 |
avis | +0.788 |
Neg logit contributions | |
APH | -1.344 |
ray | -1.192 |
Pyro | -1.185 |
� | -1.144 |
experien | -1.142 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
APH | +2.609 |
ray | +2.343 |
Pyro | +2.316 |
experien | +2.286 |
xual | +2.247 |
Neg logit contributions | |
idth | -2.577 |
psey | -1.897 |
Spoiler | -1.888 |
ento | -1.658 |
avis | -1.628 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
APH | +2.012 |
experien | +1.823 |
Pyro | +1.806 |
xual | +1.790 |
ray | +1.774 |
Neg logit contributions | |
idth | -1.692 |
Spoiler | -1.203 |
psey | -1.172 |
ento | -1.070 |
avis | -1.042 |
Token | In |
Token ID | 818 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
APH | +2.189 |
Pyro | +2.059 |
ray | +1.978 |
xual | +1.967 |
experien | +1.964 |
Neg logit contributions | |
idth | -2.039 |
psey | -1.474 |
Spoiler | -1.403 |
ento | -1.284 |
avis | -1.253 |
Token | the |
Token ID | 262 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
idth | +0.020 |
psey | +0.014 |
Spoiler | +0.013 |
ento | +0.012 |
avis | +0.012 |
Neg logit contributions | |
APH | -0.022 |
Pyro | -0.019 |
ray | -0.019 |
� | -0.019 |
experien | -0.019 |
Token | Patriots |
Token ID | 13104 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
APH | +0.705 |
ray | +0.618 |
Pyro | +0.614 |
� | +0.603 |
xual | +0.591 |
Neg logit contributions | |
idth | -0.639 |
psey | -0.488 |
Spoiler | -0.465 |
ento | -0.416 |
uning | -0.407 |
Token | ' |
Token ID | 6 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
idth | +2.105 |
psey | +1.589 |
Spoiler | +1.526 |
ento | +1.356 |
aunch | +1.344 |
Neg logit contributions | |
APH | -2.415 |
Pyro | -2.122 |
ray | -2.079 |
xual | -2.034 |
� | -2.017 |
Token | first |
Token ID | 717 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
idth | +1.726 |
psey | +1.332 |
Spoiler | +1.283 |
uning | +1.123 |
aunch | +1.117 |
Neg logit contributions | |
APH | -1.982 |
ray | -1.720 |
Pyro | -1.690 |
xual | -1.670 |
� | -1.653 |
Token | preseason |
Token ID | 18913 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
idth | +3.983 |
psey | +2.961 |
Spoiler | +2.932 |
ento | +2.574 |
aunch | +2.544 |
Neg logit contributions | |
APH | -4.809 |
Pyro | -4.275 |
ray | -4.260 |
xual | -4.222 |
BuyableInstoreAndOnline | -4.178 |
Token | game |
Token ID | 983 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
APH | +0.669 |
Pyro | +0.595 |
ray | +0.593 |
� | +0.568 |
xual | +0.557 |
Neg logit contributions | |
idth | -0.720 |
psey | -0.545 |
Spoiler | -0.521 |
ento | -0.489 |
aunch | -0.470 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
APH | +0.449 |
Pyro | +0.405 |
ray | +0.404 |
� | +0.392 |
experien | +0.387 |
Neg logit contributions | |
idth | -0.390 |
psey | -0.287 |
Spoiler | -0.266 |
ento | -0.247 |
avis | -0.235 |
Token | against |
Token ID | 1028 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
APH | +0.134 |
Pyro | +0.118 |
ray | +0.118 |
xual | +0.114 |
� | +0.114 |
Neg logit contributions | |
idth | -0.128 |
psey | -0.095 |
Spoiler | -0.090 |
ento | -0.080 |
avis | -0.080 |
Token | Val |
Token ID | 3254 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
APH | +0.886 |
Pyro | +0.797 |
ray | +0.793 |
� | +0.768 |
ax | +0.742 |
Neg logit contributions | |
idth | -1.049 |
psey | -0.801 |
Spoiler | -0.738 |
ento | -0.699 |
uning | -0.673 |
Token | er |
Token ID | 263 |
Feature activation | -5.46e-03 |
Pos logit contributions | |
APH | +0.134 |
Pyro | +0.119 |
experien | +0.113 |
� | +0.112 |
BuyableInstoreAndOnline | +0.111 |
Neg logit contributions | |
idth | -0.151 |
psey | -0.117 |
ento | -0.106 |
Spoiler | -0.103 |
uning | -0.100 |
Token | io |
Token ID | 952 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
APH | +0.074 |
BuyableInstoreAndOnline | +0.064 |
experien | +0.064 |
� | +0.063 |
Pyro | +0.063 |
Neg logit contributions | |
idth | -0.063 |
psey | -0.045 |
ento | -0.044 |
Spoiler | -0.042 |
uning | -0.040 |
Token | Borg |
Token ID | 29004 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
idth | +1.493 |
psey | +1.152 |
Spoiler | +1.063 |
ento | +1.014 |
aunch | +0.978 |
Neg logit contributions | |
APH | -1.132 |
Pyro | -1.015 |
ray | -1.010 |
� | -0.976 |
ax | -0.948 |
Token | he |
Token ID | 258 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
idth | +0.975 |
psey | +0.659 |
Spoiler | +0.592 |
ento | +0.582 |
uning | +0.549 |
Neg logit contributions | |
APH | -1.269 |
�醒 | -1.160 |
Pyro | -1.155 |
experien | -1.143 |
BuyableInstoreAndOnline | -1.142 |
Token | se |
Token ID | 325 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
APH | +0.165 |
experien | +0.142 |
Pyro | +0.140 |
BuyableInstoreAndOnline | +0.140 |
�醒 | +0.138 |
Neg logit contributions | |
idth | -0.187 |
psey | -0.140 |
Spoiler | -0.133 |
ento | -0.131 |
avis | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
idth | +0.632 |
psey | +0.475 |
Spoiler | +0.441 |
ento | +0.412 |
uning | +0.402 |
Neg logit contributions | |
APH | -0.611 |
ray | -0.540 |
Pyro | -0.540 |
� | -0.524 |
experien | -0.515 |
Token | Borg |
Token ID | 29004 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
idth | +1.537 |
Spoiler | +1.182 |
psey | +1.093 |
avis | +1.002 |
uning | +0.975 |
Neg logit contributions | |
APH | -1.724 |
ray | -1.558 |
xual | -1.516 |
experien | -1.502 |
Pyro | -1.474 |
Token | he |
Token ID | 258 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
idth | +0.966 |
psey | +0.639 |
Spoiler | +0.597 |
ento | +0.580 |
uning | +0.559 |
Neg logit contributions | |
APH | -1.269 |
�醒 | -1.167 |
Pyro | -1.156 |
experien | -1.145 |
BuyableInstoreAndOnline | -1.127 |
Token | se |
Token ID | 325 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
idth | +0.021 |
psey | +0.015 |
Spoiler | +0.014 |
ento | +0.014 |
avis | +0.014 |
Neg logit contributions | |
APH | -0.018 |
experien | -0.015 |
Pyro | -0.015 |
BuyableInstoreAndOnline | -0.015 |
�醒 | -0.015 |
Token | held |
Token ID | 2714 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
APH | +1.592 |
Pyro | +1.432 |
ray | +1.431 |
� | +1.391 |
experien | +1.364 |
Neg logit contributions | |
idth | -1.306 |
psey | -0.948 |
Spoiler | -0.859 |
ento | -0.792 |
uning | -0.772 |
Token | now |
Token ID | 783 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
APH | +0.582 |
Pyro | +0.518 |
ray | +0.517 |
� | +0.510 |
experien | +0.494 |
Neg logit contributions | |
idth | -0.497 |
psey | -0.362 |
Spoiler | -0.330 |
ento | -0.304 |
uning | -0.298 |
Token | there |
Token ID | 612 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
APH | +1.802 |
ray | +1.609 |
Pyro | +1.602 |
� | +1.566 |
experien | +1.517 |
Neg logit contributions | |
idth | -1.713 |
psey | -1.259 |
Spoiler | -1.172 |
ento | -1.086 |
uning | -1.044 |
Token | 's |
Token ID | 338 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
APH | +2.808 |
Pyro | +2.535 |
ray | +2.534 |
� | +2.455 |
experien | +2.385 |
Neg logit contributions | |
idth | -2.830 |
psey | -2.109 |
Spoiler | -1.932 |
ento | -1.814 |
uning | -1.737 |
Token | very |
Token ID | 845 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
idth | +1.785 |
psey | +1.273 |
Spoiler | +1.166 |
ento | +1.049 |
uning | +1.034 |
Neg logit contributions | |
APH | -2.359 |
Pyro | -2.088 |
ray | -2.080 |
� | -2.068 |
ゴ | -1.996 |
Token | few |
Token ID | 1178 |
Feature activation | -7.98e-02 |
Pos logit contributions | |
APH | +1.871 |
Pyro | +1.680 |
ray | +1.678 |
� | +1.637 |
ax | +1.583 |
Neg logit contributions | |
idth | -1.759 |
psey | -1.304 |
Spoiler | -1.190 |
ento | -1.104 |
uning | -1.072 |
Token | people |
Token ID | 661 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
APH | +0.987 |
ray | +0.867 |
Pyro | +0.860 |
� | +0.849 |
ax | +0.812 |
Neg logit contributions | |
idth | -1.001 |
psey | -0.751 |
Spoiler | -0.707 |
ento | -0.647 |
uning | -0.637 |
Token | who |
Token ID | 508 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
APH | +3.558 |
Pyro | +3.187 |
ray | +3.173 |
� | +3.085 |
experien | +2.986 |
Neg logit contributions | |
idth | -3.636 |
psey | -2.731 |
Spoiler | -2.523 |
ento | -2.367 |
uning | -2.272 |
Token | are |
Token ID | 389 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
APH | +3.156 |
Pyro | +2.820 |
ray | +2.792 |
� | +2.755 |
ax | +2.643 |
Neg logit contributions | |
idth | -2.979 |
psey | -2.219 |
Spoiler | -2.025 |
ento | -1.893 |
aunch | -1.814 |
Token | really |
Token ID | 1107 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
APH | +3.683 |
Pyro | +3.316 |
ray | +3.302 |
� | +3.227 |
ax | +3.109 |
Neg logit contributions | |
idth | -3.400 |
psey | -2.518 |
Spoiler | -2.303 |
ento | -2.156 |
uning | -2.074 |
Token | interested |
Token ID | 4609 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
APH | +2.811 |
Pyro | +2.523 |
ray | +2.513 |
� | +2.458 |
ax | +2.359 |
Neg logit contributions | |
idth | -2.664 |
psey | -1.975 |
Spoiler | -1.815 |
ento | -1.706 |
uning | -1.649 |
Token | in |
Token ID | 287 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
APH | +2.626 |
ray | +2.342 |
Pyro | +2.322 |
� | +2.261 |
ax | +2.229 |
Neg logit contributions | |
idth | -3.960 |
psey | -3.133 |
Spoiler | -2.804 |
ento | -2.713 |
uning | -2.637 |
Token | od |
Token ID | 375 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
idth | +4.800 |
psey | +3.576 |
Spoiler | +3.258 |
ento | +3.148 |
avis | +3.076 |
Neg logit contributions | |
APH | -4.670 |
Pyro | -4.209 |
� | -4.077 |
ray | -4.042 |
experien | -4.012 |
Token | had |
Token ID | 550 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
idth | +0.390 |
psey | +0.286 |
Spoiler | +0.268 |
ento | +0.248 |
avis | +0.246 |
Neg logit contributions | |
APH | -0.403 |
Pyro | -0.359 |
ray | -0.355 |
� | -0.350 |
experien | -0.342 |
Token | caused |
Token ID | 4073 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
APH | +1.736 |
Pyro | +1.582 |
ray | +1.561 |
� | +1.549 |
xual | +1.492 |
Neg logit contributions | |
idth | -1.335 |
psey | -0.949 |
Spoiler | -0.855 |
ento | -0.801 |
aunch | -0.765 |
Token | destruction |
Token ID | 8166 |
Feature activation | +2.14e-03 |
Pos logit contributions | |
idth | +0.449 |
psey | +0.336 |
Spoiler | +0.309 |
ento | +0.284 |
uning | +0.282 |
Neg logit contributions | |
APH | -0.477 |
Pyro | -0.422 |
ray | -0.422 |
� | -0.418 |
experien | -0.401 |
Token | to |
Token ID | 284 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
idth | +0.030 |
psey | +0.023 |
Spoiler | +0.021 |
ento | +0.020 |
aunch | +0.019 |
Neg logit contributions | |
APH | -0.023 |
Pyro | -0.021 |
ray | -0.021 |
� | -0.020 |
experien | -0.019 |
Token | man |
Token ID | 582 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
idth | +1.257 |
psey | +0.951 |
Spoiler | +0.862 |
ento | +0.798 |
uning | +0.783 |
Neg logit contributions | |
APH | -1.349 |
ray | -1.211 |
Pyro | -1.203 |
� | -1.183 |
experien | -1.142 |
Token | gro |
Token ID | 27333 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
APH | +0.882 |
Pyro | +0.684 |
ray | +0.667 |
� | +0.627 |
experien | +0.591 |
Neg logit contributions | |
idth | -2.978 |
psey | -2.499 |
Spoiler | -2.374 |
ento | -2.297 |
uning | -2.253 |
Token | ves |
Token ID | 1158 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
idth | +1.472 |
psey | +1.140 |
Spoiler | +1.047 |
avis | +1.047 |
uning | +1.018 |
Neg logit contributions | |
APH | -1.059 |
ray | -0.945 |
Pyro | -0.936 |
BuyableInstoreAndOnline | -0.934 |
experien | -0.929 |
Token | thr |
Token ID | 5636 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
idth | +0.523 |
psey | +0.392 |
Spoiler | +0.361 |
ento | +0.331 |
uning | +0.330 |
Neg logit contributions | |
APH | -0.549 |
Pyro | -0.490 |
ray | -0.488 |
� | -0.477 |
experien | -0.466 |
Token | ice |
Token ID | 501 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
idth | +0.333 |
psey | +0.240 |
Spoiler | +0.216 |
ento | +0.200 |
uning | +0.197 |
Neg logit contributions | |
APH | -0.385 |
Pyro | -0.351 |
ray | -0.349 |
� | -0.341 |
experien | -0.335 |
Token | in |
Token ID | 287 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
APH | +2.876 |
Pyro | +2.597 |
ray | +2.585 |
� | +2.508 |
experien | +2.439 |
Neg logit contributions | |
idth | -2.930 |
psey | -2.201 |
Spoiler | -2.023 |
ento | -1.894 |
uning | -1.832 |
Token | an |
Token ID | 281 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
APH | +0.693 |
Pyro | +0.626 |
ray | +0.619 |
� | +0.605 |
experien | +0.590 |
Neg logit contributions | |
idth | -0.624 |
psey | -0.458 |
Spoiler | -0.417 |
ento | -0.384 |
uning | -0.375 |
Token | obvious |
Token ID | 3489 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
APH | +1.769 |
Pyro | +1.611 |
ray | +1.589 |
� | +1.557 |
xual | +1.515 |
Neg logit contributions | |
idth | -1.749 |
psey | -1.301 |
Spoiler | -1.193 |
ento | -1.116 |
avis | -1.090 |
Token | need |
Token ID | 761 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
APH | +1.919 |
Pyro | +1.698 |
ray | +1.698 |
� | +1.658 |
xual | +1.619 |
Neg logit contributions | |
idth | -1.990 |
psey | -1.492 |
Spoiler | -1.420 |
ento | -1.283 |
uning | -1.254 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
APH | +2.058 |
� | +1.843 |
ray | +1.835 |
Pyro | +1.766 |
ax | +1.739 |
Neg logit contributions | |
idth | -3.011 |
psey | -2.351 |
Spoiler | -2.234 |
ento | -2.101 |
avis | -2.006 |
Token | too |
Token ID | 1165 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
APH | +1.703 |
ray | +1.545 |
Pyro | +1.533 |
� | +1.496 |
experien | +1.468 |
Neg logit contributions | |
idth | -1.395 |
psey | -1.014 |
Spoiler | -0.933 |
ento | -0.836 |
uning | -0.821 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
idth | +1.240 |
psey | +0.991 |
Spoiler | +0.906 |
ento | +0.884 |
aunch | +0.853 |
Neg logit contributions | |
APH | -0.867 |
ray | -0.768 |
� | -0.758 |
Pyro | -0.755 |
ax | -0.713 |
Token | for |
Token ID | 329 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
APH | +1.508 |
Pyro | +1.349 |
ray | +1.342 |
� | +1.330 |
ax | +1.271 |
Neg logit contributions | |
idth | -1.808 |
psey | -1.377 |
Spoiler | -1.287 |
ento | -1.218 |
aunch | -1.166 |
Token | schemes |
Token ID | 16546 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
idth | +0.775 |
psey | +0.579 |
Spoiler | +0.525 |
ento | +0.488 |
uning | +0.478 |
Neg logit contributions | |
APH | -0.822 |
ray | -0.737 |
Pyro | -0.731 |
� | -0.720 |
experien | -0.701 |
Token | to |
Token ID | 284 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
idth | +0.750 |
psey | +0.557 |
Spoiler | +0.497 |
ento | +0.475 |
uning | +0.459 |
Neg logit contributions | |
APH | -0.854 |
Pyro | -0.774 |
ray | -0.763 |
� | -0.744 |
experien | -0.741 |
Token | compensate |
Token ID | 21392 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
APH | +0.248 |
� | +0.218 |
Pyro | +0.215 |
ray | +0.214 |
experien | +0.208 |
Neg logit contributions | |
idth | -0.228 |
psey | -0.170 |
Spoiler | -0.155 |
aunch | -0.142 |
ento | -0.142 |
Token | current |
Token ID | 1459 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
idth | +2.572 |
psey | +1.829 |
Spoiler | +1.692 |
ento | +1.565 |
aunch | +1.522 |
Neg logit contributions | |
APH | -2.898 |
ray | -2.622 |
Pyro | -2.610 |
� | -2.545 |
xual | -2.462 |
Token | the |
Token ID | 262 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
idth | +0.798 |
psey | +0.570 |
Spoiler | +0.538 |
ento | +0.475 |
aunch | +0.466 |
Neg logit contributions | |
APH | -0.994 |
Pyro | -0.899 |
� | -0.894 |
ray | -0.893 |
xual | -0.875 |
Token | fastest |
Token ID | 14162 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
APH | +0.718 |
ray | +0.637 |
Pyro | +0.636 |
� | +0.630 |
xual | +0.615 |
Neg logit contributions | |
idth | -0.663 |
psey | -0.491 |
Spoiler | -0.463 |
ento | -0.424 |
avis | -0.409 |
Token | rate |
Token ID | 2494 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
APH | +1.176 |
Pyro | +1.053 |
ray | +1.049 |
� | +1.024 |
xual | +1.000 |
Neg logit contributions | |
idth | -1.201 |
psey | -0.881 |
Spoiler | -0.838 |
ento | -0.762 |
uning | -0.747 |
Token | in |
Token ID | 287 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
APH | +2.366 |
Pyro | +2.135 |
ray | +2.124 |
� | +2.061 |
experien | +2.005 |
Neg logit contributions | |
idth | -2.405 |
psey | -1.798 |
Spoiler | -1.662 |
ento | -1.551 |
uning | -1.487 |
Token | seven |
Token ID | 3598 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
idth | +1.507 |
psey | +1.082 |
Spoiler | +1.031 |
ento | +0.937 |
aunch | +0.906 |
Neg logit contributions | |
APH | -1.777 |
ray | -1.606 |
Pyro | -1.588 |
� | -1.579 |
xual | -1.550 |
Token | years |
Token ID | 812 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
idth | +4.029 |
psey | +2.974 |
Spoiler | +2.833 |
ento | +2.648 |
uning | +2.529 |
Neg logit contributions | |
APH | -3.871 |
ray | -3.452 |
Pyro | -3.441 |
xual | -3.383 |
� | -3.363 |
Token | , |
Token ID | 11 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
APH | +2.317 |
Pyro | +2.083 |
ray | +2.069 |
� | +2.001 |
experien | +1.947 |
Neg logit contributions | |
idth | -2.590 |
psey | -1.961 |
Spoiler | -1.819 |
ento | -1.706 |
uning | -1.648 |
Token | with |
Token ID | 351 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
APH | +4.385 |
Pyro | +3.974 |
ray | +3.967 |
� | +3.861 |
experien | +3.743 |
Neg logit contributions | |
idth | -3.925 |
psey | -2.873 |
Spoiler | -2.638 |
ento | -2.433 |
uning | -2.347 |
Token | some |
Token ID | 617 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
APH | +2.276 |
Pyro | +2.057 |
ray | +2.048 |
� | +2.012 |
xual | +1.942 |
Neg logit contributions | |
idth | -2.262 |
psey | -1.680 |
Spoiler | -1.553 |
ento | -1.437 |
aunch | -1.376 |
Token | communities |
Token ID | 5348 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
idth | +0.343 |
psey | +0.256 |
Spoiler | +0.237 |
ento | +0.215 |
uning | +0.212 |
Neg logit contributions | |
APH | -0.359 |
Pyro | -0.329 |
ray | -0.320 |
� | -0.319 |
xual | -0.318 |
Token | seeing |
Token ID | 4379 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
APH | +0.292 |
Pyro | +0.266 |
ray | +0.260 |
xual | +0.258 |
� | +0.258 |
Neg logit contributions | |
idth | -0.226 |
psey | -0.167 |
Spoiler | -0.150 |
ento | -0.141 |
uning | -0.133 |
Token | � |
Token ID | 447 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
APH | +1.218 |
ray | +1.088 |
Pyro | +1.086 |
� | +1.042 |
experien | +1.034 |
Neg logit contributions | |
idth | -1.202 |
psey | -0.887 |
Spoiler | -0.843 |
ento | -0.768 |
uning | -0.740 |
Token | � |
Token ID | 247 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
APH | +0.182 |
Pyro | +0.157 |
ray | +0.157 |
� | +0.151 |
ax | +0.145 |
Neg logit contributions | |
idth | -0.312 |
psey | -0.250 |
Spoiler | -0.234 |
ento | -0.223 |
aunch | -0.216 |
Token | s |
Token ID | 82 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
APH | +2.208 |
Pyro | +1.983 |
ray | +1.965 |
� | +1.899 |
experien | +1.867 |
Neg logit contributions | |
idth | -2.382 |
psey | -1.789 |
Spoiler | -1.666 |
ento | -1.554 |
uning | -1.496 |
Token | Book |
Token ID | 4897 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
APH | +3.694 |
Pyro | +3.309 |
ray | +3.302 |
� | +3.194 |
experien | +3.112 |
Neg logit contributions | |
idth | -4.006 |
psey | -3.022 |
Spoiler | -2.794 |
ento | -2.616 |
uning | -2.523 |
Token | of |
Token ID | 286 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
idth | +0.225 |
psey | +0.166 |
Spoiler | +0.159 |
ento | +0.146 |
avis | +0.143 |
Neg logit contributions | |
APH | -0.214 |
Pyro | -0.190 |
ray | -0.188 |
experien | -0.184 |
ax | -0.180 |
Token | Et |
Token ID | 17906 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
APH | +1.583 |
ray | +1.405 |
Pyro | +1.393 |
� | +1.341 |
experien | +1.326 |
Neg logit contributions | |
idth | -1.945 |
psey | -1.488 |
Spoiler | -1.415 |
ento | -1.307 |
uning | -1.275 |
Token | iquette |
Token ID | 40387 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
APH | +2.086 |
ray | +1.798 |
Pyro | +1.775 |
� | +1.687 |
ax | +1.654 |
Neg logit contributions | |
idth | -3.956 |
psey | -3.196 |
Spoiler | -2.982 |
ento | -2.857 |
aunch | -2.770 |
Token | and |
Token ID | 290 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
APH | +1.824 |
ray | +1.634 |
Pyro | +1.631 |
� | +1.564 |
experien | +1.553 |
Neg logit contributions | |
idth | -1.904 |
psey | -1.420 |
Spoiler | -1.333 |
ento | -1.240 |
uning | -1.197 |
Token | Manual |
Token ID | 17969 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
APH | +3.238 |
Pyro | +2.882 |
ray | +2.880 |
� | +2.786 |
experien | +2.709 |
Neg logit contributions | |
idth | -3.795 |
psey | -2.897 |
Spoiler | -2.700 |
ento | -2.529 |
uning | -2.446 |
Token | of |
Token ID | 286 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
APH | +0.480 |
ray | +0.428 |
Pyro | +0.427 |
experien | +0.411 |
� | +0.409 |
Neg logit contributions | |
idth | -0.528 |
psey | -0.396 |
Spoiler | -0.376 |
ento | -0.348 |
uning | -0.337 |
Token | Polit |
Token ID | 7793 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
APH | +2.262 |
ray | +2.009 |
Pyro | +2.001 |
� | +1.941 |
experien | +1.906 |
Neg logit contributions | |
idth | -2.651 |
psey | -2.017 |
Spoiler | -1.906 |
ento | -1.768 |
uning | -1.717 |
Token | probe |
Token ID | 12774 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
APH | +3.969 |
Pyro | +3.522 |
ray | +3.514 |
� | +3.417 |
ax | +3.286 |
Neg logit contributions | |
idth | -5.026 |
psey | -3.887 |
Spoiler | -3.586 |
ento | -3.390 |
uning | -3.288 |
Token | : |
Token ID | 25 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
APH | +6.853 |
Pyro | +6.222 |
ray | +6.103 |
� | +5.931 |
Cyrus | +5.826 |
Neg logit contributions | |
idth | -10.518 |
psey | -8.642 |
ento | -7.497 |
Spoiler | -7.497 |
uning | -7.371 |
Token | report |
Token ID | 989 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
APH | +3.466 |
Pyro | +2.957 |
ray | +2.954 |
� | +2.934 |
Cyrus | +2.829 |
Neg logit contributions | |
idth | -6.738 |
psey | -5.712 |
ento | -4.935 |
Spoiler | -4.820 |
uning | -4.804 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
APH | +9.350 |
Pyro | +8.739 |
Cyrus | +8.467 |
Kyl | +8.445 |
� | +8.272 |
Neg logit contributions | |
idth | -15.007 |
psey | -12.981 |
ento | -10.644 |
aunch | -10.423 |
uning | -10.386 |
Token | airline |
Token ID | 18091 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
APH | +0.711 |
Pyro | +0.636 |
ray | +0.632 |
� | +0.614 |
experien | +0.597 |
Neg logit contributions | |
idth | -0.777 |
psey | -0.586 |
Spoiler | -0.552 |
ento | -0.509 |
aunch | -0.501 |
Token | takes |
Token ID | 2753 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
APH | +1.279 |
Pyro | +1.153 |
ray | +1.148 |
� | +1.115 |
experien | +1.082 |
Neg logit contributions | |
idth | -1.367 |
psey | -1.028 |
Spoiler | -0.949 |
ento | -0.889 |
uning | -0.858 |
Token | steps |
Token ID | 4831 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
APH | +6.526 |
Kyl | +6.066 |
� | +5.827 |
Pyro | +5.616 |
Zy | +5.459 |
Neg logit contributions | |
idth | -13.484 |
psey | -10.856 |
ento | -9.933 |
avis | -9.499 |
ndum | -9.441 |
Token | to |
Token ID | 284 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
APH | +6.871 |
ray | +6.227 |
� | +6.092 |
Cyrus | +5.954 |
Pyro | +5.775 |
Neg logit contributions | |
idth | -12.710 |
psey | -10.166 |
Spoiler | -9.291 |
ento | -8.687 |
uning | -8.593 |
Token | open |
Token ID | 1280 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
APH | +1.832 |
ray | +1.618 |
Pyro | +1.562 |
� | +1.497 |
Cyrus | +1.477 |
Neg logit contributions | |
idth | -2.621 |
psey | -2.010 |
Spoiler | -1.854 |
ento | -1.781 |
uning | -1.716 |
Token | flights |
Token ID | 13956 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
APH | +5.131 |
ray | +4.618 |
Pyro | +4.613 |
� | +4.465 |
Cyrus | +4.303 |
Neg logit contributions | |
idth | -5.810 |
psey | -4.464 |
Spoiler | -4.052 |
ento | -3.840 |
avis | -3.707 |
Token | to |
Token ID | 284 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
APH | +3.638 |
ray | +3.299 |
Pyro | +3.276 |
� | +3.176 |
ax | +3.078 |
Neg logit contributions | |
idth | -4.128 |
psey | -3.103 |
Spoiler | -2.836 |
ento | -2.720 |
uning | -2.622 |
Token | hope |
Token ID | 2911 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
APH | +4.185 |
ray | +3.815 |
Pyro | +3.813 |
� | +3.702 |
ax | +3.608 |
Neg logit contributions | |
idth | -3.602 |
psey | -2.610 |
Spoiler | -2.359 |
ento | -2.188 |
uning | -2.090 |
Token | you |
Token ID | 345 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
APH | +1.295 |
ray | +1.153 |
Pyro | +1.146 |
� | +1.131 |
ax | +1.093 |
Neg logit contributions | |
idth | -1.167 |
psey | -0.839 |
Spoiler | -0.789 |
ento | -0.734 |
aunch | -0.696 |
Token | 'll |
Token ID | 1183 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
APH | +0.635 |
Pyro | +0.573 |
ray | +0.572 |
� | +0.558 |
experien | +0.542 |
Neg logit contributions | |
idth | -0.539 |
psey | -0.394 |
Spoiler | -0.355 |
ento | -0.329 |
aunch | -0.317 |
Token | enjoy |
Token ID | 2883 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
APH | +3.005 |
Pyro | +2.690 |
ray | +2.686 |
� | +2.625 |
experien | +2.545 |
Neg logit contributions | |
idth | -2.593 |
psey | -1.901 |
Spoiler | -1.723 |
ento | -1.600 |
aunch | -1.547 |
Token | the |
Token ID | 262 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
APH | +5.445 |
Pyro | +4.976 |
ray | +4.944 |
� | +4.749 |
experien | +4.698 |
Neg logit contributions | |
idth | -6.034 |
psey | -4.535 |
Spoiler | -4.155 |
ento | -3.898 |
avis | -3.808 |
Token | new |
Token ID | 649 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
APH | +5.929 |
Pyro | +5.365 |
ray | +5.276 |
� | +5.143 |
ax | +4.980 |
Neg logit contributions | |
idth | -8.361 |
psey | -6.478 |
Spoiler | -6.026 |
ento | -5.724 |
uning | -5.543 |
Token | features |
Token ID | 3033 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
APH | +7.583 |
Pyro | +7.131 |
ray | +6.943 |
� | +6.670 |
ax | +6.576 |
Neg logit contributions | |
idth | -9.538 |
psey | -7.271 |
Spoiler | -6.637 |
ento | -6.347 |
aunch | -6.088 |
Token | ( |
Token ID | 357 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
APH | +3.904 |
Pyro | +3.543 |
ray | +3.487 |
� | +3.440 |
ax | +3.295 |
Neg logit contributions | |
idth | -4.596 |
psey | -3.506 |
Spoiler | -3.225 |
ento | -3.046 |
aunch | -2.929 |
Token | including |
Token ID | 8201 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
APH | +1.932 |
Pyro | +1.781 |
ray | +1.779 |
� | +1.722 |
experien | +1.694 |
Neg logit contributions | |
idth | -1.526 |
psey | -1.090 |
Spoiler | -0.984 |
ento | -0.897 |
uning | -0.871 |
Token | off |
Token ID | 572 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
APH | +6.919 |
Pyro | +6.177 |
ax | +5.983 |
ray | +5.900 |
� | +5.811 |
Neg logit contributions | |
idth | -7.457 |
psey | -5.505 |
ento | -4.863 |
Spoiler | -4.774 |
avis | -4.608 |
Token | - |
Token ID | 12 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
APH | +2.375 |
Pyro | +2.114 |
ray | +2.103 |
� | +1.978 |
ax | +1.921 |
Neg logit contributions | |
idth | -3.849 |
psey | -3.061 |
Spoiler | -2.812 |
ento | -2.750 |
uning | -2.612 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
APH | +5.656 |
Pyro | +4.968 |
ray | +4.859 |
ax | +4.786 |
� | +4.778 |
Neg logit contributions | |
idth | -7.195 |
psey | -5.712 |
Spoiler | -5.126 |
ento | -4.933 |
aunch | -4.748 |
Token | of |
Token ID | 286 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
APH | +2.712 |
ray | +2.446 |
Pyro | +2.422 |
experien | +2.381 |
xual | +2.335 |
Neg logit contributions | |
idth | -2.768 |
psey | -2.050 |
Spoiler | -1.954 |
ento | -1.810 |
aunch | -1.751 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
APH | +4.988 |
Pyro | +4.473 |
Cyrus | +4.240 |
ray | +4.216 |
ax | +4.153 |
Neg logit contributions | |
idth | -6.994 |
psey | -5.663 |
Spoiler | -5.268 |
ento | -5.068 |
uning | -5.061 |
Token | - |
Token ID | 12 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
APH | +5.929 |
Pyro | +5.278 |
ray | +5.254 |
� | +5.082 |
experien | +4.947 |
Neg logit contributions | |
idth | -7.278 |
psey | -5.625 |
Spoiler | -5.227 |
ento | -4.925 |
uning | -4.770 |
Token | Kim |
Token ID | 26374 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
APH | +6.929 |
ray | +6.189 |
Pyro | +5.937 |
� | +5.603 |
ax | +5.531 |
Neg logit contributions | |
idth | -10.791 |
psey | -8.507 |
Spoiler | -8.014 |
ento | -7.327 |
avis | -7.257 |
Token | summit |
Token ID | 14237 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
APH | +7.025 |
ray | +6.009 |
Pyro | +5.661 |
� | +5.535 |
ax | +5.329 |
Neg logit contributions | |
idth | -16.435 |
psey | -12.384 |
avis | -11.978 |
netflix | -11.938 |
Spoiler | -11.886 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
APH | +6.221 |
Pyro | +5.293 |
ray | +5.080 |
Cyrus | +5.055 |
Geo | +4.917 |
Neg logit contributions | |
idth | -11.799 |
psey | -9.834 |
uning | -8.323 |
Spoiler | -8.287 |
aunch | -8.285 |
Token | 's |
Token ID | 338 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
APH | +4.528 |
ray | +4.064 |
Pyro | +4.059 |
� | +3.960 |
ax | +3.841 |
Neg logit contributions | |
idth | -4.752 |
psey | -3.570 |
Spoiler | -3.224 |
ento | -3.069 |
uning | -2.940 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
APH | +1.770 |
Pyro | +1.601 |
ray | +1.584 |
� | +1.535 |
experien | +1.513 |
Neg logit contributions | |
idth | -1.758 |
psey | -1.309 |
Spoiler | -1.211 |
ento | -1.121 |
aunch | -1.084 |
Token | say |
Token ID | 910 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
APH | +5.594 |
Pyro | +5.068 |
ray | +5.063 |
� | +4.923 |
ax | +4.786 |
Neg logit contributions | |
idth | -5.244 |
psey | -3.874 |
Spoiler | -3.513 |
ento | -3.299 |
uning | -3.156 |
Token | he |
Token ID | 339 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
APH | +4.373 |
ray | +4.088 |
Pyro | +4.023 |
� | +3.940 |
Cyrus | +3.845 |
Neg logit contributions | |
idth | -5.545 |
psey | -4.140 |
Spoiler | -3.660 |
avis | -3.496 |
ento | -3.473 |
Token | can |
Token ID | 460 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
APH | +0.207 |
Pyro | +0.184 |
ray | +0.181 |
� | +0.176 |
ax | +0.176 |
Neg logit contributions | |
idth | -0.213 |
psey | -0.164 |
Spoiler | -0.152 |
ento | -0.137 |
aunch | -0.135 |
Token | see |
Token ID | 766 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
idth | +4.913 |
psey | +3.512 |
Spoiler | +3.221 |
aunch | +2.813 |
ento | +2.751 |
Neg logit contributions | |
APH | -6.724 |
BuyableInstoreAndOnline | -6.045 |
者 | -5.804 |
Pyro | -5.781 |
ray | -5.725 |
Token | all |
Token ID | 477 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
idth | +2.601 |
psey | +1.953 |
Spoiler | +1.897 |
ento | +1.632 |
aunch | +1.574 |
Neg logit contributions | |
APH | -3.139 |
ray | -2.801 |
Pyro | -2.782 |
� | -2.717 |
ax | -2.655 |
Token | my |
Token ID | 616 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
APH | +3.543 |
Pyro | +3.179 |
ray | +3.172 |
� | +3.070 |
experien | +2.982 |
Neg logit contributions | |
idth | -3.763 |
psey | -2.841 |
Spoiler | -2.623 |
ento | -2.449 |
aunch | -2.355 |
Token | Nak |
Token ID | 22255 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
APH | +1.687 |
ray | +1.504 |
Pyro | +1.493 |
� | +1.441 |
ax | +1.421 |
Neg logit contributions | |
idth | -1.596 |
psey | -1.211 |
Spoiler | -1.129 |
ento | -1.024 |
aunch | -0.992 |
Token | Mu |
Token ID | 8252 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
APH | +0.599 |
Pyro | +0.538 |
ray | +0.535 |
� | +0.518 |
experien | +0.504 |
Neg logit contributions | |
idth | -0.624 |
psey | -0.472 |
Spoiler | -0.434 |
ento | -0.407 |
uning | -0.392 |
Token | ay |
Token ID | 323 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
APH | +6.057 |
ray | +5.308 |
Pyro | +5.183 |
� | +5.005 |
ax | +4.819 |
Neg logit contributions | |
idth | -11.159 |
psey | -8.925 |
Spoiler | -8.415 |
ento | -7.980 |
uning | -7.761 |
Token | Nation |
Token ID | 8741 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
APH | +0.859 |
Pyro | +0.758 |
ray | +0.755 |
� | +0.726 |
ax | +0.702 |
Neg logit contributions | |
idth | -1.209 |
psey | -0.949 |
Spoiler | -0.885 |
ento | -0.839 |
uning | -0.813 |
Token | features |
Token ID | 3033 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
APH | +0.759 |
Pyro | +0.679 |
ray | +0.673 |
� | +0.648 |
xual | +0.642 |
Neg logit contributions | |
idth | -0.726 |
psey | -0.548 |
Spoiler | -0.517 |
ento | -0.470 |
aunch | -0.451 |
Token | here |
Token ID | 994 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
APH | +0.682 |
Pyro | +0.618 |
ray | +0.617 |
� | +0.592 |
ax | +0.588 |
Neg logit contributions | |
idth | -0.584 |
psey | -0.429 |
Spoiler | -0.408 |
ento | -0.369 |
uning | -0.349 |
Token | . |
Token ID | 13 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
idth | +1.905 |
psey | +1.433 |
Spoiler | +1.352 |
ento | +1.235 |
uning | +1.196 |
Neg logit contributions | |
APH | -1.847 |
Pyro | -1.644 |
ray | -1.634 |
experien | -1.575 |
� | -1.564 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
APH | +1.023 |
Pyro | +0.914 |
ray | +0.914 |
� | +0.884 |
experien | +0.860 |
Neg logit contributions | |
idth | -1.159 |
psey | -0.879 |
Spoiler | -0.815 |
ento | -0.766 |
uning | -0.738 |
Token |
|
Token ID | 198 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
idth | +0.127 |
Spoiler | +0.091 |
psey | +0.083 |
ento | +0.079 |
avis | +0.077 |
Neg logit contributions | |
APH | -0.174 |
experien | -0.160 |
xual | -0.156 |
Pyro | -0.155 |
�醒 | -0.154 |
Token | " |
Token ID | 1 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
APH | +2.726 |
Pyro | +2.455 |
ray | +2.429 |
� | +2.329 |
experien | +2.308 |
Neg logit contributions | |
idth | -3.158 |
psey | -2.385 |
Spoiler | -2.228 |
ento | -2.105 |
uning | -2.027 |
Token | Ste |
Token ID | 7447 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
APH | +8.144 |
ray | +7.332 |
Pyro | +7.294 |
� | +7.156 |
ax | +6.873 |
Neg logit contributions | |
idth | -8.810 |
psey | -6.730 |
Spoiler | -6.063 |
ento | -5.695 |
uning | -5.519 |
Token | lla |
Token ID | 8466 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
APH | +6.515 |
Pyro | +5.875 |
ray | +5.816 |
� | +5.661 |
experien | +5.533 |
Neg logit contributions | |
idth | -6.635 |
psey | -4.966 |
Spoiler | -4.532 |
ento | -4.291 |
uning | -4.123 |
Token | , |
Token ID | 11 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
APH | +4.076 |
Pyro | +3.652 |
ray | +3.646 |
� | +3.529 |
ax | +3.409 |
Neg logit contributions | |
idth | -4.856 |
psey | -3.727 |
Spoiler | -3.431 |
ento | -3.233 |
uning | -3.124 |
Token | those |
Token ID | 883 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
APH | +9.577 |
Pyro | +8.843 |
ray | +8.778 |
� | +8.495 |
experien | +8.302 |
Neg logit contributions | |
idth | -9.163 |
psey | -6.745 |
Spoiler | -6.028 |
ento | -5.656 |
uning | -5.463 |
Token | clothes |
Token ID | 8242 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
APH | +0.533 |
ray | +0.464 |
Pyro | +0.461 |
� | +0.455 |
xual | +0.443 |
Neg logit contributions | |
idth | -0.497 |
psey | -0.375 |
Spoiler | -0.344 |
ento | -0.318 |
uning | -0.309 |
Token | , |
Token ID | 11 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
idth | +1.128 |
psey | +0.814 |
Spoiler | +0.771 |
ento | +0.704 |
uning | +0.672 |
Neg logit contributions | |
APH | -1.379 |
Pyro | -1.220 |
experien | -1.194 |
� | -1.188 |
ray | -1.181 |
Token | should |
Token ID | 815 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
APH | +2.867 |
ray | +2.552 |
Pyro | +2.532 |
� | +2.506 |
experien | +2.425 |
Neg logit contributions | |
idth | -2.369 |
psey | -1.693 |
Spoiler | -1.600 |
ento | -1.460 |
uning | -1.388 |
Token | I |
Token ID | 314 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
APH | +2.610 |
Pyro | +2.346 |
ray | +2.326 |
� | +2.281 |
experien | +2.225 |
Neg logit contributions | |
idth | -2.503 |
psey | -1.836 |
Spoiler | -1.691 |
ento | -1.581 |
uning | -1.520 |