Token | . |
Token ID | 13 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
hyde | +0.894 |
zyk | +0.856 |
Fail | +0.822 |
learnt | +0.821 |
ortmund | +0.816 |
Neg logit contributions | |
trop | -1.247 |
soc | -1.169 |
ftime | -1.138 |
lest | -1.120 |
othe | -1.111 |
Token | You |
Token ID | 921 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
trop | +2.927 |
soc | +2.799 |
Cros | +2.690 |
lest | +2.679 |
going | +2.675 |
Neg logit contributions | |
hyde | -2.027 |
ortmund | -1.821 |
VIDIA | -1.797 |
zyk | -1.794 |
learnt | -1.765 |
Token | can |
Token ID | 460 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
trop | +3.280 |
soc | +3.148 |
lest | +2.992 |
othe | +2.988 |
age | +2.970 |
Neg logit contributions | |
hyde | -2.303 |
ortmund | -2.058 |
zyk | -2.052 |
Fail | -2.001 |
learnt | -1.980 |
Token | read |
Token ID | 1100 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
trop | +2.933 |
soc | +2.763 |
othe | +2.597 |
lest | +2.581 |
age | +2.563 |
Neg logit contributions | |
hyde | -4.394 |
ortmund | -4.067 |
zyk | -4.041 |
XT | -4.005 |
Fail | -3.995 |
Token | our |
Token ID | 674 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
trop | +5.539 |
soc | +5.424 |
lest | +5.171 |
othe | +5.064 |
age | +4.996 |
Neg logit contributions | |
hyde | -6.150 |
VIDIA | -5.591 |
Fail | -5.531 |
zyk | -5.530 |
ortmund | -5.509 |
Token | Privacy |
Token ID | 16777 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
trop | +4.764 |
soc | +4.545 |
Cros | +4.311 |
lest | +4.180 |
age | +4.041 |
Neg logit contributions | |
hyde | -9.470 |
ortmund | -8.597 |
VIDIA | -8.553 |
�� | -8.512 |
zyk | -8.492 |
Token | Policy |
Token ID | 7820 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
trop | +2.976 |
soc | +2.565 |
Cros | +2.558 |
going | +2.420 |
Wem | +2.265 |
Neg logit contributions | |
hyde | -14.788 |
VIDIA | -14.658 |
��� | -14.068 |
�� | -13.865 |
ortmund | -13.579 |
Token | here |
Token ID | 994 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
trop | +4.810 |
soc | +4.549 |
othe | +4.304 |
lest | +4.301 |
age | +4.231 |
Neg logit contributions | |
hyde | -9.621 |
�� | -9.072 |
VIDIA | -9.028 |
ortmund | -8.894 |
Fail | -8.867 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
trop | +4.606 |
soc | +4.386 |
lest | +4.160 |
going | +4.150 |
age | +4.143 |
Neg logit contributions | |
hyde | -5.165 |
VIDIA | -4.724 |
ortmund | -4.717 |
�� | -4.677 |
zyk | -4.657 |
Token | Sign |
Token ID | 5865 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
trop | +2.481 |
soc | +2.180 |
lest | +2.118 |
Cros | +2.116 |
going | +2.075 |
Neg logit contributions | |
hyde | -7.733 |
ortmund | -7.319 |
VIDIA | -7.298 |
�� | -7.140 |
zyk | -7.043 |
Token | up |
Token ID | 510 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
trop | +4.828 |
soc | +4.629 |
age | +4.581 |
going | +4.377 |
aging | +4.299 |
Neg logit contributions | |
hyde | -7.926 |
VIDIA | -7.515 |
�� | -7.445 |
ortmund | -7.360 |
��� | -7.355 |
Token | email |
Token ID | 3053 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
trop | +4.612 |
soc | +4.434 |
demographics | +4.233 |
lest | +4.221 |
ftime | +4.220 |
Neg logit contributions | |
hyde | -4.364 |
zyk | -3.881 |
�� | -3.859 |
ortmund | -3.855 |
VIDIA | -3.836 |
Token | address |
Token ID | 2209 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
trop | +2.805 |
soc | +2.678 |
ftime | +2.545 |
lest | +2.543 |
othe | +2.535 |
Neg logit contributions | |
hyde | -2.176 |
zyk | -1.983 |
ortmund | -1.957 |
Fail | -1.933 |
learnt | -1.932 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
trop | +5.004 |
soc | +4.817 |
age | +4.536 |
going | +4.530 |
lest | +4.517 |
Neg logit contributions | |
hyde | -6.049 |
VIDIA | -5.756 |
�� | -5.561 |
��� | -5.537 |
ortmund | -5.487 |
Token | Please |
Token ID | 4222 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
trop | +0.615 |
soc | +0.585 |
ftime | +0.562 |
lest | +0.561 |
othe | +0.559 |
Neg logit contributions | |
hyde | -0.357 |
zyk | -0.325 |
Fail | -0.317 |
learnt | -0.316 |
ortmund | -0.315 |
Token | re |
Token ID | 302 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
trop | +2.665 |
soc | +2.518 |
lest | +2.392 |
othe | +2.378 |
ftime | +2.364 |
Neg logit contributions | |
hyde | -2.709 |
zyk | -2.508 |
ortmund | -2.477 |
learnt | -2.452 |
Fail | -2.439 |
Token | - |
Token ID | 12 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
trop | +2.011 |
soc | +1.896 |
lest | +1.800 |
ftime | +1.790 |
othe | +1.786 |
Neg logit contributions | |
hyde | -1.904 |
zyk | -1.761 |
ortmund | -1.736 |
learnt | -1.726 |
Fail | -1.720 |
Token | enter |
Token ID | 9255 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
trop | +4.516 |
soc | +4.154 |
age | +3.988 |
going | +3.681 |
aging | +3.666 |
Neg logit contributions | |
hyde | -13.222 |
�� | -12.629 |
��� | -12.491 |
VIDIA | -12.480 |
ortmund | -12.438 |
Token | . |
Token ID | 13 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
trop | +5.717 |
soc | +5.538 |
age | +5.407 |
going | +5.260 |
lest | +5.164 |
Neg logit contributions | |
hyde | -7.743 |
��� | -7.712 |
VIDIA | -7.628 |
�� | -7.461 |
everal | -7.096 |
Token | You |
Token ID | 921 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
trop | +3.436 |
soc | +3.287 |
lest | +3.155 |
Cros | +3.146 |
going | +3.143 |
Neg logit contributions | |
hyde | -2.199 |
zyk | -1.978 |
ortmund | -1.954 |
learnt | -1.923 |
Fail | -1.902 |
Token | must |
Token ID | 1276 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
trop | +2.365 |
soc | +2.258 |
lest | +2.167 |
ftime | +2.157 |
othe | +2.153 |
Neg logit contributions | |
hyde | -1.382 |
zyk | -1.249 |
ortmund | -1.223 |
learnt | -1.215 |
Fail | -1.209 |
Token | select |
Token ID | 2922 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
trop | +5.132 |
soc | +5.074 |
ftime | +4.917 |
age | +4.877 |
lest | +4.785 |
Neg logit contributions | |
hyde | -8.347 |
�� | -7.924 |
VIDIA | -7.919 |
zyk | -7.787 |
��� | -7.556 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
hyde | +0.490 |
zyk | +0.450 |
learnt | +0.439 |
ortmund | +0.439 |
Fail | +0.436 |
Neg logit contributions | |
trop | -0.730 |
soc | -0.693 |
ftime | -0.664 |
lest | -0.662 |
othe | -0.659 |
Token | . |
Token ID | 13 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
trop | +1.270 |
soc | +1.200 |
lest | +1.143 |
othe | +1.139 |
ftime | +1.136 |
Neg logit contributions | |
hyde | -1.091 |
zyk | -1.006 |
ortmund | -0.995 |
learnt | -0.986 |
Fail | -0.981 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
hyde | +1.364 |
zyk | +1.252 |
Fail | +1.219 |
learnt | +1.216 |
XT | +1.213 |
Neg logit contributions | |
trop | -2.167 |
soc | -2.055 |
ftime | -1.978 |
lest | -1.972 |
othe | -1.947 |
Token | / |
Token ID | 14 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
hyde | +1.240 |
zyk | +1.160 |
Fail | +1.131 |
learnt | +1.130 |
XT | +1.130 |
Neg logit contributions | |
trop | -1.518 |
soc | -1.428 |
ftime | -1.372 |
lest | -1.364 |
othe | -1.350 |
Token | Cl |
Token ID | 2601 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
hyde | +2.592 |
Fail | +2.451 |
zyk | +2.447 |
XT | +2.418 |
learnt | +2.354 |
Neg logit contributions | |
trop | -2.902 |
soc | -2.713 |
ftime | -2.660 |
othe | -2.615 |
lest | -2.595 |
Token | od |
Token ID | 375 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
trop | +0.921 |
soc | +0.869 |
lest | +0.830 |
ftime | +0.829 |
going | +0.819 |
Neg logit contributions | |
hyde | -0.819 |
zyk | -0.763 |
ortmund | -0.744 |
learnt | -0.744 |
Fail | -0.736 |
Token | agh |
Token ID | 10471 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
trop | +6.909 |
soc | +6.061 |
age | +5.942 |
othe | +5.884 |
Cros | +5.668 |
Neg logit contributions | |
ortmund | -9.868 |
hyde | -9.827 |
Fail | -9.654 |
VIDIA | -9.648 |
XT | -9.394 |
Token | Kil |
Token ID | 19902 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
hyde | +2.643 |
zyk | +2.481 |
Fail | +2.432 |
learnt | +2.397 |
XT | +2.360 |
Neg logit contributions | |
trop | -2.282 |
soc | -2.104 |
ftime | -2.039 |
lest | -1.993 |
going | -1.968 |
Token | c |
Token ID | 66 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
hyde | +5.021 |
zyk | +4.714 |
learnt | +4.392 |
XT | +4.381 |
ortmund | +4.354 |
Neg logit contributions | |
trop | -4.458 |
soc | -4.243 |
lest | -4.066 |
ERA | -4.045 |
Wem | -4.017 |
Token | oy |
Token ID | 726 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
hyde | +4.465 |
zyk | +4.451 |
learnt | +4.176 |
Fail | +4.166 |
ortmund | +4.129 |
Neg logit contributions | |
trop | -2.686 |
soc | -2.590 |
stood | -2.408 |
Cros | -2.313 |
Wem | -2.309 |
Token | ne |
Token ID | 710 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
hyde | +2.246 |
zyk | +2.169 |
learnt | +2.142 |
Fail | +2.133 |
XT | +2.104 |
Neg logit contributions | |
trop | -0.866 |
soc | -0.791 |
ftime | -0.725 |
ERA | -0.672 |
Cros | -0.666 |
Token | email |
Token ID | 3053 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
trop | +4.182 |
soc | +4.018 |
demographics | +3.821 |
ftime | +3.818 |
age | +3.817 |
Neg logit contributions | |
hyde | -3.864 |
zyk | -3.446 |
�� | -3.435 |
ortmund | -3.424 |
VIDIA | -3.422 |
Token | address |
Token ID | 2209 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
trop | +3.133 |
soc | +2.997 |
ftime | +2.848 |
lest | +2.840 |
othe | +2.832 |
Neg logit contributions | |
hyde | -2.484 |
zyk | -2.262 |
ortmund | -2.232 |
Fail | -2.210 |
learnt | -2.204 |
Token | . |
Token ID | 13 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
trop | +4.717 |
soc | +4.524 |
going | +4.270 |
lest | +4.265 |
age | +4.258 |
Neg logit contributions | |
hyde | -5.479 |
VIDIA | -5.174 |
�� | -5.011 |
ortmund | -4.968 |
��� | -4.936 |
Token | Please |
Token ID | 4222 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
trop | +0.306 |
soc | +0.291 |
ftime | +0.280 |
lest | +0.279 |
othe | +0.279 |
Neg logit contributions | |
hyde | -0.176 |
zyk | -0.160 |
Fail | -0.157 |
learnt | -0.156 |
ortmund | -0.155 |
Token | re |
Token ID | 302 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
trop | +2.508 |
soc | +2.367 |
lest | +2.250 |
othe | +2.239 |
ftime | +2.229 |
Neg logit contributions | |
hyde | -2.501 |
zyk | -2.316 |
ortmund | -2.283 |
learnt | -2.262 |
Fail | -2.255 |
Token | - |
Token ID | 12 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
trop | +2.115 |
soc | +1.994 |
lest | +1.894 |
ftime | +1.884 |
othe | +1.880 |
Neg logit contributions | |
hyde | -1.983 |
zyk | -1.836 |
ortmund | -1.808 |
learnt | -1.800 |
Fail | -1.793 |
Token | enter |
Token ID | 9255 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
trop | +4.506 |
soc | +4.207 |
age | +4.031 |
going | +3.696 |
aging | +3.667 |
Neg logit contributions | |
hyde | -12.632 |
�� | -12.035 |
VIDIA | -11.987 |
ortmund | -11.858 |
��� | -11.843 |
Token | . |
Token ID | 13 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
trop | +5.598 |
soc | +5.418 |
age | +5.259 |
going | +5.150 |
lest | +5.039 |
Neg logit contributions | |
hyde | -7.329 |
��� | -7.207 |
VIDIA | -7.187 |
�� | -7.015 |
ortmund | -6.707 |
Token | You |
Token ID | 921 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
trop | +2.824 |
soc | +2.700 |
lest | +2.589 |
Cros | +2.579 |
going | +2.575 |
Neg logit contributions | |
hyde | -1.739 |
zyk | -1.565 |
ortmund | -1.542 |
learnt | -1.522 |
Fail | -1.507 |
Token | must |
Token ID | 1276 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
trop | +1.710 |
soc | +1.626 |
lest | +1.562 |
ftime | +1.557 |
othe | +1.555 |
Neg logit contributions | |
hyde | -0.947 |
zyk | -0.854 |
ortmund | -0.834 |
learnt | -0.833 |
Fail | -0.825 |
Token | select |
Token ID | 2922 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
trop | +4.936 |
soc | +4.842 |
age | +4.735 |
ftime | +4.716 |
lest | +4.595 |
Neg logit contributions | |
hyde | -7.695 |
VIDIA | -7.293 |
�� | -7.287 |
zyk | -7.172 |
��� | -6.977 |
Token | email |
Token ID | 3053 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
trop | +4.334 |
soc | +4.149 |
demographics | +3.978 |
ftime | +3.959 |
lest | +3.955 |
Neg logit contributions | |
hyde | -4.153 |
�� | -3.705 |
zyk | -3.688 |
VIDIA | -3.674 |
ortmund | -3.669 |
Token | address |
Token ID | 2209 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
trop | +2.838 |
soc | +2.713 |
ftime | +2.580 |
lest | +2.572 |
othe | +2.565 |
Neg logit contributions | |
hyde | -2.248 |
zyk | -2.046 |
ortmund | -2.019 |
Fail | -1.998 |
learnt | -1.993 |
Token | . |
Token ID | 13 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
trop | +4.778 |
soc | +4.599 |
age | +4.335 |
lest | +4.328 |
going | +4.321 |
Neg logit contributions | |
hyde | -5.754 |
VIDIA | -5.493 |
�� | -5.280 |
��� | -5.232 |
ortmund | -5.207 |
Token | Please |
Token ID | 4222 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
trop | +0.534 |
soc | +0.508 |
ftime | +0.487 |
lest | +0.486 |
othe | +0.485 |
Neg logit contributions | |
hyde | -0.319 |
zyk | -0.290 |
ortmund | -0.283 |
Fail | -0.283 |
learnt | -0.283 |
Token | re |
Token ID | 302 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
trop | +2.394 |
soc | +2.261 |
lest | +2.148 |
othe | +2.137 |
ftime | +2.128 |
Neg logit contributions | |
hyde | -2.394 |
zyk | -2.216 |
ortmund | -2.188 |
learnt | -2.169 |
Fail | -2.158 |
Token | - |
Token ID | 12 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
trop | +1.532 |
soc | +1.444 |
lest | +1.374 |
ftime | +1.368 |
othe | +1.367 |
Neg logit contributions | |
hyde | -1.393 |
zyk | -1.293 |
ortmund | -1.268 |
learnt | -1.268 |
Fail | -1.260 |
Token | enter |
Token ID | 9255 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
trop | +4.490 |
soc | +4.131 |
age | +3.956 |
going | +3.682 |
aging | +3.640 |
Neg logit contributions | |
hyde | -12.544 |
�� | -12.020 |
VIDIA | -11.931 |
��� | -11.812 |
ortmund | -11.804 |
Token | . |
Token ID | 13 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
trop | +5.442 |
soc | +5.253 |
age | +5.092 |
going | +4.981 |
lest | +4.892 |
Neg logit contributions | |
hyde | -7.020 |
VIDIA | -6.864 |
��� | -6.858 |
�� | -6.706 |
ortmund | -6.430 |
Token | You |
Token ID | 921 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
trop | +3.056 |
soc | +2.923 |
lest | +2.805 |
Cros | +2.799 |
going | +2.794 |
Neg logit contributions | |
hyde | -1.949 |
zyk | -1.754 |
ortmund | -1.734 |
learnt | -1.710 |
Fail | -1.687 |
Token | must |
Token ID | 1276 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
trop | +1.804 |
soc | +1.719 |
lest | +1.651 |
ftime | +1.644 |
othe | +1.642 |
Neg logit contributions | |
hyde | -1.028 |
zyk | -0.928 |
ortmund | -0.907 |
learnt | -0.903 |
Fail | -0.897 |
Token | select |
Token ID | 2922 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
trop | +4.927 |
soc | +4.839 |
age | +4.719 |
ftime | +4.714 |
lest | +4.587 |
Neg logit contributions | |
hyde | -7.591 |
�� | -7.221 |
VIDIA | -7.212 |
zyk | -7.052 |
��� | -6.897 |
Token | email |
Token ID | 3053 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
trop | +4.245 |
soc | +4.092 |
demographics | +3.919 |
ftime | +3.896 |
lest | +3.888 |
Neg logit contributions | |
hyde | -4.049 |
zyk | -3.600 |
�� | -3.590 |
ortmund | -3.577 |
VIDIA | -3.560 |
Token | address |
Token ID | 2209 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
trop | +2.714 |
soc | +2.590 |
ftime | +2.464 |
lest | +2.459 |
othe | +2.452 |
Neg logit contributions | |
hyde | -2.112 |
zyk | -1.924 |
ortmund | -1.897 |
Fail | -1.877 |
learnt | -1.876 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
trop | +4.599 |
soc | +4.412 |
lest | +4.153 |
age | +4.146 |
going | +4.142 |
Neg logit contributions | |
hyde | -5.319 |
VIDIA | -5.014 |
�� | -4.851 |
ortmund | -4.836 |
zyk | -4.807 |
Token | Please |
Token ID | 4222 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
trop | +0.096 |
soc | +0.091 |
ftime | +0.088 |
lest | +0.087 |
othe | +0.087 |
Neg logit contributions | |
hyde | -0.055 |
zyk | -0.050 |
Fail | -0.049 |
learnt | -0.049 |
ortmund | -0.049 |
Token | re |
Token ID | 302 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
trop | +2.099 |
soc | +1.981 |
lest | +1.884 |
othe | +1.872 |
ftime | +1.865 |
Neg logit contributions | |
hyde | -2.075 |
zyk | -1.924 |
ortmund | -1.898 |
learnt | -1.884 |
Fail | -1.873 |
Token | - |
Token ID | 12 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
trop | +1.524 |
soc | +1.436 |
lest | +1.366 |
ftime | +1.360 |
othe | +1.358 |
Neg logit contributions | |
hyde | -1.392 |
zyk | -1.292 |
ortmund | -1.268 |
learnt | -1.267 |
Fail | -1.259 |
Token | enter |
Token ID | 9255 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
trop | +4.381 |
soc | +4.047 |
age | +3.863 |
going | +3.605 |
aging | +3.562 |
Neg logit contributions | |
hyde | -12.126 |
�� | -11.577 |
VIDIA | -11.451 |
ortmund | -11.420 |
��� | -11.357 |
Token | . |
Token ID | 13 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
trop | +5.315 |
soc | +5.132 |
age | +4.973 |
going | +4.856 |
lest | +4.781 |
Neg logit contributions | |
hyde | -6.759 |
VIDIA | -6.570 |
��� | -6.534 |
�� | -6.419 |
ortmund | -6.186 |
Token | You |
Token ID | 921 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
trop | +2.758 |
soc | +2.636 |
lest | +2.530 |
Cros | +2.519 |
going | +2.514 |
Neg logit contributions | |
hyde | -1.704 |
zyk | -1.536 |
ortmund | -1.515 |
learnt | -1.497 |
Fail | -1.480 |
Token | must |
Token ID | 1276 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
trop | +1.493 |
soc | +1.420 |
lest | +1.363 |
ftime | +1.359 |
othe | +1.358 |
Neg logit contributions | |
hyde | -0.830 |
zyk | -0.748 |
ortmund | -0.730 |
learnt | -0.729 |
Fail | -0.723 |
Token | select |
Token ID | 2922 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
trop | +4.919 |
soc | +4.826 |
ftime | +4.697 |
age | +4.666 |
lest | +4.599 |
Neg logit contributions | |
hyde | -7.359 |
�� | -7.002 |
VIDIA | -6.958 |
zyk | -6.861 |
��� | -6.680 |
Token | Mrs |
Token ID | 9074 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
trop | +1.789 |
soc | +1.656 |
lest | +1.538 |
othe | +1.531 |
ftime | +1.523 |
Neg logit contributions | |
hyde | -2.982 |
zyk | -2.785 |
ortmund | -2.768 |
Fail | -2.755 |
learnt | -2.735 |
Token | . |
Token ID | 13 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
hyde | +2.205 |
zyk | +2.150 |
learnt | +2.049 |
XT | +2.048 |
Fail | +2.041 |
Neg logit contributions | |
trop | -3.482 |
soc | -3.261 |
ftime | -3.201 |
nomine | -3.159 |
lest | -3.124 |
Token | Obama |
Token ID | 2486 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
hyde | +2.573 |
zyk | +2.505 |
learnt | +2.438 |
Fail | +2.378 |
XT | +2.360 |
Neg logit contributions | |
trop | -2.957 |
soc | -2.779 |
ftime | -2.667 |
lest | -2.623 |
othe | -2.614 |
Token | said |
Token ID | 531 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
trop | +2.986 |
soc | +2.806 |
age | +2.678 |
lest | +2.678 |
othe | +2.657 |
Neg logit contributions | |
hyde | -3.224 |
ortmund | -2.994 |
Fail | -2.956 |
zyk | -2.951 |
XT | -2.915 |
Token | with |
Token ID | 351 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
trop | +0.816 |
soc | +0.770 |
lest | +0.733 |
ftime | +0.728 |
othe | +0.727 |
Neg logit contributions | |
hyde | -0.688 |
zyk | -0.636 |
learnt | -0.625 |
ortmund | -0.621 |
Fail | -0.616 |
Token | damp |
Token ID | 21151 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
trop | +2.101 |
soc | +1.999 |
going | +1.913 |
lest | +1.907 |
Cros | +1.904 |
Neg logit contributions | |
hyde | -1.722 |
zyk | -1.574 |
ortmund | -1.564 |
Fail | -1.541 |
learnt | -1.519 |
Token | eyes |
Token ID | 2951 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
trop | +7.958 |
soc | +7.591 |
othe | +7.542 |
going | +7.451 |
age | +7.370 |
Neg logit contributions | |
hyde | -7.762 |
zyk | -7.262 |
ortmund | -7.177 |
XT | -6.957 |
Fail | -6.934 |
Token |
|
Token ID | 198 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
trop | +4.260 |
soc | +4.015 |
lest | +3.843 |
ftime | +3.829 |
othe | +3.813 |
Neg logit contributions | |
hyde | -4.167 |
zyk | -3.860 |
ortmund | -3.851 |
Fail | -3.798 |
learnt | -3.734 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
hyde | +0.076 |
zyk | +0.072 |
Fail | +0.069 |
learnt | +0.069 |
ortmund | +0.068 |
Neg logit contributions | |
trop | -0.126 |
soc | -0.119 |
ftime | -0.116 |
lest | -0.114 |
othe | -0.114 |
Token | Mrs |
Token ID | 27034 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
trop | +0.138 |
soc | +0.130 |
lest | +0.123 |
ftime | +0.123 |
othe | +0.123 |
Neg logit contributions | |
hyde | -0.131 |
zyk | -0.122 |
ortmund | -0.120 |
learnt | -0.119 |
Fail | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
hyde | +1.312 |
zyk | +1.252 |
learnt | +1.210 |
Fail | +1.201 |
XT | +1.199 |
Neg logit contributions | |
trop | -1.837 |
soc | -1.726 |
ftime | -1.670 |
lest | -1.647 |
othe | -1.643 |
Token | but |
Token ID | 475 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
hyde | +1.989 |
zyk | +1.846 |
learnt | +1.831 |
ortmund | +1.813 |
Fail | +1.807 |
Neg logit contributions | |
trop | -2.225 |
soc | -2.085 |
ftime | -1.992 |
lest | -1.981 |
othe | -1.979 |
Token | once |
Token ID | 1752 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
hyde | +0.835 |
zyk | +0.774 |
learnt | +0.763 |
ortmund | +0.757 |
Fail | +0.753 |
Neg logit contributions | |
trop | -1.010 |
soc | -0.952 |
lest | -0.907 |
ftime | -0.906 |
othe | -0.900 |
Token | I |
Token ID | 314 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
hyde | +0.348 |
zyk | +0.323 |
learnt | +0.319 |
ortmund | +0.316 |
Fail | +0.314 |
Neg logit contributions | |
trop | -0.411 |
soc | -0.388 |
lest | -0.371 |
ftime | -0.368 |
othe | -0.367 |
Token | got |
Token ID | 1392 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
trop | +0.925 |
soc | +0.874 |
lest | +0.833 |
othe | +0.833 |
ftime | +0.828 |
Neg logit contributions | |
hyde | -0.759 |
zyk | -0.692 |
ortmund | -0.689 |
Fail | -0.682 |
XT | -0.671 |
Token | it |
Token ID | 340 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
trop | +0.556 |
soc | +0.525 |
lest | +0.501 |
ftime | +0.497 |
othe | +0.495 |
Neg logit contributions | |
hyde | -0.491 |
zyk | -0.456 |
learnt | -0.450 |
ortmund | -0.447 |
Fail | -0.444 |
Token | up |
Token ID | 510 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
trop | +6.701 |
soc | +6.236 |
going | +6.062 |
Cros | +5.987 |
othe | +5.965 |
Neg logit contributions | |
hyde | -7.178 |
ortmund | -6.573 |
Fail | -6.480 |
VIDIA | -6.428 |
zyk | -6.361 |
Token | on |
Token ID | 319 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
trop | +7.037 |
soc | +6.682 |
ftime | +6.308 |
Cros | +6.298 |
going | +6.291 |
Neg logit contributions | |
hyde | -8.685 |
ortmund | -8.096 |
zyk | -7.953 |
Fail | -7.891 |
VIDIA | -7.715 |
Token | some |
Token ID | 617 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
trop | +3.335 |
soc | +3.157 |
Cros | +2.988 |
lest | +2.987 |
othe | +2.978 |
Neg logit contributions | |
hyde | -3.245 |
zyk | -3.010 |
ortmund | -2.991 |
Fail | -2.934 |
learnt | -2.933 |
Token | vinyl |
Token ID | 23275 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
trop | +2.742 |
soc | +2.591 |
Cros | +2.457 |
othe | +2.456 |
ftime | +2.451 |
Neg logit contributions | |
hyde | -2.450 |
zyk | -2.268 |
ortmund | -2.244 |
Fail | -2.214 |
learnt | -2.207 |
Token | floor |
Token ID | 4314 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
trop | +3.902 |
soc | +3.724 |
othe | +3.499 |
lest | +3.483 |
age | +3.475 |
Neg logit contributions | |
hyde | -3.940 |
zyk | -3.642 |
ortmund | -3.614 |
Fail | -3.579 |
XT | -3.561 |
Token | ing |
Token ID | 278 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
trop | +0.796 |
soc | +0.746 |
lest | +0.707 |
ftime | +0.703 |
othe | +0.702 |
Neg logit contributions | |
hyde | -0.842 |
zyk | -0.783 |
ortmund | -0.771 |
learnt | -0.770 |
Fail | -0.766 |
Token | � |
Token ID | 251 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
hyde | +0.153 |
zyk | +0.138 |
learnt | +0.135 |
ortmund | +0.135 |
Fail | +0.135 |
Neg logit contributions | |
trop | -0.248 |
soc | -0.236 |
lest | -0.226 |
ftime | -0.224 |
othe | -0.224 |
Token | she |
Token ID | 673 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
hyde | +0.741 |
zyk | +0.681 |
ortmund | +0.666 |
learnt | +0.665 |
Fail | +0.664 |
Neg logit contributions | |
trop | -0.985 |
soc | -0.933 |
lest | -0.891 |
ftime | -0.887 |
othe | -0.885 |
Token | says |
Token ID | 1139 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
trop | +1.206 |
soc | +1.143 |
lest | +1.092 |
ftime | +1.087 |
othe | +1.086 |
Neg logit contributions | |
hyde | -0.914 |
zyk | -0.837 |
ortmund | -0.826 |
learnt | -0.817 |
Fail | -0.816 |
Token | , |
Token ID | 11 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
trop | +4.766 |
soc | +4.509 |
Cros | +4.355 |
othe | +4.355 |
age | +4.323 |
Neg logit contributions | |
hyde | -4.934 |
ortmund | -4.589 |
zyk | -4.559 |
Fail | -4.451 |
XT | -4.411 |
Token | pe |
Token ID | 613 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
trop | +4.252 |
soc | +4.024 |
going | +3.856 |
Cros | +3.841 |
age | +3.841 |
Neg logit contributions | |
hyde | -4.119 |
ortmund | -3.828 |
zyk | -3.818 |
Fail | -3.744 |
XT | -3.691 |
Token | ering |
Token ID | 1586 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
trop | +1.130 |
soc | +1.048 |
lest | +0.985 |
ftime | +0.979 |
othe | +0.975 |
Neg logit contributions | |
hyde | -1.538 |
zyk | -1.444 |
ortmund | -1.423 |
learnt | -1.420 |
Fail | -1.413 |
Token | at |
Token ID | 379 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
trop | +7.150 |
Cros | +6.715 |
soc | +6.695 |
age | +6.687 |
going | +6.589 |
Neg logit contributions | |
hyde | -8.263 |
ortmund | -7.788 |
zyk | -7.769 |
Fail | -7.506 |
VIDIA | -7.399 |
Token | it |
Token ID | 340 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
trop | +2.769 |
soc | +2.620 |
Cros | +2.494 |
lest | +2.490 |
othe | +2.483 |
Neg logit contributions | |
hyde | -2.610 |
zyk | -2.415 |
ortmund | -2.395 |
learnt | -2.371 |
Fail | -2.352 |
Token | . |
Token ID | 13 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
trop | +2.764 |
soc | +2.619 |
lest | +2.504 |
othe | +2.492 |
Cros | +2.481 |
Neg logit contributions | |
hyde | -2.391 |
zyk | -2.190 |
ortmund | -2.177 |
Fail | -2.137 |
XT | -2.114 |
Token | � |
Token ID | 564 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
trop | +2.328 |
soc | +2.204 |
Cros | +2.122 |
lest | +2.109 |
othe | +2.094 |
Neg logit contributions | |
hyde | -1.961 |
zyk | -1.797 |
ortmund | -1.790 |
learnt | -1.771 |
Fail | -1.736 |
Token | � |
Token ID | 250 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
trop | +0.578 |
soc | +0.547 |
lest | +0.522 |
ftime | +0.520 |
othe | +0.518 |
Neg logit contributions | |
hyde | -0.429 |
zyk | -0.393 |
ortmund | -0.385 |
learnt | -0.385 |
Fail | -0.384 |
Token | Five |
Token ID | 10579 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
hyde | +1.375 |
zyk | +1.277 |
Fail | +1.248 |
learnt | +1.228 |
XT | +1.228 |
Neg logit contributions | |
trop | -1.690 |
soc | -1.602 |
lest | -1.509 |
ftime | -1.507 |
othe | -1.504 |
Token | is |
Token ID | 318 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
hyde | +1.532 |
zyk | +1.404 |
learnt | +1.391 |
ortmund | +1.360 |
Fail | +1.359 |
Neg logit contributions | |
trop | -2.035 |
soc | -1.912 |
lest | -1.834 |
othe | -1.817 |
ftime | -1.809 |
Token | being |
Token ID | 852 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
trop | +0.188 |
soc | +0.178 |
lest | +0.170 |
ftime | +0.169 |
othe | +0.168 |
Neg logit contributions | |
hyde | -0.158 |
zyk | -0.146 |
learnt | -0.143 |
ortmund | -0.143 |
Fail | -0.142 |
Token | pre |
Token ID | 662 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
trop | +1.829 |
soc | +1.730 |
lest | +1.646 |
ftime | +1.645 |
Cros | +1.641 |
Neg logit contributions | |
hyde | -1.548 |
zyk | -1.422 |
ortmund | -1.408 |
Fail | -1.392 |
learnt | -1.381 |
Token | - |
Token ID | 12 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
trop | +4.886 |
soc | +4.450 |
ftime | +4.251 |
othe | +4.118 |
age | +4.108 |
Neg logit contributions | |
hyde | -6.634 |
ortmund | -6.229 |
Fail | -6.077 |
VIDIA | -6.060 |
zyk | -6.057 |
Token | empt |
Token ID | 1791 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
trop | +7.106 |
soc | +6.395 |
going | +5.955 |
lest | +5.936 |
age | +5.900 |
Neg logit contributions | |
hyde | -7.815 |
ortmund | -7.444 |
�� | -7.320 |
VIDIA | -7.246 |
learnt | -7.196 |
Token | ed |
Token ID | 276 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
trop | +5.187 |
soc | +4.777 |
age | +4.489 |
lest | +4.488 |
ftime | +4.440 |
Neg logit contributions | |
hyde | -10.352 |
VIDIA | -9.885 |
�� | -9.865 |
ortmund | -9.732 |
��� | -9.696 |
Token | for |
Token ID | 329 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
trop | +4.172 |
soc | +3.942 |
going | +3.773 |
age | +3.773 |
lest | +3.767 |
Neg logit contributions | |
hyde | -3.886 |
ortmund | -3.584 |
Fail | -3.568 |
zyk | -3.555 |
learnt | -3.500 |
Token | continuing |
Token ID | 8282 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
trop | +3.095 |
soc | +2.940 |
going | +2.805 |
Cros | +2.790 |
age | +2.763 |
Neg logit contributions | |
hyde | -2.940 |
ortmund | -2.708 |
zyk | -2.699 |
learnt | -2.675 |
Fail | -2.657 |
Token | coverage |
Token ID | 5197 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
hyde | +2.339 |
zyk | +2.219 |
learnt | +2.152 |
Fail | +2.129 |
ortmund | +2.117 |
Neg logit contributions | |
trop | -2.891 |
soc | -2.730 |
lest | -2.626 |
ftime | -2.610 |
othe | -2.586 |
Token | . |
Token ID | 13 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
trop | +1.860 |
soc | +1.758 |
lest | +1.669 |
ftime | +1.663 |
othe | +1.658 |
Neg logit contributions | |
hyde | -1.749 |
zyk | -1.613 |
ortmund | -1.595 |
learnt | -1.583 |
Fail | -1.582 |
Token | 15 |
Token ID | 1315 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
trop | +2.735 |
soc | +2.600 |
lest | +2.441 |
Cros | +2.436 |
othe | +2.427 |
Neg logit contributions | |
hyde | -2.783 |
zyk | -2.565 |
ortmund | -2.545 |
Fail | -2.519 |
learnt | -2.506 |
Token | - |
Token ID | 12 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
trop | +1.761 |
soc | +1.663 |
lest | +1.579 |
othe | +1.568 |
ftime | +1.568 |
Neg logit contributions | |
hyde | -1.648 |
zyk | -1.523 |
ortmund | -1.501 |
learnt | -1.493 |
Fail | -1.487 |
Token | year |
Token ID | 1941 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
trop | +2.751 |
soc | +2.575 |
age | +2.390 |
going | +2.322 |
lest | +2.314 |
Neg logit contributions | |
hyde | -5.624 |
zyk | -5.266 |
ortmund | -5.265 |
learnt | -5.178 |
Fail | -5.177 |
Token | - |
Token ID | 12 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
trop | +3.934 |
soc | +3.738 |
age | +3.554 |
othe | +3.516 |
aging | +3.497 |
Neg logit contributions | |
hyde | -4.387 |
zyk | -4.057 |
ortmund | -4.035 |
Fail | -3.987 |
learnt | -3.951 |
Token | old |
Token ID | 727 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
trop | +1.775 |
soc | +1.659 |
lest | +1.558 |
ftime | +1.542 |
othe | +1.542 |
Neg logit contributions | |
hyde | -2.326 |
zyk | -2.174 |
ortmund | -2.152 |
learnt | -2.143 |
Fail | -2.133 |
Token | Venus |
Token ID | 21094 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
trop | +2.062 |
soc | +1.938 |
lest | +1.827 |
ftime | +1.814 |
othe | +1.813 |
Neg logit contributions | |
hyde | -2.309 |
zyk | -2.149 |
ortmund | -2.124 |
learnt | -2.106 |
Fail | -2.104 |
Token | Angel |
Token ID | 3905 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
trop | +7.595 |
soc | +7.255 |
Cros | +7.167 |
age | +7.141 |
Wem | +6.798 |
Neg logit contributions | |
hyde | -7.560 |
ortmund | -7.379 |
�� | -7.023 |
Fail | -6.976 |
zyk | -6.928 |
Token | ic |
Token ID | 291 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
hyde | +1.330 |
zyk | +1.252 |
learnt | +1.218 |
ortmund | +1.205 |
Fail | +1.203 |
Neg logit contributions | |
trop | -1.231 |
soc | -1.154 |
ftime | -1.098 |
lest | -1.093 |
othe | -1.080 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
trop | +0.330 |
soc | +0.311 |
lest | +0.296 |
ftime | +0.295 |
othe | +0.294 |
Neg logit contributions | |
hyde | -0.306 |
zyk | -0.283 |
ortmund | -0.279 |
learnt | -0.278 |
Fail | -0.277 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
trop | +0.743 |
soc | +0.700 |
lest | +0.665 |
ftime | +0.661 |
othe | +0.660 |
Neg logit contributions | |
hyde | -0.705 |
zyk | -0.653 |
ortmund | -0.643 |
learnt | -0.639 |
Fail | -0.638 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
hyde | +0.491 |
zyk | +0.457 |
learnt | +0.450 |
ortmund | +0.445 |
Fail | +0.445 |
Neg logit contributions | |
trop | -0.559 |
soc | -0.526 |
lest | -0.504 |
ftime | -0.503 |
othe | -0.500 |
Token | . |
Token ID | 13 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
trop | +0.861 |
soc | +0.815 |
lest | +0.774 |
othe | +0.769 |
ftime | +0.769 |
Neg logit contributions | |
hyde | -0.774 |
zyk | -0.714 |
ortmund | -0.703 |
learnt | -0.702 |
Fail | -0.695 |
Token | S |
Token ID | 50 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
trop | +1.304 |
soc | +1.239 |
lest | +1.177 |
othe | +1.168 |
ftime | +1.164 |
Neg logit contributions | |
hyde | -1.097 |
zyk | -1.004 |
ortmund | -0.992 |
learnt | -0.987 |
Fail | -0.972 |
Token | . |
Token ID | 13 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
trop | +1.502 |
soc | +1.420 |
lest | +1.349 |
othe | +1.342 |
ftime | +1.341 |
Neg logit contributions | |
hyde | -1.340 |
zyk | -1.234 |
ortmund | -1.217 |
learnt | -1.211 |
Fail | -1.204 |
Token | Senate |
Token ID | 3845 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
trop | +2.024 |
soc | +1.877 |
othe | +1.733 |
lest | +1.731 |
ftime | +1.729 |
Neg logit contributions | |
hyde | -3.051 |
zyk | -2.862 |
ortmund | -2.841 |
learnt | -2.808 |
Fail | -2.807 |
Token | at |
Token ID | 379 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
hyde | +2.462 |
zyk | +2.313 |
learnt | +2.292 |
Fail | +2.283 |
XT | +2.277 |
Neg logit contributions | |
trop | -3.168 |
soc | -2.947 |
lest | -2.846 |
othe | -2.818 |
ftime | -2.810 |
Token | Earth |
Token ID | 3668 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
trop | +1.163 |
soc | +1.101 |
lest | +1.044 |
ftime | +1.042 |
othe | +1.037 |
Neg logit contributions | |
hyde | -0.990 |
zyk | -0.915 |
ortmund | -0.900 |
learnt | -0.899 |
Fail | -0.894 |
Token | Friendly |
Token ID | 38683 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
trop | +8.013 |
soc | +7.810 |
age | +7.460 |
lest | +7.328 |
going | +7.287 |
Neg logit contributions | |
hyde | -7.446 |
learnt | -7.049 |
ortmund | -6.965 |
zyk | -6.842 |
�� | -6.823 |
Token | Products |
Token ID | 18675 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
trop | +1.788 |
soc | +1.685 |
lest | +1.598 |
ftime | +1.587 |
othe | +1.586 |
Neg logit contributions | |
hyde | -1.756 |
zyk | -1.631 |
ortmund | -1.606 |
learnt | -1.601 |
Fail | -1.592 |
Token | packaging |
Token ID | 16846 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
trop | +3.065 |
soc | +2.903 |
lest | +2.746 |
othe | +2.745 |
Cros | +2.743 |
Neg logit contributions | |
hyde | -3.210 |
zyk | -2.977 |
ortmund | -2.938 |
learnt | -2.909 |
Fail | -2.895 |
Token | plant |
Token ID | 4618 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
trop | +1.221 |
soc | +1.146 |
lest | +1.088 |
ftime | +1.082 |
othe | +1.079 |
Neg logit contributions | |
hyde | -1.173 |
zyk | -1.086 |
learnt | -1.076 |
ortmund | -1.073 |
Fail | -1.066 |
Token | on |
Token ID | 319 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
trop | +1.918 |
soc | +1.804 |
lest | +1.711 |
ftime | +1.703 |
othe | +1.700 |
Neg logit contributions | |
hyde | -1.916 |
zyk | -1.780 |
ortmund | -1.751 |
learnt | -1.746 |
Fail | -1.738 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
trop | +4.606 |
soc | +4.386 |
lest | +4.160 |
going | +4.150 |
age | +4.143 |
Neg logit contributions | |
hyde | -5.165 |
VIDIA | -4.724 |
ortmund | -4.717 |
�� | -4.677 |
zyk | -4.657 |
Token | Sign |
Token ID | 5865 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
trop | +2.481 |
soc | +2.180 |
lest | +2.118 |
Cros | +2.116 |
going | +2.075 |
Neg logit contributions | |
hyde | -7.733 |
ortmund | -7.319 |
VIDIA | -7.298 |
�� | -7.140 |
zyk | -7.043 |
Token | up |
Token ID | 510 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
trop | +4.828 |
soc | +4.629 |
age | +4.581 |
going | +4.377 |
aging | +4.299 |
Neg logit contributions | |
hyde | -7.926 |
VIDIA | -7.515 |
�� | -7.445 |
ortmund | -7.360 |
��� | -7.355 |
Token | for |
Token ID | 329 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
trop | +5.989 |
soc | +5.722 |
lest | +5.560 |
age | +5.531 |
going | +5.422 |
Neg logit contributions | |
hyde | -6.793 |
VIDIA | -6.599 |
��� | -6.315 |
�� | -6.292 |
ortmund | -6.049 |
Token | Take |
Token ID | 7214 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
trop | +4.360 |
soc | +4.127 |
Cros | +4.009 |
age | +3.996 |
going | +3.909 |
Neg logit contributions | |
hyde | -6.725 |
VIDIA | -6.335 |
ortmund | -6.318 |
�� | -6.276 |
zyk | -6.197 |
Token | Action |
Token ID | 7561 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
trop | +4.520 |
soc | +4.316 |
age | +4.141 |
going | +4.075 |
Cros | +4.075 |
Neg logit contributions | |
hyde | -4.166 |
ortmund | -3.853 |
VIDIA | -3.784 |
�� | -3.761 |
zyk | -3.744 |
Token | Now |
Token ID | 2735 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
trop | +6.066 |
soc | +5.899 |
going | +5.640 |
age | +5.621 |
Cros | +5.607 |
Neg logit contributions | |
hyde | -9.461 |
VIDIA | -9.328 |
��� | -9.135 |
�� | -8.671 |
everal | -8.580 |
Token | and |
Token ID | 290 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
trop | +3.480 |
soc | +3.279 |
lest | +3.022 |
age | +2.997 |
going | +2.948 |
Neg logit contributions | |
hyde | -8.303 |
VIDIA | -7.857 |
�� | -7.786 |
ortmund | -7.738 |
zyk | -7.660 |
Token | we |
Token ID | 356 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
trop | +3.883 |
soc | +3.772 |
othe | +3.578 |
lest | +3.562 |
age | +3.525 |
Neg logit contributions | |
hyde | -3.317 |
ortmund | -2.988 |
zyk | -2.966 |
�� | -2.963 |
VIDIA | -2.956 |
Token | � |
Token ID | 447 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
trop | +5.091 |
soc | +4.962 |
lest | +4.748 |
othe | +4.712 |
Cros | +4.598 |
Neg logit contributions | |
hyde | -4.309 |
ortmund | -3.927 |
zyk | -3.809 |
Fail | -3.809 |
learnt | -3.778 |
Token | � |
Token ID | 247 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
trop | +4.753 |
soc | +4.635 |
lest | +4.505 |
age | +4.457 |
going | +4.450 |
Neg logit contributions | |
hyde | -1.479 |
zyk | -1.241 |
learnt | -1.211 |
ortmund | -1.211 |
XT | -1.161 |
Token | moon |
Token ID | 8824 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
trop | +0.760 |
soc | +0.711 |
lest | +0.673 |
ftime | +0.671 |
othe | +0.668 |
Neg logit contributions | |
hyde | -0.866 |
zyk | -0.807 |
learnt | -0.796 |
ortmund | -0.794 |
Fail | -0.789 |
Token | are |
Token ID | 389 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
hyde | +0.221 |
zyk | +0.201 |
learnt | +0.199 |
ortmund | +0.195 |
Fail | +0.194 |
Neg logit contributions | |
trop | -0.336 |
soc | -0.319 |
lest | -0.306 |
ftime | -0.306 |
othe | -0.303 |
Token | tug |
Token ID | 27762 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
hyde | +0.988 |
learnt | +0.916 |
zyk | +0.913 |
ortmund | +0.889 |
XT | +0.885 |
Neg logit contributions | |
trop | -1.172 |
soc | -1.109 |
lest | -1.057 |
ftime | -1.056 |
othe | -1.047 |
Token | ging |
Token ID | 2667 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
hyde | +2.103 |
zyk | +1.999 |
learnt | +1.992 |
XT | +1.954 |
Fail | +1.953 |
Neg logit contributions | |
trop | -1.141 |
soc | -1.022 |
ftime | -0.977 |
Cros | -0.963 |
ERA | -0.936 |
Token | on |
Token ID | 319 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
trop | +1.026 |
soc | +0.965 |
lest | +0.916 |
ftime | +0.911 |
othe | +0.910 |
Neg logit contributions | |
hyde | -1.008 |
zyk | -0.936 |
ortmund | -0.921 |
learnt | -0.917 |
Fail | -0.914 |
Token | Earth |
Token ID | 3668 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
hyde | +0.257 |
zyk | +0.237 |
learnt | +0.235 |
ortmund | +0.231 |
XT | +0.230 |
Neg logit contributions | |
trop | -0.304 |
soc | -0.287 |
ftime | -0.275 |
lest | -0.274 |
othe | -0.272 |
Token | 's |
Token ID | 338 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
trop | +6.519 |
soc | +6.205 |
going | +5.896 |
age | +5.825 |
lest | +5.710 |
Neg logit contributions | |
hyde | -8.820 |
ortmund | -8.379 |
Fail | -8.342 |
zyk | -8.167 |
�� | -8.151 |
Token | spin |
Token ID | 7906 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
trop | +1.507 |
soc | +1.419 |
lest | +1.350 |
othe | +1.340 |
Cros | +1.338 |
Neg logit contributions | |
hyde | -1.366 |
zyk | -1.265 |
ortmund | -1.250 |
Fail | -1.235 |
learnt | -1.230 |
Token | . |
Token ID | 13 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
trop | +3.608 |
soc | +3.384 |
lest | +3.236 |
age | +3.223 |
going | +3.190 |
Neg logit contributions | |
hyde | -3.445 |
zyk | -3.200 |
ortmund | -3.187 |
Fail | -3.162 |
learnt | -3.143 |
Token | That |
Token ID | 1320 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
hyde | +0.186 |
zyk | +0.171 |
ortmund | +0.167 |
learnt | +0.167 |
Fail | +0.167 |
Neg logit contributions | |
trop | -0.255 |
soc | -0.242 |
lest | -0.231 |
ftime | -0.231 |
othe | -0.230 |
Token | would |
Token ID | 561 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
hyde | +2.802 |
learnt | +2.660 |
zyk | +2.625 |
XT | +2.576 |
ortmund | +2.535 |
Neg logit contributions | |
trop | -4.155 |
soc | -3.928 |
ftime | -3.802 |
lest | -3.761 |
othe | -3.743 |
Token | the |
Token ID | 262 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
trop | +3.372 |
soc | +3.187 |
Cros | +3.025 |
going | +3.006 |
othe | +2.995 |
Neg logit contributions | |
hyde | -3.243 |
zyk | -3.013 |
ortmund | -2.975 |
Fail | -2.949 |
learnt | -2.917 |
Token | machines |
Token ID | 8217 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
trop | +2.718 |
soc | +2.590 |
Cros | +2.475 |
othe | +2.456 |
lest | +2.450 |
Neg logit contributions | |
hyde | -2.404 |
zyk | -2.221 |
ortmund | -2.185 |
Fail | -2.157 |
learnt | -2.146 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
trop | +2.693 |
soc | +2.538 |
lest | +2.404 |
othe | +2.387 |
ftime | +2.381 |
Neg logit contributions | |
hyde | -2.838 |
zyk | -2.628 |
ortmund | -2.605 |
Fail | -2.590 |
learnt | -2.570 |
Token | An |
Token ID | 1052 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
trop | +1.402 |
soc | +1.326 |
lest | +1.265 |
Cros | +1.260 |
othe | +1.255 |
Neg logit contributions | |
hyde | -1.193 |
zyk | -1.096 |
ortmund | -1.085 |
learnt | -1.076 |
Fail | -1.067 |
Token | Internet |
Token ID | 4455 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
hyde | +0.236 |
zyk | +0.219 |
ortmund | +0.215 |
learnt | +0.215 |
Fail | +0.214 |
Neg logit contributions | |
trop | -0.247 |
soc | -0.233 |
lest | -0.221 |
ftime | -0.220 |
othe | -0.219 |
Token | search |
Token ID | 2989 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
trop | +4.781 |
soc | +4.590 |
going | +4.442 |
age | +4.429 |
aging | +4.382 |
Neg logit contributions | |
hyde | -2.360 |
zyk | -2.049 |
ortmund | -2.041 |
�� | -1.958 |
Fail | -1.947 |
Token | turned |
Token ID | 2900 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
trop | +7.574 |
soc | +7.057 |
age | +6.945 |
going | +6.932 |
aging | +6.861 |
Neg logit contributions | |
hyde | -7.731 |
�� | -7.116 |
VIDIA | -7.096 |
ortmund | -7.057 |
Fail | -7.017 |
Token | up |
Token ID | 510 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
trop | +0.774 |
soc | +0.725 |
lest | +0.683 |
ftime | +0.679 |
othe | +0.679 |
Neg logit contributions | |
hyde | -0.883 |
zyk | -0.824 |
ortmund | -0.813 |
learnt | -0.809 |
Fail | -0.807 |
Token | references |
Token ID | 10288 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
hyde | +0.044 |
zyk | +0.040 |
ortmund | +0.040 |
learnt | +0.040 |
Fail | +0.039 |
Neg logit contributions | |
trop | -0.058 |
soc | -0.055 |
lest | -0.053 |
ftime | -0.052 |
othe | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
trop | +0.277 |
soc | +0.263 |
ftime | +0.249 |
lest | +0.249 |
othe | +0.247 |
Neg logit contributions | |
hyde | -0.251 |
zyk | -0.234 |
learnt | -0.230 |
ortmund | -0.228 |
Fail | -0.227 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
hyde | +0.059 |
zyk | +0.054 |
learnt | +0.054 |
ortmund | +0.053 |
Fail | +0.053 |
Neg logit contributions | |
trop | -0.064 |
soc | -0.060 |
ftime | -0.057 |
lest | -0.057 |
othe | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
trop | +5.857 |
soc | +5.669 |
age | +5.433 |
lest | +5.392 |
Cros | +5.335 |
Neg logit contributions | |
hyde | -5.240 |
zyk | -5.041 |
ortmund | -4.919 |
�� | -4.908 |
learnt | -4.782 |
Token | sun |
Token ID | 4252 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
trop | +1.578 |
soc | +1.482 |
lest | +1.405 |
ftime | +1.395 |
othe | +1.394 |
Neg logit contributions | |
hyde | -1.624 |
zyk | -1.515 |
ortmund | -1.490 |
learnt | -1.484 |
Fail | -1.478 |
Token | ? |
Token ID | 30 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
trop | +4.353 |
soc | +4.145 |
lest | +3.994 |
going | +3.971 |
age | +3.958 |
Neg logit contributions | |
hyde | -2.922 |
zyk | -2.679 |
ortmund | -2.645 |
Fail | -2.591 |
learnt | -2.577 |
Token |
|
Token ID | 198 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
trop | +0.485 |
soc | +0.459 |
lest | +0.438 |
ftime | +0.437 |
othe | +0.436 |
Neg logit contributions | |
hyde | -0.372 |
zyk | -0.341 |
ortmund | -0.335 |
learnt | -0.334 |
Fail | -0.332 |
Token |
|
Token ID | 198 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
hyde | +0.647 |
zyk | +0.597 |
Fail | +0.591 |
XT | +0.581 |
ortmund | +0.579 |
Neg logit contributions | |
trop | -1.037 |
soc | -0.987 |
ftime | -0.959 |
othe | -0.949 |
lest | -0.947 |
Token | Earth |
Token ID | 22840 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
trop | +0.167 |
soc | +0.158 |
ftime | +0.151 |
lest | +0.151 |
othe | +0.151 |
Neg logit contributions | |
hyde | -0.133 |
zyk | -0.123 |
Fail | -0.121 |
ortmund | -0.120 |
learnt | -0.120 |
Token | 's |
Token ID | 338 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
trop | +7.587 |
soc | +7.307 |
going | +6.890 |
lest | +6.837 |
age | +6.817 |
Neg logit contributions | |
hyde | -7.556 |
zyk | -7.191 |
ortmund | -7.115 |
Fail | -7.028 |
�� | -6.942 |
Token | spin |
Token ID | 7906 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
trop | +1.082 |
soc | +1.004 |
lest | +0.941 |
ftime | +0.938 |
othe | +0.935 |
Neg logit contributions | |
hyde | -1.541 |
zyk | -1.446 |
learnt | -1.429 |
ortmund | -1.426 |
Fail | -1.419 |
Token | , |
Token ID | 11 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
trop | +4.418 |
soc | +4.174 |
age | +4.014 |
lest | +3.997 |
ftime | +3.990 |
Neg logit contributions | |
hyde | -3.444 |
zyk | -3.216 |
ortmund | -3.172 |
Fail | -3.134 |
learnt | -3.104 |
Token | of |
Token ID | 286 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
trop | +2.127 |
soc | +1.996 |
lest | +1.901 |
ftime | +1.888 |
othe | +1.884 |
Neg logit contributions | |
hyde | -1.937 |
zyk | -1.800 |
ortmund | -1.767 |
Fail | -1.759 |
learnt | -1.741 |
Token | course |
Token ID | 1781 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
trop | +2.767 |
soc | +2.612 |
lest | +2.488 |
ftime | +2.487 |
going | +2.482 |
Neg logit contributions | |
hyde | -2.108 |
zyk | -1.945 |
ortmund | -1.915 |
Fail | -1.899 |
learnt | -1.883 |
Token | . |
Token ID | 13 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
trop | +1.787 |
soc | +1.687 |
lest | +1.607 |
ftime | +1.601 |
othe | +1.597 |
Neg logit contributions | |
hyde | -1.546 |
zyk | -1.430 |
ortmund | -1.404 |
learnt | -1.401 |
Fail | -1.394 |
Token |
|
Token ID | 198 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
trop | +1.917 |
soc | +1.821 |
lest | +1.741 |
ftime | +1.729 |
othe | +1.729 |
Neg logit contributions | |
hyde | -1.377 |
zyk | -1.253 |
ortmund | -1.235 |
learnt | -1.227 |
Fail | -1.217 |
Token |
|
Token ID | 198 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
trop | +3.924 |
soc | +3.749 |
age | +3.603 |
going | +3.588 |
lest | +3.567 |
Neg logit contributions | |
hyde | -3.612 |
VIDIA | -3.315 |
�� | -3.312 |
ortmund | -3.225 |
��� | -3.197 |
Token | Thank |
Token ID | 10449 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
trop | +2.901 |
soc | +2.720 |
lest | +2.553 |
going | +2.530 |
ftime | +2.517 |
Neg logit contributions | |
hyde | -3.572 |
zyk | -3.282 |
ortmund | -3.262 |
learnt | -3.255 |
Fail | -3.213 |
Token | you |
Token ID | 345 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
trop | +1.938 |
soc | +1.854 |
lest | +1.772 |
othe | +1.759 |
ftime | +1.754 |
Neg logit contributions | |
hyde | -1.264 |
zyk | -1.140 |
ortmund | -1.127 |
learnt | -1.111 |
Fail | -1.103 |
Token | for |
Token ID | 329 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
trop | +6.150 |
soc | +5.978 |
age | +5.613 |
going | +5.523 |
lest | +5.451 |
Neg logit contributions | |
hyde | -6.828 |
VIDIA | -6.504 |
��� | -6.436 |
�� | -6.419 |
ortmund | -6.162 |
Token | signing |
Token ID | 8415 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
trop | +4.740 |
soc | +4.400 |
going | +4.371 |
aging | +4.327 |
age | +4.130 |
Neg logit contributions | |
hyde | -10.730 |
VIDIA | -9.950 |
ortmund | -9.856 |
��� | -9.803 |
Fail | -9.758 |
Token | up |
Token ID | 510 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
trop | +4.693 |
soc | +4.499 |
age | +4.297 |
going | +4.273 |
aging | +4.091 |
Neg logit contributions | |
hyde | -7.388 |
�� | -6.989 |
VIDIA | -6.923 |
ortmund | -6.805 |
��� | -6.708 |
Token | . |
Token ID | 13 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
trop | +4.389 |
soc | +4.185 |
age | +3.961 |
lest | +3.937 |
going | +3.913 |
Neg logit contributions | |
hyde | -5.023 |
VIDIA | -4.747 |
�� | -4.675 |
��� | -4.638 |
ortmund | -4.576 |
Token | For |
Token ID | 1114 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
trop | +2.405 |
soc | +2.293 |
Cros | +2.205 |
age | +2.199 |
lest | +2.193 |
Neg logit contributions | |
hyde | -2.035 |
VIDIA | -1.867 |
ortmund | -1.852 |
zyk | -1.845 |
learnt | -1.824 |
Token | more |
Token ID | 517 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
trop | +0.371 |
soc | +0.350 |
lest | +0.334 |
ftime | +0.332 |
othe | +0.331 |
Neg logit contributions | |
hyde | -0.322 |
zyk | -0.298 |
learnt | -0.293 |
ortmund | -0.293 |
Fail | -0.291 |
Token | email |
Token ID | 3053 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
trop | +2.634 |
soc | +2.535 |
othe | +2.433 |
lest | +2.415 |
age | +2.413 |
Neg logit contributions | |
hyde | -1.772 |
zyk | -1.627 |
ortmund | -1.610 |
learnt | -1.593 |
Fail | -1.583 |
Token | to |
Token ID | 284 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
trop | +1.132 |
soc | +1.075 |
lest | +1.027 |
ftime | +1.022 |
othe | +1.021 |
Neg logit contributions | |
hyde | -0.860 |
zyk | -0.790 |
ortmund | -0.777 |
learnt | -0.772 |
Fail | -0.770 |
Token | confirm |
Token ID | 6216 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
trop | +3.297 |
soc | +3.133 |
lest | +3.017 |
othe | +3.014 |
Cros | +2.978 |
Neg logit contributions | |
hyde | -2.725 |
zyk | -2.527 |
ortmund | -2.504 |
Fail | -2.484 |
�� | -2.465 |
Token | your |
Token ID | 534 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
trop | +2.050 |
soc | +1.945 |
lest | +1.859 |
othe | +1.849 |
ftime | +1.844 |
Neg logit contributions | |
hyde | -1.644 |
zyk | -1.512 |
ortmund | -1.490 |
Fail | -1.472 |
learnt | -1.472 |
Token | newsletter |
Token ID | 13129 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
trop | +1.818 |
soc | +1.712 |
Cros | +1.603 |
othe | +1.595 |
going | +1.594 |
Neg logit contributions | |
hyde | -2.668 |
zyk | -2.506 |
ortmund | -2.495 |
Fail | -2.444 |
learnt | -2.427 |
Token | registration |
Token ID | 9352 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
trop | +1.350 |
soc | +1.275 |
lest | +1.212 |
ftime | +1.207 |
othe | +1.204 |
Neg logit contributions | |
hyde | -1.222 |
zyk | -1.131 |
ortmund | -1.114 |
learnt | -1.108 |
Fail | -1.103 |
Token | . |
Token ID | 13 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
trop | +7.207 |
soc | +6.935 |
Cros | +6.770 |
age | +6.640 |
going | +6.603 |
Neg logit contributions | |
hyde | -7.379 |
ortmund | -7.022 |
zyk | -7.010 |
�� | -6.855 |
XT | -6.831 |
Token | More |
Token ID | 3125 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
trop | +2.583 |
soc | +2.454 |
Cros | +2.347 |
lest | +2.336 |
othe | +2.333 |
Neg logit contributions | |
hyde | -2.097 |
zyk | -1.921 |
ortmund | -1.917 |
Fail | -1.884 |
learnt | -1.882 |
Token | newsletters |
Token ID | 16983 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
trop | +3.584 |
soc | +3.412 |
lest | +3.269 |
Cros | +3.258 |
othe | +3.257 |
Neg logit contributions | |
hyde | -2.716 |
zyk | -2.483 |
ortmund | -2.436 |
Fail | -2.409 |
learnt | -2.404 |
Token |
|
Token ID | 198 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
trop | +2.665 |
soc | +2.522 |
lest | +2.403 |
othe | +2.393 |
ftime | +2.387 |
Neg logit contributions | |
hyde | -2.245 |
zyk | -2.071 |
ortmund | -2.046 |
Fail | -2.021 |
learnt | -2.020 |
Token |
|
Token ID | 198 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
trop | +3.212 |
soc | +3.062 |
lest | +2.921 |
age | +2.919 |
going | +2.915 |
Neg logit contributions | |
hyde | -2.628 |
�� | -2.357 |
ortmund | -2.356 |
zyk | -2.354 |
VIDIA | -2.339 |
Token | by |
Token ID | 416 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
trop | +2.974 |
soc | +2.850 |
going | +2.706 |
Cros | +2.693 |
ftime | +2.693 |
Neg logit contributions | |
hyde | -2.430 |
ortmund | -2.245 |
zyk | -2.226 |
learnt | -2.198 |
Fail | -2.194 |
Token | George |
Token ID | 4502 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
trop | +1.772 |
soc | +1.674 |
lest | +1.589 |
ftime | +1.580 |
othe | +1.580 |
Neg logit contributions | |
hyde | -1.624 |
zyk | -1.502 |
ortmund | -1.481 |
learnt | -1.472 |
Fail | -1.466 |
Token | Soros |
Token ID | 27900 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
trop | +0.721 |
soc | +0.672 |
lest | +0.632 |
ftime | +0.626 |
othe | +0.626 |
Neg logit contributions | |
hyde | -0.969 |
zyk | -0.909 |
ortmund | -0.897 |
learnt | -0.895 |
Fail | -0.890 |
Token | 's |
Token ID | 338 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
trop | +0.309 |
soc | +0.290 |
lest | +0.276 |
ftime | +0.276 |
othe | +0.274 |
Neg logit contributions | |
hyde | -0.284 |
zyk | -0.264 |
learnt | -0.258 |
ortmund | -0.258 |
Fail | -0.257 |
Token | pre |
Token ID | 662 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
hyde | +0.034 |
zyk | +0.031 |
learnt | +0.031 |
ortmund | +0.031 |
Fail | +0.031 |
Neg logit contributions | |
trop | -0.047 |
soc | -0.044 |
ftime | -0.042 |
lest | -0.042 |
othe | -0.042 |
Token | - |
Token ID | 12 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
trop | +4.955 |
soc | +4.674 |
othe | +4.446 |
lest | +4.440 |
ftime | +4.384 |
Neg logit contributions | |
hyde | -5.598 |
learnt | -5.054 |
zyk | -5.050 |
ortmund | -5.050 |
Fail | -4.956 |
Token | tax |
Token ID | 19290 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
trop | +7.358 |
soc | +6.940 |
othe | +6.430 |
lest | +6.419 |
going | +6.398 |
Neg logit contributions | |
hyde | -8.027 |
ortmund | -7.447 |
�� | -7.349 |
learnt | -7.344 |
zyk | -7.330 |
Token | dollars |
Token ID | 5054 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
trop | +2.787 |
soc | +2.650 |
othe | +2.508 |
lest | +2.491 |
ftime | +2.475 |
Neg logit contributions | |
hyde | -3.017 |
zyk | -2.796 |
ortmund | -2.773 |
learnt | -2.747 |
Fail | -2.726 |
Token | . |
Token ID | 13 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
hyde | +1.064 |
zyk | +0.983 |
learnt | +0.968 |
ortmund | +0.957 |
Fail | +0.955 |
Neg logit contributions | |
trop | -1.301 |
soc | -1.221 |
lest | -1.167 |
ftime | -1.164 |
othe | -1.155 |
Token | See |
Token ID | 4091 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
trop | +2.209 |
soc | +2.101 |
lest | +2.010 |
Cros | +2.006 |
othe | +1.992 |
Neg logit contributions | |
hyde | -1.778 |
zyk | -1.625 |
ortmund | -1.624 |
learnt | -1.601 |
Fail | -1.578 |
Token | earlier |
Token ID | 2961 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
trop | +1.753 |
soc | +1.661 |
lest | +1.585 |
othe | +1.575 |
Cros | +1.572 |
Neg logit contributions | |
hyde | -1.516 |
zyk | -1.392 |
ortmund | -1.378 |
learnt | -1.365 |
Fail | -1.363 |
Token | ly |
Token ID | 306 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
hyde | +0.308 |
zyk | +0.288 |
learnt | +0.286 |
ortmund | +0.283 |
Fail | +0.283 |
Neg logit contributions | |
trop | -0.252 |
soc | -0.234 |
ftime | -0.221 |
lest | -0.220 |
othe | -0.220 |
Token | but |
Token ID | 475 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
trop | +0.292 |
soc | +0.274 |
lest | +0.259 |
ftime | +0.258 |
othe | +0.257 |
Neg logit contributions | |
hyde | -0.307 |
zyk | -0.286 |
learnt | -0.283 |
ortmund | -0.281 |
Fail | -0.279 |
Token | the |
Token ID | 262 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
hyde | +0.863 |
zyk | +0.794 |
learnt | +0.793 |
ortmund | +0.775 |
Fail | +0.774 |
Neg logit contributions | |
trop | -1.126 |
soc | -1.065 |
ftime | -1.018 |
lest | -1.016 |
othe | -1.007 |
Token | un |
Token ID | 555 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
hyde | +0.295 |
zyk | +0.272 |
learnt | +0.268 |
ortmund | +0.267 |
Fail | +0.265 |
Neg logit contributions | |
trop | -0.350 |
soc | -0.331 |
lest | -0.316 |
ftime | -0.315 |
othe | -0.313 |
Token | cl |
Token ID | 565 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
hyde | +0.430 |
zyk | +0.395 |
learnt | +0.387 |
ortmund | +0.383 |
Fail | +0.382 |
Neg logit contributions | |
trop | -0.576 |
soc | -0.541 |
ftime | -0.526 |
Cros | -0.520 |
lest | -0.517 |
Token | ot |
Token ID | 313 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
trop | +1.883 |
soc | +1.760 |
othe | +1.669 |
lest | +1.646 |
age | +1.633 |
Neg logit contributions | |
hyde | -2.415 |
zyk | -2.244 |
ortmund | -2.233 |
Fail | -2.219 |
learnt | -2.209 |
Token | hed |
Token ID | 704 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
trop | +5.385 |
othe | +5.022 |
soc | +5.018 |
age | +4.905 |
lest | +4.857 |
Neg logit contributions | |
hyde | -9.241 |
ortmund | -9.112 |
Fail | -8.746 |
VIDIA | -8.725 |
zyk | -8.691 |
Token | male |
Token ID | 4257 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
trop | +3.058 |
soc | +2.894 |
lest | +2.740 |
othe | +2.736 |
age | +2.732 |
Neg logit contributions | |
hyde | -2.824 |
zyk | -2.639 |
ortmund | -2.570 |
Fail | -2.545 |
XT | -2.521 |
Token | form |
Token ID | 1296 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
trop | +1.870 |
soc | +1.780 |
lest | +1.702 |
othe | +1.695 |
age | +1.688 |
Neg logit contributions | |
hyde | -1.325 |
zyk | -1.217 |
ortmund | -1.200 |
Fail | -1.187 |
XT | -1.174 |
Token | was |
Token ID | 373 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
trop | +0.100 |
soc | +0.095 |
lest | +0.090 |
ftime | +0.090 |
othe | +0.090 |
Neg logit contributions | |
hyde | -0.067 |
zyk | -0.061 |
learnt | -0.060 |
ortmund | -0.059 |
Fail | -0.059 |
Token | everywhere |
Token ID | 8347 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
trop | +0.583 |
soc | +0.553 |
lest | +0.527 |
othe | +0.524 |
ftime | +0.524 |
Neg logit contributions | |
hyde | -0.468 |
zyk | -0.431 |
ortmund | -0.424 |
Fail | -0.419 |
learnt | -0.419 |
Token | News |
Token ID | 3000 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
hyde | +4.106 |
XT | +3.718 |
learnt | +3.702 |
zyk | +3.518 |
Fail | +3.423 |
Neg logit contributions | |
trop | -10.775 |
soc | -9.863 |
ftime | -9.688 |
verson | -9.606 |
soType | -9.583 |
Token | , |
Token ID | 11 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
hyde | +2.586 |
zyk | +2.408 |
XT | +2.330 |
Fail | +2.328 |
learnt | +2.312 |
Neg logit contributions | |
trop | -2.595 |
soc | -2.394 |
ftime | -2.309 |
lest | -2.302 |
othe | -2.267 |
Token | The |
Token ID | 383 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
trop | +1.033 |
soc | +0.972 |
lest | +0.924 |
ftime | +0.921 |
othe | +0.918 |
Neg logit contributions | |
hyde | -0.985 |
zyk | -0.913 |
ortmund | -0.897 |
learnt | -0.896 |
Fail | -0.892 |
Token | San |
Token ID | 2986 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
hyde | +3.598 |
zyk | +3.333 |
Fail | +3.321 |
XT | +3.268 |
learnt | +3.202 |
Neg logit contributions | |
trop | -3.404 |
soc | -3.141 |
ftime | -3.038 |
lest | -2.966 |
othe | -2.935 |
Token | Antonio |
Token ID | 11366 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
trop | +2.178 |
soc | +2.016 |
lest | +1.878 |
othe | +1.866 |
Cros | +1.860 |
Neg logit contributions | |
hyde | -3.677 |
zyk | -3.466 |
ortmund | -3.462 |
learnt | -3.430 |
Fail | -3.413 |
Token | Express |
Token ID | 10604 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
hyde | +0.709 |
zyk | +0.628 |
Fail | +0.609 |
learnt | +0.608 |
XT | +0.589 |
Neg logit contributions | |
trop | -1.849 |
soc | -1.748 |
ftime | -1.703 |
lest | -1.692 |
going | -1.661 |
Token | - |
Token ID | 12 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
hyde | +6.357 |
Fail | +5.967 |
zyk | +5.914 |
learnt | +5.822 |
XT | +5.792 |
Neg logit contributions | |
trop | -12.735 |
soc | -11.765 |
ftime | -11.452 |
acements | -11.381 |
lest | -11.222 |
Token | News |
Token ID | 9980 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
Fail | +2.695 |
hyde | +2.627 |
zyk | +2.572 |
XT | +2.554 |
Po | +2.526 |
Neg logit contributions | |
trop | -9.693 |
ftime | -9.403 |
soc | -9.258 |
lest | -9.153 |
acements | -9.058 |
Token | , |
Token ID | 11 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
hyde | +2.204 |
zyk | +2.048 |
XT | +1.983 |
Fail | +1.980 |
ortmund | +1.975 |
Neg logit contributions | |
trop | -2.144 |
soc | -1.988 |
lest | -1.916 |
ftime | -1.903 |
othe | -1.873 |
Token | Go |
Token ID | 1514 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
trop | +1.440 |
soc | +1.357 |
lest | +1.289 |
ftime | +1.283 |
othe | +1.280 |
Neg logit contributions | |
hyde | -1.363 |
zyk | -1.264 |
ortmund | -1.243 |
learnt | -1.239 |
Fail | -1.234 |
Token | N |
Token ID | 45 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
hyde | +1.003 |
zyk | +0.926 |
Fail | +0.914 |
XT | +0.904 |
ortmund | +0.900 |
Neg logit contributions | |
trop | -1.062 |
soc | -0.996 |
ftime | -0.955 |
lest | -0.948 |
othe | -0.942 |
Token | at |
Token ID | 379 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
hyde | +1.330 |
zyk | +1.228 |
learnt | +1.220 |
ortmund | +1.206 |
XT | +1.193 |
Neg logit contributions | |
trop | -1.870 |
soc | -1.758 |
ftime | -1.682 |
othe | -1.680 |
lest | -1.679 |
Token | stand |
Token ID | 1302 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
hyde | +0.584 |
zyk | +0.534 |
learnt | +0.527 |
ortmund | +0.525 |
XT | +0.518 |
Neg logit contributions | |
trop | -0.832 |
soc | -0.786 |
lest | -0.753 |
ftime | -0.750 |
othe | -0.747 |
Token | - |
Token ID | 12 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
hyde | +1.110 |
zyk | +1.033 |
learnt | +1.023 |
XT | +1.013 |
ortmund | +1.008 |
Neg logit contributions | |
trop | -1.339 |
soc | -1.264 |
lest | -1.195 |
ftime | -1.189 |
othe | -1.185 |
Token | off |
Token ID | 2364 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
hyde | +2.863 |
zyk | +2.665 |
XT | +2.633 |
learnt | +2.613 |
ortmund | +2.576 |
Neg logit contributions | |
trop | -2.765 |
soc | -2.565 |
ftime | -2.449 |
lest | -2.441 |
othe | -2.439 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
trop | +0.134 |
soc | +0.127 |
lest | +0.120 |
ftime | +0.120 |
othe | +0.120 |
Neg logit contributions | |
hyde | -0.110 |
zyk | -0.102 |
learnt | -0.100 |
ortmund | -0.100 |
Fail | -0.099 |
Token | scr |
Token ID | 6040 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
trop | +0.561 |
soc | +0.532 |
lest | +0.506 |
ftime | +0.504 |
othe | +0.504 |
Neg logit contributions | |
hyde | -0.488 |
zyk | -0.449 |
ortmund | -0.442 |
learnt | -0.439 |
Fail | -0.438 |
Token | um |
Token ID | 388 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
zyk | +4.128 |
hyde | +4.034 |
Fail | +3.432 |
ortmund | +3.378 |
XT | +3.315 |
Neg logit contributions | |
trop | -14.248 |
soType | -13.381 |
nomine | -12.949 |
going | -12.858 |
Wem | -12.808 |
Token | - |
Token ID | 12 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
hyde | +1.241 |
zyk | +1.155 |
learnt | +1.137 |
ortmund | +1.119 |
Fail | +1.113 |
Neg logit contributions | |
trop | -1.544 |
soc | -1.456 |
lest | -1.390 |
ftime | -1.379 |
othe | -1.376 |
Token | half |
Token ID | 13959 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
trop | +1.390 |
soc | +1.321 |
lest | +1.260 |
ftime | +1.249 |
going | +1.248 |
Neg logit contributions | |
hyde | -0.995 |
zyk | -0.909 |
ortmund | -0.908 |
learnt | -0.886 |
Fail | -0.883 |
Token | respectively |
Token ID | 8148 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
hyde | +0.438 |
zyk | +0.407 |
learnt | +0.400 |
ortmund | +0.399 |
Fail | +0.397 |
Neg logit contributions | |
trop | -0.454 |
soc | -0.426 |
lest | -0.404 |
ftime | -0.401 |
othe | -0.401 |
Token | . |
Token ID | 13 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
trop | +0.132 |
soc | +0.124 |
lest | +0.118 |
ftime | +0.118 |
othe | +0.117 |
Neg logit contributions | |
hyde | -0.111 |
zyk | -0.103 |
ortmund | -0.101 |
learnt | -0.101 |
Fail | -0.100 |
Token | : |
Token ID | 25 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
hyde | +1.874 |
zyk | +1.736 |
learnt | +1.726 |
Fail | +1.697 |
ortmund | +1.674 |
Neg logit contributions | |
trop | -2.202 |
soc | -2.065 |
ftime | -1.961 |
lest | -1.958 |
othe | -1.955 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
hyde | +0.126 |
zyk | +0.115 |
learnt | +0.113 |
ortmund | +0.112 |
Fail | +0.112 |
Neg logit contributions | |
trop | -0.184 |
soc | -0.174 |
lest | -0.167 |
ftime | -0.166 |
othe | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
hyde | +0.589 |
zyk | +0.554 |
Fail | +0.536 |
learnt | +0.533 |
XT | +0.528 |
Neg logit contributions | |
trop | -1.022 |
soc | -0.966 |
ftime | -0.942 |
Cros | -0.926 |
lest | -0.926 |
Token | Did |
Token ID | 11633 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
hyde | +0.336 |
zyk | +0.310 |
Fail | +0.303 |
learnt | +0.302 |
ortmund | +0.302 |
Neg logit contributions | |
trop | -0.422 |
soc | -0.399 |
ftime | -0.380 |
lest | -0.380 |
othe | -0.379 |
Token | you |
Token ID | 345 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
hyde | +0.270 |
zyk | +0.245 |
learnt | +0.240 |
ortmund | +0.239 |
Fail | +0.239 |
Neg logit contributions | |
trop | -0.438 |
soc | -0.415 |
lest | -0.397 |
ftime | -0.397 |
othe | -0.397 |
Token | enjoy |
Token ID | 2883 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
learnt | +4.516 |
hyde | +4.438 |
zyk | +4.340 |
Fail | +4.240 |
ortmund | +4.002 |
Neg logit contributions | |
trop | -7.074 |
soc | -6.568 |
ftime | -6.445 |
ERA | -6.320 |
going | -6.310 |
Token | this |
Token ID | 428 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
hyde | +6.817 |
learnt | +6.737 |
zyk | +6.603 |
discovery | +6.418 |
text | +6.272 |
Neg logit contributions | |
trop | -10.225 |
soc | -9.610 |
ftime | -9.543 |
acements | -9.443 |
othe | -9.343 |
Token | episode |
Token ID | 4471 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
hyde | +1.990 |
zyk | +1.817 |
learnt | +1.787 |
Fail | +1.690 |
XT | +1.681 |
Neg logit contributions | |
trop | -5.238 |
soc | -5.038 |
ftime | -4.854 |
lest | -4.841 |
othe | -4.820 |
Token | ? |
Token ID | 30 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
hyde | +1.819 |
zyk | +1.631 |
learnt | +1.597 |
Fail | +1.534 |
ortmund | +1.498 |
Neg logit contributions | |
trop | -4.439 |
soc | -4.246 |
ftime | -4.083 |
lest | -4.062 |
ERA | -4.055 |
Token | Thank |
Token ID | 6952 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
hyde | +2.235 |
zyk | +2.099 |
learnt | +2.040 |
Fail | +2.027 |
XT | +2.011 |
Neg logit contributions | |
trop | -3.548 |
soc | -3.344 |
ftime | -3.259 |
lest | -3.206 |
othe | -3.206 |
Token | Will |
Token ID | 2561 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
hyde | +2.098 |
zyk | +1.888 |
Fail | +1.816 |
XT | +1.791 |
learnt | +1.769 |
Neg logit contributions | |
trop | -4.511 |
soc | -4.262 |
ftime | -4.170 |
othe | -4.092 |
lest | -4.090 |
Token | 375 |
Token ID | 22318 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
hyde | +2.528 |
zyk | +2.361 |
learnt | +2.280 |
ortmund | +2.266 |
XT | +2.233 |
Neg logit contributions | |
trop | -3.033 |
soc | -2.898 |
ftime | -2.825 |
Cros | -2.809 |
othe | -2.794 |
Token | 7 |
Token ID | 22 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
hyde | +0.812 |
zyk | +0.750 |
ortmund | +0.728 |
Fail | +0.726 |
learnt | +0.726 |
Neg logit contributions | |
trop | -1.082 |
soc | -1.025 |
ftime | -0.984 |
lest | -0.981 |
Cros | -0.974 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
hyde | +2.811 |
zyk | +2.677 |
learnt | +2.571 |
XT | +2.550 |
ortmund | +2.535 |
Neg logit contributions | |
trop | -3.242 |
soc | -3.089 |
ftime | -2.964 |
Cros | -2.945 |
ERA | -2.933 |
Token | mel |
Token ID | 7758 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
hyde | +0.112 |
zyk | +0.105 |
learnt | +0.104 |
ortmund | +0.103 |
Fail | +0.101 |
Neg logit contributions | |
trop | -0.131 |
soc | -0.124 |
ftime | -0.119 |
lest | -0.119 |
othe | -0.117 |
Token | bourne |
Token ID | 12544 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
hyde | +1.815 |
zyk | +1.713 |
ortmund | +1.635 |
learnt | +1.608 |
Fail | +1.573 |
Neg logit contributions | |
trop | -3.622 |
soc | -3.492 |
Cros | -3.424 |
going | -3.390 |
Wem | -3.387 |
Token | - |
Token ID | 12 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
hyde | +1.621 |
zyk | +1.549 |
learnt | +1.504 |
ortmund | +1.491 |
Fail | +1.485 |
Neg logit contributions | |
trop | -2.030 |
soc | -1.902 |
lest | -1.840 |
ftime | -1.828 |
othe | -1.815 |
Token | 3000 |
Token ID | 23924 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
hyde | +4.677 |
zyk | +4.617 |
mpeg | +4.062 |
Fail | +3.864 |
ortmund | +3.804 |
Neg logit contributions | |
nomine | -12.033 |
soType | -11.607 |
Wem | -11.580 |
Cros | -11.548 |
ftime | -11.543 |
Token | , |
Token ID | 11 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
hyde | +2.796 |
zyk | +2.745 |
ortmund | +2.573 |
XT | +2.565 |
learnt | +2.559 |
Neg logit contributions | |
trop | -4.317 |
soc | -4.015 |
lest | -3.930 |
ERA | -3.903 |
ftime | -3.890 |
Token | vic |
Token ID | 20429 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
hyde | +0.883 |
learnt | +0.841 |
zyk | +0.835 |
ortmund | +0.822 |
Fail | +0.803 |
Neg logit contributions | |
trop | -1.024 |
soc | -0.963 |
ftime | -0.938 |
lest | -0.929 |
ERA | -0.916 |
Token |
|
Token ID | 198 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
trop | +1.521 |
soc | +1.441 |
lest | +1.376 |
ftime | +1.369 |
othe | +1.363 |
Neg logit contributions | |
hyde | -1.199 |
zyk | -1.108 |
ortmund | -1.086 |
learnt | -1.082 |
Fail | -1.074 |
Token |
|
Token ID | 198 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
hyde | +0.848 |
zyk | +0.806 |
learnt | +0.779 |
Fail | +0.776 |
XT | +0.766 |
Neg logit contributions | |
trop | -1.510 |
soc | -1.425 |
ftime | -1.400 |
lest | -1.368 |
othe | -1.368 |
Token | as |
Token ID | 355 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
hyde | +1.296 |
zyk | +1.199 |
learnt | +1.191 |
ortmund | +1.159 |
Fail | +1.154 |
Neg logit contributions | |
trop | -1.819 |
soc | -1.730 |
lest | -1.653 |
ftime | -1.652 |
othe | -1.641 |
Token | well |
Token ID | 880 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
hyde | +1.314 |
zyk | +1.227 |
learnt | +1.209 |
ortmund | +1.194 |
Fail | +1.189 |
Neg logit contributions | |
trop | -1.553 |
soc | -1.465 |
lest | -1.393 |
ftime | -1.380 |
othe | -1.372 |
Token |
|
Token ID | 198 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
hyde | +2.046 |
zyk | +1.925 |
learnt | +1.915 |
ortmund | +1.845 |
Fail | +1.838 |
Neg logit contributions | |
trop | -2.589 |
soc | -2.455 |
lest | -2.334 |
ftime | -2.330 |
othe | -2.317 |
Token |
|
Token ID | 198 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
hyde | +1.444 |
zyk | +1.395 |
Fail | +1.349 |
XT | +1.327 |
learnt | +1.321 |
Neg logit contributions | |
trop | -2.908 |
nomine | -2.746 |
soc | -2.743 |
ftime | -2.725 |
othe | -2.650 |
Token | Marc |
Token ID | 22697 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
hyde | +1.325 |
zyk | +1.224 |
Fail | +1.206 |
ortmund | +1.195 |
learnt | +1.190 |
Neg logit contributions | |
trop | -1.751 |
soc | -1.652 |
ftime | -1.586 |
lest | -1.583 |
othe | -1.577 |
Token | - |
Token ID | 12 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
hyde | +2.372 |
zyk | +2.258 |
learnt | +2.184 |
ortmund | +2.160 |
Fail | +2.157 |
Neg logit contributions | |
trop | -2.927 |
soc | -2.765 |
lest | -2.606 |
ftime | -2.593 |
othe | -2.577 |
Token | And |
Token ID | 1870 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
Fail | +7.664 |
Po | +7.512 |
zyk | +7.491 |
XT | +7.483 |
Cry | +7.224 |
Neg logit contributions | |
nomine | -8.664 |
trop | -8.382 |
ufact | -7.997 |
Wem | -7.882 |
soc | -7.821 |
Token | ré |
Token ID | 29350 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
hyde | +4.171 |
zyk | +4.080 |
ortmund | +4.036 |
learnt | +3.982 |
Fail | +3.929 |
Neg logit contributions | |
trop | -2.910 |
soc | -2.578 |
ftime | -2.447 |
going | -2.402 |
lest | -2.364 |
Token | Fle |
Token ID | 12005 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
hyde | +1.211 |
zyk | +1.120 |
learnt | +1.102 |
Fail | +1.080 |
ortmund | +1.075 |
Neg logit contributions | |
trop | -1.954 |
soc | -1.847 |
lest | -1.766 |
ftime | -1.759 |
othe | -1.743 |
Token | ury |
Token ID | 1601 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
hyde | +4.790 |
zyk | +4.539 |
ortmund | +4.390 |
learnt | +4.354 |
XT | +4.349 |
Neg logit contributions | |
trop | -3.474 |
soc | -3.201 |
Cros | -3.079 |
ftime | -3.032 |
Wem | -2.967 |
Token | accepted |
Token ID | 6292 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
trop | +0.887 |
soc | +0.844 |
lest | +0.805 |
othe | +0.800 |
ftime | +0.800 |
Neg logit contributions | |
hyde | -0.669 |
zyk | -0.609 |
ortmund | -0.602 |
Fail | -0.595 |
learnt | -0.593 |
Token | was |
Token ID | 373 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
hyde | +0.812 |
zyk | +0.746 |
learnt | +0.734 |
ortmund | +0.730 |
Fail | +0.726 |
Neg logit contributions | |
trop | -1.122 |
soc | -1.061 |
lest | -1.018 |
ftime | -1.009 |
othe | -1.009 |
Token | the |
Token ID | 262 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
hyde | +2.520 |
learnt | +2.410 |
Fail | +2.360 |
zyk | +2.329 |
ortmund | +2.298 |
Neg logit contributions | |
trop | -3.676 |
soc | -3.457 |
ftime | -3.292 |
othe | -3.284 |
lest | -3.264 |
Token | most |
Token ID | 749 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
hyde | +1.676 |
zyk | +1.539 |
Fail | +1.511 |
learnt | +1.511 |
ortmund | +1.496 |
Neg logit contributions | |
trop | -2.562 |
soc | -2.435 |
othe | -2.321 |
lest | -2.320 |
ftime | -2.312 |
Token | interesting |
Token ID | 3499 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
learnt | +4.452 |
hyde | +4.124 |
discovery | +4.015 |
Fail | +4.010 |
text | +3.815 |
Neg logit contributions | |
trop | -8.682 |
soc | -8.312 |
ERA | -8.058 |
othe | -7.975 |
ftime | -7.944 |
Token | thing |
Token ID | 1517 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
learnt | +3.761 |
hyde | +3.645 |
discovery | +3.557 |
zyk | +3.527 |
Fail | +3.513 |
Neg logit contributions | |
trop | -6.532 |
soc | -6.241 |
othe | -6.059 |
ftime | -5.996 |
lest | -5.993 |
Token | you |
Token ID | 345 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
learnt | +4.035 |
hyde | +3.608 |
zyk | +3.578 |
XT | +3.478 |
Fail | +3.419 |
Neg logit contributions | |
trop | -9.393 |
soc | -8.645 |
ftime | -8.511 |
othe | -8.436 |
acements | -8.407 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
learnt | +5.505 |
zyk | +4.553 |
hyde | +4.313 |
Fail | +4.009 |
text | +3.893 |
Neg logit contributions | |
trop | -11.642 |
soc | -10.866 |
ftime | -10.799 |
othe | -10.669 |
Wem | -10.611 |
Token | from |
Token ID | 422 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
learnt | +4.329 |
hyde | +4.183 |
zyk | +3.984 |
XT | +3.708 |
ortmund | +3.687 |
Neg logit contributions | |
trop | -7.444 |
soc | -6.908 |
acements | -6.876 |
ftime | -6.862 |
othe | -6.778 |
Token | this |
Token ID | 428 |
Feature activation | +4.69e-03 |
Pos logit contributions | |
hyde | +2.886 |
learnt | +2.765 |
zyk | +2.719 |
Fail | +2.644 |
ortmund | +2.594 |
Neg logit contributions | |
trop | -3.947 |
soc | -3.643 |
ftime | -3.577 |
othe | -3.522 |
lest | -3.521 |
Token | episode |
Token ID | 4471 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
trop | +0.029 |
soc | +0.028 |
lest | +0.027 |
ftime | +0.027 |
othe | +0.027 |
Neg logit contributions | |
hyde | -0.014 |
zyk | -0.012 |
ortmund | -0.012 |
learnt | -0.012 |
Fail | -0.012 |
Token | ? |
Token ID | 30 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
hyde | +1.156 |
zyk | +1.058 |
learnt | +1.037 |
Fail | +1.014 |
ortmund | +1.011 |
Neg logit contributions | |
trop | -2.211 |
soc | -2.095 |
lest | -2.023 |
ftime | -2.014 |
othe | -1.999 |
Token | story |
Token ID | 1621 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
hyde | +1.563 |
zyk | +1.461 |
learnt | +1.413 |
Fail | +1.398 |
ortmund | +1.386 |
Neg logit contributions | |
trop | -2.748 |
soc | -2.587 |
lest | -2.502 |
ftime | -2.488 |
othe | -2.472 |
Token | " |
Token ID | 1 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
hyde | +2.748 |
zyk | +2.576 |
learnt | +2.515 |
ortmund | +2.482 |
Fail | +2.473 |
Neg logit contributions | |
trop | -2.900 |
soc | -2.731 |
lest | -2.576 |
ftime | -2.564 |
othe | -2.543 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
hyde | +1.671 |
zyk | +1.560 |
learnt | +1.535 |
ortmund | +1.521 |
Fail | +1.512 |
Neg logit contributions | |
trop | -1.664 |
soc | -1.565 |
lest | -1.480 |
ftime | -1.479 |
othe | -1.477 |
Token | ( |
Token ID | 7 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
trop | +0.626 |
soc | +0.592 |
lest | +0.565 |
ftime | +0.564 |
othe | +0.562 |
Neg logit contributions | |
hyde | -0.493 |
zyk | -0.454 |
ortmund | -0.445 |
learnt | -0.443 |
Fail | -0.443 |
Token | Phys |
Token ID | 43215 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
trop | +0.380 |
soc | +0.361 |
lest | +0.346 |
ftime | +0.344 |
othe | +0.344 |
Neg logit contributions | |
hyde | -0.239 |
zyk | -0.217 |
ortmund | -0.213 |
learnt | -0.212 |
Fail | -0.210 |
Token | . |
Token ID | 13 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
hyde | +4.180 |
XT | +3.879 |
zyk | +3.732 |
learnt | +3.714 |
Fail | +3.666 |
Neg logit contributions | |
trop | -6.242 |
soc | -6.006 |
lest | -5.853 |
ftime | -5.803 |
going | -5.723 |
Token | org |
Token ID | 2398 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
zyk | +8.617 |
XT | +8.328 |
text | +8.203 |
Cry | +8.170 |
lang | +8.163 |
Neg logit contributions | |
trop | -7.125 |
ftime | -6.759 |
acements | -6.554 |
verson | -6.413 |
icion | -6.408 |
Token | ) |
Token ID | 8 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
hyde | +2.863 |
zyk | +2.616 |
learnt | +2.584 |
XT | +2.531 |
Fail | +2.523 |
Neg logit contributions | |
trop | -5.804 |
soc | -5.540 |
ftime | -5.416 |
Cros | -5.342 |
othe | -5.311 |
Token | -- |
Token ID | 1377 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
hyde | +2.489 |
zyk | +2.278 |
Fail | +2.247 |
learnt | +2.237 |
XT | +2.232 |
Neg logit contributions | |
trop | -3.098 |
soc | -2.901 |
ftime | -2.856 |
othe | -2.774 |
lest | -2.764 |
Token | An |
Token ID | 1052 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
hyde | +1.381 |
zyk | +1.268 |
Fail | +1.250 |
XT | +1.246 |
learnt | +1.238 |
Neg logit contributions | |
trop | -1.825 |
soc | -1.728 |
ftime | -1.666 |
othe | -1.643 |
lest | -1.641 |
Token | international |
Token ID | 3230 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
hyde | +2.903 |
zyk | +2.673 |
learnt | +2.642 |
ortmund | +2.631 |
XT | +2.612 |
Neg logit contributions | |
trop | -3.423 |
soc | -3.238 |
lest | -3.115 |
ftime | -3.111 |
Cros | -3.039 |
Token |
|
Token ID | 198 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
trop | +2.847 |
soc | +2.696 |
Cros | +2.565 |
going | +2.546 |
age | +2.545 |
Neg logit contributions | |
hyde | -2.681 |
ortmund | -2.490 |
zyk | -2.483 |
Fail | -2.404 |
XT | -2.402 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
hyde | +0.965 |
zyk | +0.908 |
Fail | +0.890 |
learnt | +0.874 |
XT | +0.872 |
Neg logit contributions | |
trop | -1.725 |
soc | -1.635 |
ftime | -1.605 |
othe | -1.572 |
lest | -1.569 |
Token | Now |
Token ID | 3844 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
hyde | +0.733 |
zyk | +0.673 |
ortmund | +0.659 |
Fail | +0.657 |
learnt | +0.657 |
Neg logit contributions | |
trop | -1.008 |
soc | -0.956 |
lest | -0.915 |
ftime | -0.913 |
othe | -0.911 |
Token | if |
Token ID | 611 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
hyde | +3.524 |
learnt | +3.317 |
zyk | +3.244 |
ortmund | +3.187 |
Fail | +3.184 |
Neg logit contributions | |
trop | -4.857 |
soc | -4.551 |
ftime | -4.415 |
lest | -4.395 |
othe | -4.339 |
Token | we |
Token ID | 356 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
hyde | +2.253 |
learnt | +2.080 |
zyk | +2.075 |
Fail | +2.025 |
XT | +2.001 |
Neg logit contributions | |
trop | -3.661 |
soc | -3.433 |
lest | -3.350 |
ftime | -3.344 |
othe | -3.302 |
Token | stack |
Token ID | 8931 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
hyde | +2.098 |
zyk | +1.941 |
learnt | +1.926 |
Fail | +1.887 |
ortmund | +1.883 |
Neg logit contributions | |
trop | -3.054 |
soc | -2.889 |
lest | -2.771 |
ftime | -2.771 |
othe | -2.746 |
Token | this |
Token ID | 428 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
hyde | +7.428 |
learnt | +6.824 |
Fail | +6.689 |
zyk | +6.577 |
XT | +6.520 |
Neg logit contributions | |
trop | -8.725 |
lest | -7.961 |
soc | -7.833 |
othe | -7.797 |
soType | -7.721 |
Token | on |
Token ID | 319 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
hyde | +1.076 |
zyk | +0.991 |
learnt | +0.976 |
ortmund | +0.972 |
Fail | +0.966 |
Neg logit contributions | |
trop | -1.330 |
soc | -1.254 |
lest | -1.201 |
ftime | -1.195 |
othe | -1.189 |
Token | top |
Token ID | 1353 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
hyde | +2.520 |
learnt | +2.344 |
zyk | +2.326 |
Fail | +2.300 |
XT | +2.279 |
Neg logit contributions | |
trop | -3.244 |
soc | -3.021 |
ftime | -2.920 |
lest | -2.919 |
othe | -2.901 |
Token | of |
Token ID | 286 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
hyde | +2.201 |
zyk | +2.034 |
learnt | +2.016 |
ortmund | +2.002 |
Fail | +1.999 |
Neg logit contributions | |
trop | -2.528 |
soc | -2.369 |
ftime | -2.288 |
lest | -2.281 |
othe | -2.257 |
Token | our |
Token ID | 674 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
hyde | +0.832 |
zyk | +0.765 |
learnt | +0.760 |
Fail | +0.748 |
ortmund | +0.744 |
Neg logit contributions | |
trop | -1.045 |
soc | -0.983 |
lest | -0.946 |
ftime | -0.945 |
othe | -0.937 |
Token | it |
Token ID | 270 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
trop | +2.955 |
soc | +2.687 |
lest | +2.580 |
othe | +2.508 |
age | +2.493 |
Neg logit contributions | |
hyde | -5.511 |
ortmund | -5.201 |
zyk | -5.193 |
learnt | -5.165 |
Fail | -5.140 |
Token | published |
Token ID | 3199 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
hyde | +1.240 |
zyk | +1.165 |
learnt | +1.157 |
ortmund | +1.133 |
Fail | +1.120 |
Neg logit contributions | |
trop | -1.339 |
soc | -1.248 |
ftime | -1.176 |
Cros | -1.174 |
lest | -1.173 |
Token | in |
Token ID | 287 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
trop | +2.063 |
soc | +1.937 |
lest | +1.830 |
ftime | +1.821 |
othe | +1.820 |
Neg logit contributions | |
hyde | -2.311 |
zyk | -2.149 |
ortmund | -2.122 |
learnt | -2.110 |
Fail | -2.109 |
Token | the |
Token ID | 262 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
hyde | +0.398 |
zyk | +0.368 |
learnt | +0.359 |
Fail | +0.358 |
ortmund | +0.358 |
Neg logit contributions | |
trop | -0.465 |
soc | -0.438 |
lest | -0.417 |
ftime | -0.417 |
othe | -0.414 |
Token | Richmond |
Token ID | 16940 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
hyde | +0.201 |
zyk | +0.187 |
learnt | +0.183 |
ortmund | +0.182 |
Fail | +0.181 |
Neg logit contributions | |
trop | -0.233 |
soc | -0.219 |
lest | -0.209 |
ftime | -0.208 |
othe | -0.207 |
Token | Times |
Token ID | 3782 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
hyde | +0.520 |
zyk | +0.481 |
learnt | +0.469 |
Fail | +0.465 |
ortmund | +0.464 |
Neg logit contributions | |
trop | -0.743 |
soc | -0.696 |
lest | -0.667 |
ftime | -0.665 |
othe | -0.659 |
Token | - |
Token ID | 12 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
hyde | +5.597 |
zyk | +5.490 |
XT | +5.490 |
Po | +5.332 |
Fail | +5.313 |
Neg logit contributions | |
trop | -9.711 |
soc | -8.924 |
lest | -8.893 |
ERA | -8.788 |
ftime | -8.765 |
Token | Dispatch |
Token ID | 49354 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
hyde | +3.209 |
zyk | +3.110 |
Fail | +3.029 |
XT | +2.976 |
Po | +2.788 |
Neg logit contributions | |
trop | -7.936 |
ftime | -7.560 |
soc | -7.491 |
lest | -7.414 |
Cros | -7.365 |
Token | . |
Token ID | 13 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
hyde | +2.001 |
zyk | +1.877 |
learnt | +1.833 |
ortmund | +1.814 |
Fail | +1.802 |
Neg logit contributions | |
trop | -2.269 |
soc | -2.099 |
lest | -2.029 |
ftime | -2.004 |
acements | -1.964 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
trop | +4.031 |
soc | +3.827 |
lest | +3.653 |
othe | +3.647 |
Cros | +3.633 |
Neg logit contributions | |
hyde | -3.868 |
ortmund | -3.566 |
zyk | -3.565 |
learnt | -3.545 |
Fail | -3.490 |
Token | Elf |
Token ID | 46995 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
trop | +0.849 |
soc | +0.804 |
lest | +0.767 |
ftime | +0.764 |
othe | +0.763 |
Neg logit contributions | |
hyde | -0.667 |
zyk | -0.613 |
ortmund | -0.602 |
learnt | -0.600 |
Fail | -0.598 |
Token | a |
Token ID | 257 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
hyde | +3.403 |
learnt | +3.173 |
zyk | +3.169 |
Fail | +3.078 |
XT | +3.077 |
Neg logit contributions | |
trop | -5.242 |
soc | -4.931 |
ftime | -4.749 |
lest | -4.744 |
othe | -4.735 |
Token | critical |
Token ID | 4688 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
hyde | +2.181 |
zyk | +2.009 |
learnt | +1.982 |
Fail | +1.967 |
XT | +1.939 |
Neg logit contributions | |
trop | -3.440 |
soc | -3.244 |
ftime | -3.122 |
lest | -3.122 |
othe | -3.081 |
Token | error |
Token ID | 4049 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
hyde | +2.336 |
zyk | +2.146 |
Fail | +2.109 |
learnt | +2.092 |
ortmund | +2.077 |
Neg logit contributions | |
trop | -3.751 |
soc | -3.535 |
ftime | -3.379 |
lest | -3.375 |
othe | -3.360 |
Token | ( |
Token ID | 357 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
hyde | +1.156 |
zyk | +1.071 |
learnt | +1.058 |
ortmund | +1.053 |
Fail | +1.047 |
Neg logit contributions | |
trop | -1.298 |
soc | -1.222 |
lest | -1.159 |
ftime | -1.158 |
othe | -1.155 |
Token | a |
Token ID | 64 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
hyde | +3.437 |
zyk | +3.219 |
Fail | +3.212 |
XT | +3.184 |
learnt | +3.144 |
Neg logit contributions | |
trop | -3.353 |
soc | -3.119 |
ftime | -3.015 |
Cros | -2.985 |
othe | -2.980 |
Token | kernel |
Token ID | 9720 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
hyde | +2.744 |
zyk | +2.534 |
Fail | +2.504 |
learnt | +2.503 |
XT | +2.468 |
Neg logit contributions | |
trop | -3.910 |
soc | -3.655 |
ftime | -3.517 |
lest | -3.515 |
othe | -3.487 |
Token | panic |
Token ID | 13619 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
hyde | +5.719 |
learnt | +5.527 |
Fail | +5.502 |
zyk | +5.398 |
XT | +5.304 |
Neg logit contributions | |
trop | -10.120 |
soc | -9.186 |
ftime | -9.166 |
soType | -9.027 |
lest | -9.025 |
Token | ), |
Token ID | 828 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
hyde | +5.177 |
learnt | +4.795 |
Fail | +4.785 |
zyk | +4.785 |
XT | +4.675 |
Neg logit contributions | |
trop | -8.586 |
soc | -8.241 |
ftime | -7.792 |
acements | -7.784 |
othe | -7.725 |
Token | it |
Token ID | 340 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
hyde | +1.487 |
zyk | +1.381 |
learnt | +1.364 |
Fail | +1.352 |
ortmund | +1.349 |
Neg logit contributions | |
trop | -1.665 |
soc | -1.567 |
ftime | -1.491 |
othe | -1.485 |
lest | -1.482 |
Token | automatically |
Token ID | 6338 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
hyde | +1.367 |
zyk | +1.260 |
learnt | +1.253 |
Fail | +1.222 |
ortmund | +1.218 |
Neg logit contributions | |
trop | -1.946 |
soc | -1.848 |
ftime | -1.763 |
othe | -1.752 |
lest | -1.752 |
Token | reb |
Token ID | 3405 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
trop | +0.354 |
soc | +0.335 |
lest | +0.320 |
othe | +0.318 |
ftime | +0.318 |
Neg logit contributions | |
hyde | -0.280 |
zyk | -0.257 |
ortmund | -0.254 |
Fail | -0.250 |
learnt | -0.250 |
Token | 4 |
Token ID | 604 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
hyde | +1.013 |
zyk | +0.940 |
learnt | +0.928 |
ortmund | +0.922 |
Fail | +0.914 |
Neg logit contributions | |
trop | -1.226 |
soc | -1.160 |
lest | -1.108 |
ftime | -1.103 |
othe | -1.098 |
Token | 272 |
Token ID | 29807 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
hyde | +2.732 |
zyk | +2.573 |
XT | +2.522 |
learnt | +2.507 |
ortmund | +2.481 |
Neg logit contributions | |
trop | -3.229 |
soc | -3.027 |
lest | -2.934 |
ftime | -2.934 |
othe | -2.906 |
Token | px |
Token ID | 8416 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
hyde | +5.179 |
XT | +5.006 |
zyk | +4.943 |
learnt | +4.767 |
Fail | +4.698 |
Neg logit contributions | |
trop | -7.266 |
lest | -6.876 |
soc | -6.771 |
ftime | -6.607 |
othe | -6.518 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
hyde | +1.352 |
zyk | +1.256 |
ortmund | +1.234 |
learnt | +1.230 |
Fail | +1.217 |
Neg logit contributions | |
trop | -1.599 |
soc | -1.511 |
lest | -1.448 |
ftime | -1.439 |
othe | -1.434 |
Token | 44 |
Token ID | 5846 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
trop | +0.667 |
soc | +0.629 |
lest | +0.598 |
Cros | +0.594 |
going | +0.594 |
Neg logit contributions | |
hyde | -0.598 |
zyk | -0.549 |
ortmund | -0.540 |
Fail | -0.538 |
learnt | -0.536 |
Token | 80 |
Token ID | 1795 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
hyde | +1.840 |
zyk | +1.713 |
learnt | +1.678 |
ortmund | +1.674 |
Fail | +1.665 |
Neg logit contributions | |
trop | -1.996 |
soc | -1.880 |
lest | -1.797 |
ftime | -1.786 |
othe | -1.778 |
Token | px |
Token ID | 8416 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
hyde | +5.165 |
zyk | +5.010 |
XT | +4.976 |
learnt | +4.713 |
text | +4.644 |
Neg logit contributions | |
trop | -10.108 |
lest | -9.563 |
soc | -9.427 |
ftime | -9.323 |
Cros | -9.222 |
Token | and |
Token ID | 290 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
hyde | +0.678 |
zyk | +0.634 |
ortmund | +0.625 |
learnt | +0.623 |
Fail | +0.619 |
Neg logit contributions | |
trop | -0.600 |
soc | -0.563 |
lest | -0.533 |
ftime | -0.530 |
othe | -0.528 |
Token | 41 |
Token ID | 6073 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
trop | +1.537 |
soc | +1.451 |
Cros | +1.388 |
going | +1.381 |
age | +1.377 |
Neg logit contributions | |
hyde | -1.315 |
zyk | -1.184 |
ortmund | -1.179 |
Fail | -1.163 |
learnt | -1.153 |
Token | 12 |
Token ID | 1065 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
trop | +1.571 |
soc | +1.481 |
lest | +1.387 |
othe | +1.383 |
Cros | +1.375 |
Neg logit contributions | |
hyde | -1.879 |
zyk | -1.737 |
ortmund | -1.731 |
learnt | -1.703 |
Fail | -1.698 |
Token | px |
Token ID | 8416 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
hyde | +3.101 |
zyk | +2.958 |
XT | +2.874 |
learnt | +2.796 |
Fail | +2.751 |
Neg logit contributions | |
trop | -7.441 |
soc | -7.039 |
lest | -6.955 |
Cros | -6.947 |
ftime | -6.896 |
Token | 29 |
Token ID | 2808 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
trop | +2.259 |
soc | +2.140 |
Cros | +2.034 |
lest | +2.014 |
going | +2.004 |
Neg logit contributions | |
hyde | -2.637 |
zyk | -2.412 |
ortmund | -2.411 |
VIDIA | -2.370 |
�� | -2.370 |
Token | . |
Token ID | 13 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
hyde | +4.121 |
learnt | +3.806 |
zyk | +3.772 |
ortmund | +3.737 |
XT | +3.639 |
Neg logit contributions | |
trop | -6.238 |
soc | -5.718 |
othe | -5.583 |
Cros | -5.546 |
ftime | -5.532 |
Token |
|
Token ID | 198 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
trop | +0.230 |
soc | +0.218 |
lest | +0.209 |
ftime | +0.208 |
othe | +0.208 |
Neg logit contributions | |
hyde | -0.154 |
zyk | -0.141 |
ortmund | -0.138 |
learnt | -0.137 |
Fail | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
hyde | +0.302 |
zyk | +0.282 |
Fail | +0.272 |
learnt | +0.272 |
ortmund | +0.270 |
Neg logit contributions | |
trop | -0.488 |
soc | -0.461 |
ftime | -0.448 |
lest | -0.443 |
othe | -0.442 |
Token | Republic |
Token ID | 15431 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
hyde | +0.294 |
zyk | +0.272 |
Fail | +0.266 |
ortmund | +0.266 |
learnt | +0.264 |
Neg logit contributions | |
trop | -0.368 |
soc | -0.346 |
lest | -0.331 |
othe | -0.331 |
ftime | -0.330 |
Token | Of |
Token ID | 3226 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
hyde | +4.831 |
zyk | +4.567 |
ortmund | +4.534 |
Fail | +4.481 |
learnt | +4.473 |
Neg logit contributions | |
trop | -6.530 |
lest | -5.836 |
soc | -5.833 |
Cros | -5.710 |
verson | -5.701 |
Token | Ireland |
Token ID | 7517 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
zyk | +5.694 |
hyde | +5.637 |
Whilst | +5.601 |
Fail | +5.596 |
learnt | +5.526 |
Neg logit contributions | |
trop | -9.649 |
ftime | -9.047 |
soc | -8.983 |
nomine | -8.892 |
aging | -8.763 |
Token | : |
Token ID | 25 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
hyde | +2.235 |
zyk | +2.118 |
learnt | +2.101 |
ortmund | +2.080 |
Fail | +2.063 |
Neg logit contributions | |
trop | -2.818 |
soc | -2.562 |
lest | -2.539 |
othe | -2.514 |
ftime | -2.482 |
Token | Moran |
Token ID | 42705 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
trop | +0.541 |
soc | +0.510 |
lest | +0.483 |
ftime | +0.481 |
othe | +0.480 |
Neg logit contributions | |
hyde | -0.545 |
zyk | -0.506 |
ortmund | -0.498 |
learnt | -0.497 |
Fail | -0.494 |
Token | , |
Token ID | 11 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
trop | +0.147 |
soc | +0.138 |
lest | +0.131 |
ftime | +0.130 |
othe | +0.130 |
Neg logit contributions | |
hyde | -0.142 |
zyk | -0.132 |
learnt | -0.130 |
ortmund | -0.130 |
Fail | -0.129 |
Token | Benson |
Token ID | 33940 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
hyde | +0.367 |
zyk | +0.341 |
ortmund | +0.335 |
learnt | +0.334 |
Fail | +0.332 |
Neg logit contributions | |
trop | -0.382 |
soc | -0.358 |
lest | -0.340 |
ftime | -0.339 |
othe | -0.338 |
Token | to |
Token ID | 284 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
trop | +3.075 |
soc | +2.896 |
othe | +2.752 |
lest | +2.748 |
age | +2.744 |
Neg logit contributions | |
hyde | -2.707 |
zyk | -2.511 |
ortmund | -2.480 |
Fail | -2.449 |
learnt | -2.441 |
Token | scene |
Token ID | 3715 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
trop | +1.939 |
soc | +1.854 |
lest | +1.777 |
othe | +1.771 |
Cros | +1.769 |
Neg logit contributions | |
hyde | -1.458 |
zyk | -1.335 |
ortmund | -1.301 |
learnt | -1.290 |
XT | -1.271 |
Token | ! |
Token ID | 0 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
hyde | +1.273 |
zyk | +1.171 |
learnt | +1.151 |
Fail | +1.150 |
ortmund | +1.146 |
Neg logit contributions | |
trop | -1.609 |
soc | -1.520 |
lest | -1.450 |
ftime | -1.444 |
othe | -1.438 |
Token | During |
Token ID | 5856 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
hyde | +0.237 |
zyk | +0.217 |
ortmund | +0.213 |
learnt | +0.213 |
Fail | +0.212 |
Neg logit contributions | |
trop | -0.329 |
soc | -0.311 |
lest | -0.298 |
ftime | -0.297 |
othe | -0.296 |
Token | some |
Token ID | 617 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
hyde | +0.725 |
zyk | +0.670 |
learnt | +0.659 |
ortmund | +0.659 |
Fail | +0.656 |
Neg logit contributions | |
trop | -0.880 |
soc | -0.831 |
lest | -0.791 |
ftime | -0.790 |
othe | -0.787 |
Token | brain |
Token ID | 3632 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
trop | +0.619 |
soc | +0.585 |
lest | +0.557 |
ftime | +0.555 |
othe | +0.554 |
Neg logit contributions | |
hyde | -0.541 |
zyk | -0.500 |
ortmund | -0.491 |
learnt | -0.488 |
Fail | -0.486 |
Token | storms |
Token ID | 38563 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
hyde | +7.777 |
learnt | +7.263 |
zyk | +7.204 |
Fail | +7.142 |
XT | +6.963 |
Neg logit contributions | |
trop | -7.882 |
soc | -7.402 |
Cros | -7.302 |
Wem | -7.258 |
othe | -7.178 |
Token | on |
Token ID | 319 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
trop | +0.558 |
soc | +0.526 |
lest | +0.499 |
ftime | +0.497 |
othe | +0.496 |
Neg logit contributions | |
hyde | -0.541 |
zyk | -0.501 |
ortmund | -0.493 |
learnt | -0.491 |
Fail | -0.489 |
Token | genres |
Token ID | 27962 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
hyde | +1.614 |
zyk | +1.497 |
learnt | +1.497 |
Fail | +1.484 |
ortmund | +1.478 |
Neg logit contributions | |
trop | -1.956 |
soc | -1.845 |
lest | -1.764 |
ftime | -1.758 |
othe | -1.746 |
Token | of |
Token ID | 286 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
hyde | +2.962 |
learnt | +2.802 |
zyk | +2.801 |
ortmund | +2.771 |
Fail | +2.764 |
Neg logit contributions | |
trop | -2.990 |
soc | -2.797 |
lest | -2.668 |
othe | -2.653 |
ftime | -2.645 |
Token | games |
Token ID | 1830 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
hyde | +1.208 |
zyk | +1.115 |
learnt | +1.098 |
Fail | +1.091 |
ortmund | +1.086 |
Neg logit contributions | |
trop | -1.647 |
soc | -1.560 |
lest | -1.493 |
ftime | -1.490 |
othe | -1.484 |
Token | "] |
Token ID | 8973 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
hyde | +3.125 |
ortmund | +2.956 |
zyk | +2.948 |
learnt | +2.912 |
XT | +2.877 |
Neg logit contributions | |
trop | -3.121 |
soc | -2.882 |
ftime | -2.764 |
Cros | -2.739 |
lest | -2.728 |
Token | [ |
Token ID | 685 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
hyde | +1.300 |
ortmund | +1.199 |
zyk | +1.198 |
learnt | +1.189 |
XT | +1.164 |
Neg logit contributions | |
trop | -1.810 |
soc | -1.708 |
lest | -1.646 |
ftime | -1.640 |
othe | -1.636 |
Token | Date |
Token ID | 10430 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
hyde | +3.170 |
Fail | +3.046 |
zyk | +3.015 |
XT | +2.985 |
learnt | +2.956 |
Neg logit contributions | |
trop | -3.243 |
soc | -3.031 |
othe | -2.972 |
ftime | -2.891 |
Cros | -2.871 |
Token | " |
Token ID | 366 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
trop | +2.745 |
soc | +2.391 |
age | +2.356 |
ftime | +2.277 |
lest | +2.214 |
Neg logit contributions | |
hyde | -5.266 |
zyk | -4.907 |
�� | -4.885 |
ortmund | -4.793 |
VIDIA | -4.755 |
Token | 2016 |
Token ID | 5304 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
hyde | +2.806 |
zyk | +2.689 |
XT | +2.670 |
Fail | +2.669 |
learnt | +2.623 |
Neg logit contributions | |
trop | -3.554 |
soc | -3.300 |
ftime | -3.256 |
othe | -3.231 |
Cros | -3.187 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
hyde | +1.768 |
zyk | +1.659 |
ortmund | +1.618 |
XT | +1.607 |
learnt | +1.600 |
Neg logit contributions | |
trop | -2.369 |
soc | -2.224 |
ftime | -2.150 |
othe | -2.134 |
lest | -2.132 |
Token | 01 |
Token ID | 486 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Fail | +4.937 |
hyde | +4.910 |
zyk | +4.861 |
XT | +4.817 |
Cry | +4.652 |
Neg logit contributions | |
nomine | -10.352 |
trop | -10.261 |
ftime | -9.654 |
demographics | -9.575 |
verson | -9.434 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
zyk | +3.646 |
hyde | +3.527 |
XT | +3.497 |
Fail | +3.401 |
ortmund | +3.332 |
Neg logit contributions | |
nomine | -7.270 |
trop | -7.236 |
ftime | -6.820 |
soc | -6.715 |
ufact | -6.630 |
Token | 29 |
Token ID | 1959 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
hyde | +3.871 |
zyk | +3.736 |
XT | +3.706 |
Fail | +3.704 |
ortmund | +3.494 |
Neg logit contributions | |
trop | -5.531 |
nomine | -5.337 |
ftime | -5.214 |
soc | -5.186 |
othe | -5.064 |
Token | "] |
Token ID | 8973 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
hyde | +3.716 |
XT | +3.565 |
zyk | +3.559 |
Fail | +3.507 |
ortmund | +3.465 |
Neg logit contributions | |
trop | -5.961 |
soc | -5.576 |
othe | -5.424 |
ftime | -5.420 |
verson | -5.327 |
Token | [ |
Token ID | 685 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
hyde | +1.180 |
zyk | +1.113 |
learnt | +1.107 |
ortmund | +1.091 |
Fail | +1.082 |
Neg logit contributions | |
trop | -1.733 |
soc | -1.628 |
ftime | -1.578 |
othe | -1.576 |
lest | -1.568 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
hyde | +1.408 |
zyk | +1.301 |
learnt | +1.261 |
XT | +1.249 |
Fail | +1.245 |
Neg logit contributions | |
trop | -1.855 |
soc | -1.764 |
othe | -1.672 |
lest | -1.668 |
ftime | -1.650 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
hyde | +0.707 |
zyk | +0.649 |
Fail | +0.632 |
ortmund | +0.631 |
learnt | +0.630 |
Neg logit contributions | |
trop | -0.998 |
soc | -0.942 |
lest | -0.901 |
ftime | -0.901 |
othe | -0.897 |
Token |
|
Token ID | 198 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
hyde | +0.462 |
zyk | +0.432 |
Fail | +0.420 |
learnt | +0.416 |
XT | +0.413 |
Neg logit contributions | |
trop | -0.770 |
soc | -0.727 |
ftime | -0.709 |
lest | -0.698 |
othe | -0.696 |
Token | Ford |
Token ID | 37308 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
hyde | +0.709 |
zyk | +0.652 |
Fail | +0.637 |
ortmund | +0.637 |
learnt | +0.634 |
Neg logit contributions | |
trop | -0.966 |
soc | -0.913 |
lest | -0.873 |
ftime | -0.873 |
othe | -0.870 |
Token | was |
Token ID | 373 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
hyde | +0.760 |
zyk | +0.702 |
learnt | +0.687 |
Fail | +0.684 |
ortmund | +0.683 |
Neg logit contributions | |
trop | -0.935 |
soc | -0.881 |
lest | -0.841 |
ftime | -0.837 |
othe | -0.835 |
Token | ind |
Token ID | 773 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
hyde | +0.469 |
zyk | +0.432 |
ortmund | +0.424 |
learnt | +0.423 |
Fail | +0.421 |
Neg logit contributions | |
trop | -0.583 |
soc | -0.551 |
lest | -0.526 |
ftime | -0.524 |
othe | -0.523 |
Token | ignant |
Token ID | 25114 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
hyde | +5.211 |
zyk | +4.775 |
XT | +4.664 |
Fail | +4.506 |
learnt | +4.477 |
Neg logit contributions | |
trop | -10.007 |
soc | -9.238 |
demographics | -9.180 |
ftime | -9.167 |
Cros | -9.119 |
Token | . |
Token ID | 13 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
trop | +2.365 |
soc | +2.242 |
lest | +2.109 |
going | +2.102 |
othe | +2.101 |
Neg logit contributions | |
hyde | -2.521 |
ortmund | -2.315 |
zyk | -2.312 |
Fail | -2.294 |
learnt | -2.254 |
Token | He |
Token ID | 679 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
hyde | +0.990 |
zyk | +0.919 |
Fail | +0.899 |
learnt | +0.892 |
ortmund | +0.892 |
Neg logit contributions | |
trop | -1.186 |
soc | -1.112 |
ftime | -1.063 |
lest | -1.058 |
othe | -1.055 |
Token | denied |
Token ID | 6699 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
hyde | +2.381 |
zyk | +2.229 |
learnt | +2.207 |
Fail | +2.090 |
ortmund | +2.074 |
Neg logit contributions | |
trop | -3.494 |
soc | -3.324 |
ftime | -3.152 |
lest | -3.145 |
othe | -3.126 |
Token | the |
Token ID | 262 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
hyde | +0.665 |
zyk | +0.613 |
learnt | +0.601 |
ortmund | +0.600 |
Fail | +0.597 |
Neg logit contributions | |
trop | -0.834 |
soc | -0.788 |
lest | -0.751 |
ftime | -0.751 |
othe | -0.747 |
Token | . |
Token ID | 13 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
hyde | +3.393 |
zyk | +3.255 |
learnt | +3.202 |
Fail | +3.156 |
XT | +3.135 |
Neg logit contributions | |
trop | -5.207 |
soc | -4.932 |
ftime | -4.804 |
Cros | -4.743 |
lest | -4.720 |
Token | e |
Token ID | 68 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
hyde | +3.272 |
zyk | +3.211 |
XT | +3.210 |
Fail | +3.156 |
learnt | +3.082 |
Neg logit contributions | |
trop | -3.511 |
nomine | -3.321 |
ftime | -3.245 |
soc | -3.181 |
Cros | -3.144 |
Token | . |
Token ID | 13 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
hyde | +0.534 |
zyk | +0.493 |
ortmund | +0.484 |
learnt | +0.483 |
Fail | +0.480 |
Neg logit contributions | |
trop | -0.619 |
soc | -0.584 |
lest | -0.557 |
ftime | -0.554 |
othe | -0.553 |
Token | is |
Token ID | 318 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
hyde | +1.417 |
zyk | +1.303 |
learnt | +1.277 |
ortmund | +1.277 |
Fail | +1.270 |
Neg logit contributions | |
trop | -1.864 |
soc | -1.766 |
lest | -1.685 |
ftime | -1.680 |
othe | -1.677 |
Token | the |
Token ID | 262 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
hyde | +1.872 |
zyk | +1.729 |
learnt | +1.702 |
Fail | +1.691 |
ortmund | +1.688 |
Neg logit contributions | |
trop | -2.365 |
soc | -2.237 |
lest | -2.129 |
ftime | -2.124 |
othe | -2.116 |
Token | syntax |
Token ID | 15582 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
hyde | +1.666 |
zyk | +1.520 |
learnt | +1.501 |
Fail | +1.481 |
ortmund | +1.481 |
Neg logit contributions | |
trop | -2.700 |
soc | -2.566 |
lest | -2.457 |
ftime | -2.451 |
othe | -2.441 |
Token | just |
Token ID | 655 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
hyde | +6.616 |
learnt | +6.602 |
zyk | +6.288 |
Fail | +6.201 |
XT | +5.937 |
Neg logit contributions | |
trop | -8.955 |
soc | -8.426 |
ftime | -8.031 |
othe | -8.002 |
onica | -7.902 |
Token | as |
Token ID | 355 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
hyde | +2.886 |
learnt | +2.690 |
zyk | +2.676 |
Fail | +2.631 |
ortmund | +2.593 |
Neg logit contributions | |
trop | -3.835 |
soc | -3.643 |
lest | -3.466 |
ftime | -3.460 |
othe | -3.442 |
Token | rich |
Token ID | 5527 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
hyde | +2.466 |
zyk | +2.279 |
learnt | +2.257 |
Fail | +2.220 |
ortmund | +2.210 |
Neg logit contributions | |
trop | -3.454 |
soc | -3.274 |
lest | -3.129 |
ftime | -3.123 |
othe | -3.094 |
Token | , |
Token ID | 11 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
hyde | +6.134 |
learnt | +5.823 |
zyk | +5.747 |
Fail | +5.569 |
ortmund | +5.489 |
Neg logit contributions | |
trop | -7.043 |
soc | -6.725 |
ftime | -6.477 |
Cros | -6.394 |
othe | -6.393 |
Token | can |
Token ID | 460 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
hyde | +3.716 |
learnt | +3.470 |
zyk | +3.456 |
Fail | +3.385 |
XT | +3.334 |
Neg logit contributions | |
trop | -4.937 |
soc | -4.698 |
ftime | -4.497 |
othe | -4.459 |
lest | -4.458 |
Token | Mike |
Token ID | 16073 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
trop | +0.861 |
soc | +0.814 |
lest | +0.774 |
ftime | +0.771 |
othe | +0.769 |
Neg logit contributions | |
hyde | -0.752 |
zyk | -0.694 |
ortmund | -0.683 |
learnt | -0.681 |
Fail | -0.677 |
Token | Richards |
Token ID | 14743 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
hyde | +0.072 |
zyk | +0.067 |
ortmund | +0.065 |
learnt | +0.065 |
Fail | +0.065 |
Neg logit contributions | |
trop | -0.084 |
soc | -0.079 |
lest | -0.075 |
ftime | -0.075 |
othe | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
hyde | +0.326 |
zyk | +0.302 |
ortmund | +0.293 |
Fail | +0.290 |
learnt | +0.290 |
Neg logit contributions | |
trop | -0.472 |
soc | -0.444 |
lest | -0.426 |
othe | -0.425 |
ftime | -0.425 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
hyde | +0.821 |
zyk | +0.781 |
Fail | +0.752 |
learnt | +0.745 |
XT | +0.744 |
Neg logit contributions | |
trop | -1.506 |
soc | -1.417 |
ftime | -1.394 |
nomine | -1.374 |
Cros | -1.368 |
Token | Daniel |
Token ID | 19962 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
trop | +0.981 |
soc | +0.928 |
lest | +0.883 |
ftime | +0.878 |
othe | +0.876 |
Neg logit contributions | |
hyde | -0.859 |
zyk | -0.792 |
ortmund | -0.780 |
learnt | -0.778 |
Fail | -0.770 |
Token | Winn |
Token ID | 19454 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
hyde | +0.429 |
zyk | +0.399 |
learnt | +0.391 |
ortmund | +0.389 |
Fail | +0.388 |
Neg logit contributions | |
trop | -0.456 |
soc | -0.429 |
lest | -0.407 |
ftime | -0.407 |
othe | -0.405 |
Token | ik |
Token ID | 1134 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
zyk | +6.241 |
hyde | +5.486 |
JS | +4.748 |
learnt | +4.738 |
Po | +4.653 |
Neg logit contributions | |
trop | -10.052 |
ftime | -9.161 |
soc | -8.944 |
Cros | -8.929 |
soType | -8.899 |
Token |
|
Token ID | 198 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
hyde | +1.028 |
zyk | +0.955 |
ortmund | +0.914 |
Fail | +0.901 |
learnt | +0.899 |
Neg logit contributions | |
trop | -1.550 |
soc | -1.457 |
lest | -1.397 |
ftime | -1.386 |
othe | -1.383 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
hyde | +1.370 |
zyk | +1.328 |
Fail | +1.276 |
XT | +1.262 |
learnt | +1.255 |
Neg logit contributions | |
trop | -2.794 |
nomine | -2.640 |
soc | -2.621 |
ftime | -2.603 |
Cros | -2.545 |
Token | Nick |
Token ID | 23609 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
trop | +0.764 |
soc | +0.722 |
lest | +0.687 |
ftime | +0.683 |
othe | +0.682 |
Neg logit contributions | |
hyde | -0.667 |
zyk | -0.616 |
ortmund | -0.606 |
learnt | -0.604 |
Fail | -0.599 |
Token | las |
Token ID | 21921 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
trop | +0.056 |
soc | +0.053 |
lest | +0.051 |
ftime | +0.050 |
othe | +0.050 |
Neg logit contributions | |
hyde | -0.045 |
zyk | -0.042 |
learnt | -0.041 |
ortmund | -0.041 |
Fail | -0.040 |
Token | code |
Token ID | 2438 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
hyde | +1.724 |
zyk | +1.614 |
learnt | +1.590 |
Fail | +1.577 |
XT | +1.575 |
Neg logit contributions | |
trop | -1.926 |
soc | -1.806 |
lest | -1.729 |
ftime | -1.728 |
othe | -1.713 |
Token | faster |
Token ID | 5443 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
hyde | +2.953 |
learnt | +2.775 |
zyk | +2.773 |
XT | +2.706 |
Fail | +2.664 |
Neg logit contributions | |
trop | -3.546 |
soc | -3.369 |
ftime | -3.233 |
lest | -3.207 |
othe | -3.203 |
Token | , |
Token ID | 11 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
hyde | +3.684 |
zyk | +3.521 |
learnt | +3.498 |
XT | +3.439 |
Fail | +3.393 |
Neg logit contributions | |
trop | -4.094 |
soc | -3.893 |
ftime | -3.700 |
lest | -3.693 |
othe | -3.669 |
Token | but |
Token ID | 475 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
hyde | +1.858 |
zyk | +1.746 |
learnt | +1.731 |
Fail | +1.696 |
XT | +1.691 |
Neg logit contributions | |
trop | -2.303 |
soc | -2.169 |
ftime | -2.076 |
lest | -2.065 |
othe | -2.036 |
Token | optimized |
Token ID | 23392 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
hyde | +1.253 |
zyk | +1.162 |
learnt | +1.142 |
ortmund | +1.131 |
Fail | +1.131 |
Neg logit contributions | |
trop | -1.633 |
soc | -1.544 |
ftime | -1.476 |
lest | -1.475 |
othe | -1.459 |
Token | native |
Token ID | 6868 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
hyde | +3.326 |
zyk | +3.189 |
XT | +3.163 |
learnt | +3.161 |
Fail | +3.094 |
Neg logit contributions | |
trop | -4.700 |
soc | -4.391 |
ftime | -4.272 |
lest | -4.225 |
othe | -4.203 |
Token | libraries |
Token ID | 12782 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
XT | +6.830 |
hyde | +6.715 |
learnt | +6.611 |
zyk | +6.609 |
Fail | +6.512 |
Neg logit contributions | |
trop | -8.116 |
soc | -7.497 |
ftime | -7.279 |
othe | -7.182 |
soType | -7.177 |
Token | are |
Token ID | 389 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
hyde | +4.405 |
learnt | +4.283 |
zyk | +4.176 |
Fail | +4.087 |
ortmund | +4.030 |
Neg logit contributions | |
trop | -5.210 |
soc | -4.939 |
ftime | -4.787 |
lest | -4.692 |
ERA | -4.599 |
Token | what |
Token ID | 644 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
hyde | +0.944 |
zyk | +0.872 |
learnt | +0.864 |
ortmund | +0.847 |
Fail | +0.846 |
Neg logit contributions | |
trop | -1.253 |
soc | -1.187 |
lest | -1.132 |
ftime | -1.132 |
othe | -1.124 |
Token | really |
Token ID | 1107 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
hyde | +1.415 |
zyk | +1.318 |
learnt | +1.312 |
XT | +1.292 |
Fail | +1.289 |
Neg logit contributions | |
trop | -1.815 |
soc | -1.700 |
lest | -1.630 |
ftime | -1.626 |
going | -1.603 |
Token | facilitates |
Token ID | 42699 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
trop | +0.293 |
soc | +0.276 |
lest | +0.263 |
ftime | +0.262 |
othe | +0.261 |
Neg logit contributions | |
hyde | -0.250 |
zyk | -0.231 |
learnt | -0.227 |
ortmund | -0.227 |
Fail | -0.225 |
Token | GB |
Token ID | 4579 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
hyde | +0.916 |
zyk | +0.785 |
ortmund | +0.757 |
learnt | +0.753 |
Fail | +0.745 |
Neg logit contributions | |
trop | -2.804 |
soc | -2.693 |
lest | -2.603 |
ftime | -2.595 |
othe | -2.592 |
Token | GDDR |
Token ID | 50092 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
hyde | +0.586 |
zyk | +0.534 |
learnt | +0.526 |
XT | +0.521 |
ortmund | +0.520 |
Neg logit contributions | |
trop | -0.941 |
soc | -0.894 |
lest | -0.859 |
ftime | -0.858 |
othe | -0.852 |
Token | 5 |
Token ID | 20 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
hyde | +2.569 |
XT | +2.367 |
zyk | +2.341 |
learnt | +2.308 |
Fail | +2.227 |
Neg logit contributions | |
trop | -5.309 |
soc | -5.112 |
ftime | -4.930 |
othe | -4.887 |
Cros | -4.867 |
Token | - |
Token ID | 532 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
hyde | +2.660 |
XT | +2.434 |
zyk | +2.431 |
learnt | +2.409 |
Fail | +2.359 |
Neg logit contributions | |
trop | -4.076 |
soc | -3.859 |
ftime | -3.749 |
lest | -3.734 |
othe | -3.698 |
Token | 48 |
Token ID | 4764 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
trop | +3.031 |
soc | +2.890 |
Cros | +2.781 |
age | +2.751 |
lest | +2.725 |
Neg logit contributions | |
hyde | -2.318 |
zyk | -2.106 |
ortmund | -2.103 |
Fail | -2.034 |
learnt | -2.015 |
Token | 00 |
Token ID | 405 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
hyde | +3.127 |
zyk | +2.902 |
XT | +2.864 |
learnt | +2.861 |
Fail | +2.835 |
Neg logit contributions | |
trop | -3.965 |
soc | -3.719 |
ftime | -3.592 |
lest | -3.575 |
othe | -3.544 |
Token | MHz |
Token ID | 19805 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
XT | +4.022 |
hyde | +3.930 |
learnt | +3.753 |
zyk | +3.664 |
Fail | +3.614 |
Neg logit contributions | |
trop | -10.719 |
soc | -10.151 |
ftime | -10.082 |
lest | -10.023 |
othe | -9.869 |
Token | - |
Token ID | 532 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
hyde | +0.791 |
zyk | +0.721 |
learnt | +0.708 |
Fail | +0.703 |
XT | +0.701 |
Neg logit contributions | |
trop | -1.153 |
soc | -1.094 |
lest | -1.053 |
ftime | -1.049 |
othe | -1.041 |
Token | 256 |
Token ID | 17759 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
trop | +2.917 |
soc | +2.775 |
Cros | +2.681 |
age | +2.652 |
othe | +2.630 |
Neg logit contributions | |
hyde | -2.253 |
zyk | -2.037 |
ortmund | -2.032 |
Fail | -1.961 |
learnt | -1.955 |
Token | bit |
Token ID | 1643 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
hyde | +1.549 |
zyk | +1.364 |
XT | +1.341 |
Fail | +1.333 |
learnt | +1.313 |
Neg logit contributions | |
trop | -4.624 |
soc | -4.413 |
ftime | -4.283 |
lest | -4.268 |
othe | -4.246 |
Token |
|
Token ID | 198 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
hyde | +1.543 |
zyk | +1.406 |
learnt | +1.392 |
Fail | +1.383 |
XT | +1.374 |
Neg logit contributions | |
trop | -2.352 |
soc | -2.222 |
lest | -2.129 |
othe | -2.118 |
ftime | -2.116 |
Token | path |
Token ID | 3108 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
hyde | +1.366 |
zyk | +1.214 |
learnt | +1.199 |
Fail | +1.180 |
ortmund | +1.173 |
Neg logit contributions | |
trop | -2.522 |
soc | -2.393 |
lest | -2.323 |
othe | -2.290 |
ftime | -2.282 |
Token | , |
Token ID | 837 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
hyde | +0.355 |
zyk | +0.321 |
ortmund | +0.314 |
learnt | +0.314 |
Fail | +0.313 |
Neg logit contributions | |
trop | -0.587 |
soc | -0.558 |
lest | -0.535 |
othe | -0.533 |
ftime | -0.532 |
Token | 5 |
Token ID | 642 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
hyde | +1.439 |
zyk | +1.316 |
learnt | +1.299 |
Fail | +1.281 |
ortmund | +1.281 |
Neg logit contributions | |
trop | -2.228 |
soc | -2.117 |
lest | -2.029 |
ftime | -2.014 |
othe | -2.009 |
Token | ) |
Token ID | 1267 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
hyde | +1.202 |
zyk | +1.046 |
learnt | +1.003 |
ortmund | +0.993 |
Fail | +0.991 |
Neg logit contributions | |
trop | -3.370 |
soc | -3.234 |
lest | -3.134 |
ftime | -3.114 |
othe | -3.111 |
Token | = |
Token ID | 796 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
hyde | +1.502 |
zyk | +1.330 |
Fail | +1.316 |
XT | +1.305 |
learnt | +1.302 |
Neg logit contributions | |
trop | -3.239 |
soc | -3.087 |
lest | -2.976 |
othe | -2.953 |
ftime | -2.950 |
Token | '. |
Token ID | 45302 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
hyde | +0.919 |
learnt | +0.820 |
zyk | +0.818 |
ortmund | +0.801 |
Fail | +0.799 |
Neg logit contributions | |
trop | -1.641 |
soc | -1.561 |
lest | -1.504 |
othe | -1.490 |
ftime | -1.484 |
Token | cl |
Token ID | 565 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
hyde | +5.687 |
XT | +5.222 |
zyk | +5.216 |
ortmund | +4.948 |
learnt | +4.918 |
Neg logit contributions | |
trop | -8.967 |
Cros | -8.665 |
ERA | -8.625 |
Wem | -8.506 |
lest | -8.395 |
Token | jc |
Token ID | 48055 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
hyde | +5.251 |
zyk | +4.957 |
XT | +4.868 |
learnt | +4.838 |
Fail | +4.793 |
Neg logit contributions | |
trop | -5.568 |
Cros | -5.218 |
Wem | -5.207 |
ERA | -5.170 |
soc | -5.138 |
Token | ' |
Token ID | 6 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
hyde | +3.974 |
zyk | +3.708 |
XT | +3.668 |
ortmund | +3.562 |
Fail | +3.560 |
Neg logit contributions | |
trop | -5.193 |
soc | -4.867 |
Cros | -4.745 |
lest | -4.711 |
Wem | -4.688 |
Token | OR |
Token ID | 6375 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
hyde | +2.929 |
zyk | +2.708 |
Fail | +2.671 |
learnt | +2.647 |
XT | +2.645 |
Neg logit contributions | |
trop | -4.330 |
soc | -4.100 |
lest | -3.908 |
othe | -3.896 |
ftime | -3.858 |
Token | RIGHT |
Token ID | 33621 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
hyde | +1.136 |
zyk | +1.052 |
learnt | +1.040 |
Fail | +1.032 |
ortmund | +1.030 |
Neg logit contributions | |
trop | -1.326 |
soc | -1.248 |
lest | -1.190 |
othe | -1.176 |
ftime | -1.173 |
Token | of |
Token ID | 286 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
trop | +4.043 |
soc | +3.855 |
lest | +3.622 |
Cros | +3.592 |
ftime | +3.587 |
Neg logit contributions | |
hyde | -4.372 |
zyk | -4.076 |
ortmund | -3.987 |
Fail | -3.965 |
learnt | -3.926 |
Token | Catalonia |
Token ID | 33859 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
trop | +1.506 |
soc | +1.427 |
lest | +1.365 |
ftime | +1.361 |
othe | +1.356 |
Neg logit contributions | |
hyde | -1.092 |
zyk | -1.001 |
ortmund | -0.983 |
learnt | -0.980 |
Fail | -0.972 |
Token | ( |
Token ID | 357 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
trop | +2.081 |
soc | +1.955 |
lest | +1.851 |
ftime | +1.841 |
othe | +1.834 |
Neg logit contributions | |
hyde | -2.276 |
zyk | -2.118 |
ortmund | -2.089 |
learnt | -2.075 |
Fail | -2.072 |
Token | Di |
Token ID | 18683 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
trop | +0.615 |
soc | +0.581 |
lest | +0.554 |
ftime | +0.552 |
othe | +0.551 |
Neg logit contributions | |
hyde | -0.501 |
zyk | -0.462 |
ortmund | -0.454 |
learnt | -0.452 |
Fail | -0.450 |
Token | pl |
Token ID | 489 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
trop | +4.140 |
soc | +3.919 |
age | +3.764 |
othe | +3.742 |
lest | +3.711 |
Neg logit contributions | |
hyde | -4.170 |
zyk | -3.838 |
learnt | -3.774 |
ortmund | -3.771 |
Fail | -3.718 |
Token | oc |
Token ID | 420 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
hyde | +1.143 |
zyk | +1.065 |
ortmund | +1.045 |
learnt | +1.037 |
XT | +1.031 |
Neg logit contributions | |
trop | -1.112 |
soc | -1.036 |
ftime | -0.988 |
lest | -0.987 |
going | -0.977 |
Token | at |
Token ID | 265 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
trop | +5.665 |
soc | +5.507 |
lest | +5.246 |
age | +5.202 |
othe | +5.179 |
Neg logit contributions | |
hyde | -4.379 |
�� | -3.975 |
ortmund | -3.972 |
learnt | -3.931 |
zyk | -3.927 |
Token | ) |
Token ID | 8 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
hyde | +0.412 |
zyk | +0.381 |
ortmund | +0.373 |
learnt | +0.371 |
Fail | +0.370 |
Neg logit contributions | |
trop | -0.503 |
soc | -0.472 |
ftime | -0.450 |
lest | -0.449 |
othe | -0.447 |
Token | told |
Token ID | 1297 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
trop | +0.700 |
soc | +0.657 |
lest | +0.625 |
ftime | +0.623 |
othe | +0.623 |
Neg logit contributions | |
hyde | -0.645 |
zyk | -0.599 |
learnt | -0.590 |
ortmund | -0.588 |
Fail | -0.584 |
Token | The |
Token ID | 383 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
hyde | +0.977 |
zyk | +0.907 |
learnt | +0.901 |
ortmund | +0.891 |
Fail | +0.881 |
Neg logit contributions | |
trop | -1.156 |
soc | -1.078 |
ftime | -1.038 |
lest | -1.037 |
othe | -1.025 |
Token | Nat |
Token ID | 14393 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
hyde | +3.156 |
zyk | +2.986 |
learnt | +2.899 |
ortmund | +2.897 |
XT | +2.884 |
Neg logit contributions | |
trop | -4.123 |
soc | -3.866 |
ftime | -3.773 |
lest | -3.695 |
othe | -3.666 |
Token | n |
Token ID | 77 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
hyde | +5.038 |
zyk | +4.906 |
learnt | +4.501 |
Fail | +4.447 |
ortmund | +4.424 |
Neg logit contributions | |
trop | -4.749 |
soc | -4.505 |
ftime | -4.257 |
Cros | -4.217 |
ERA | -4.171 |
Token | ahan |
Token ID | 19210 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
hyde | +3.294 |
zyk | +3.173 |
learnt | +3.048 |
XT | +3.004 |
ortmund | +2.990 |
Neg logit contributions | |
trop | -3.293 |
soc | -3.135 |
ftime | -2.997 |
Wem | -2.930 |
lest | -2.917 |
Token | , |
Token ID | 11 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
trop | +2.095 |
soc | +1.969 |
lest | +1.865 |
othe | +1.857 |
ftime | +1.855 |
Neg logit contributions | |
hyde | -2.192 |
zyk | -2.036 |
ortmund | -2.017 |
learnt | -2.011 |
Fail | -1.998 |
Token | the |
Token ID | 262 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
trop | +4.181 |
soc | +4.005 |
lest | +3.784 |
Cros | +3.761 |
age | +3.754 |
Neg logit contributions | |
hyde | -3.929 |
ortmund | -3.602 |
zyk | -3.599 |
learnt | -3.577 |
XT | -3.552 |
Token | executive |
Token ID | 4640 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
trop | +0.849 |
soc | +0.795 |
ftime | +0.757 |
lest | +0.756 |
othe | +0.751 |
Neg logit contributions | |
hyde | -0.821 |
zyk | -0.766 |
learnt | -0.750 |
ortmund | -0.749 |
Fail | -0.748 |
Token | director |
Token ID | 3437 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
hyde | +0.296 |
zyk | +0.279 |
learnt | +0.273 |
ortmund | +0.269 |
Fail | +0.269 |
Neg logit contributions | |
trop | -0.316 |
soc | -0.296 |
ftime | -0.283 |
lest | -0.282 |
othe | -0.279 |
Token | of |
Token ID | 286 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
trop | +4.532 |
soc | +4.296 |
lest | +4.059 |
age | +4.030 |
othe | +4.024 |
Neg logit contributions | |
hyde | -5.141 |
zyk | -4.777 |
learnt | -4.769 |
ortmund | -4.760 |
Fail | -4.712 |
Token | the |
Token ID | 262 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
trop | +3.719 |
soc | +3.537 |
Cros | +3.329 |
lest | +3.327 |
othe | +3.309 |
Neg logit contributions | |
hyde | -3.726 |
zyk | -3.457 |
ortmund | -3.428 |
learnt | -3.394 |
Fail | -3.363 |
Token | Coalition |
Token ID | 15135 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
trop | +2.673 |
soc | +2.532 |
lest | +2.394 |
othe | +2.380 |
Cros | +2.380 |
Neg logit contributions | |
hyde | -2.757 |
zyk | -2.557 |
ortmund | -2.540 |
learnt | -2.517 |
Fail | -2.493 |
Token | for |
Token ID | 329 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
trop | +5.134 |
soc | +4.935 |
Cros | +4.680 |
lest | +4.640 |
age | +4.634 |
Neg logit contributions | |
hyde | -4.882 |
ortmund | -4.444 |
zyk | -4.434 |
XT | -4.326 |
learnt | -4.312 |
Token | the |
Token ID | 262 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
trop | +1.519 |
soc | +1.436 |
lest | +1.368 |
ftime | +1.360 |
othe | +1.359 |
Neg logit contributions | |
hyde | -1.292 |
zyk | -1.192 |
ortmund | -1.172 |
learnt | -1.168 |
Fail | -1.162 |
Token | a |
Token ID | 257 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
hyde | +0.418 |
zyk | +0.387 |
ortmund | +0.380 |
learnt | +0.379 |
Fail | +0.375 |
Neg logit contributions | |
trop | -0.497 |
soc | -0.468 |
lest | -0.447 |
ftime | -0.446 |
othe | -0.443 |
Token | year |
Token ID | 614 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
hyde | +1.045 |
zyk | +0.971 |
learnt | +0.961 |
ortmund | +0.946 |
Fail | +0.939 |
Neg logit contributions | |
trop | -1.485 |
soc | -1.407 |
lest | -1.347 |
ftime | -1.341 |
othe | -1.331 |
Token | for |
Token ID | 329 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
hyde | +0.472 |
zyk | +0.439 |
learnt | +0.432 |
ortmund | +0.430 |
XT | +0.425 |
Neg logit contributions | |
trop | -0.534 |
soc | -0.502 |
lest | -0.477 |
ftime | -0.477 |
othe | -0.474 |
Token | what |
Token ID | 644 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
trop | +2.189 |
soc | +2.067 |
going | +1.987 |
Cros | +1.981 |
age | +1.976 |
Neg logit contributions | |
hyde | -1.809 |
ortmund | -1.638 |
zyk | -1.635 |
Fail | -1.617 |
learnt | -1.594 |
Token | 's |
Token ID | 338 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
trop | +0.359 |
soc | +0.339 |
lest | +0.323 |
ftime | +0.322 |
othe | +0.321 |
Neg logit contributions | |
hyde | -0.308 |
zyk | -0.284 |
ortmund | -0.279 |
learnt | -0.278 |
Fail | -0.277 |
Token | called |
Token ID | 1444 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
hyde | +0.996 |
learnt | +0.920 |
zyk | +0.915 |
ortmund | +0.893 |
Fail | +0.887 |
Neg logit contributions | |
trop | -1.358 |
soc | -1.283 |
lest | -1.228 |
ftime | -1.226 |
othe | -1.220 |
Token | a |
Token ID | 257 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
trop | +5.928 |
soc | +5.567 |
Cros | +5.485 |
going | +5.459 |
age | +5.421 |
Neg logit contributions | |
hyde | -5.468 |
zyk | -4.923 |
ortmund | -4.877 |
Fail | -4.850 |
XT | -4.748 |
Token | " |
Token ID | 366 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
trop | +4.060 |
soc | +3.807 |
Cros | +3.677 |
age | +3.622 |
going | +3.610 |
Neg logit contributions | |
hyde | -3.914 |
zyk | -3.593 |
ortmund | -3.550 |
Fail | -3.524 |
learnt | -3.480 |
Token | d |
Token ID | 67 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
trop | +4.091 |
soc | +3.842 |
age | +3.620 |
going | +3.596 |
lest | +3.591 |
Neg logit contributions | |
hyde | -4.255 |
zyk | -3.940 |
ortmund | -3.933 |
learnt | -3.921 |
Fail | -3.829 |
Token | owntown |
Token ID | 22748 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
hyde | +0.301 |
zyk | +0.280 |
ortmund | +0.278 |
learnt | +0.274 |
Fail | +0.274 |
Neg logit contributions | |
trop | -0.282 |
soc | -0.264 |
lest | -0.250 |
ftime | -0.249 |
Cros | -0.247 |
Token | allowance |
Token ID | 24930 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
hyde | +1.013 |
zyk | +0.942 |
learnt | +0.929 |
ortmund | +0.922 |
Fail | +0.919 |
Neg logit contributions | |
trop | -1.050 |
soc | -0.981 |
lest | -0.933 |
ftime | -0.926 |
othe | -0.920 |
Token | o |
Token ID | 78 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
hyde | +1.230 |
zyk | +1.120 |
learnt | +1.096 |
Fail | +1.082 |
ortmund | +1.079 |
Neg logit contributions | |
trop | -1.308 |
soc | -1.235 |
lest | -1.173 |
Cros | -1.167 |
ftime | -1.162 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
trop | +2.375 |
soc | +2.217 |
lest | +2.106 |
othe | +2.093 |
ftime | +2.093 |
Neg logit contributions | |
hyde | -2.561 |
zyk | -2.379 |
ortmund | -2.347 |
learnt | -2.326 |
Fail | -2.322 |
Token | meant |
Token ID | 4001 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
trop | +1.045 |
soc | +0.992 |
lest | +0.949 |
ftime | +0.945 |
othe | +0.944 |
Neg logit contributions | |
hyde | -0.729 |
zyk | -0.664 |
ortmund | -0.652 |
learnt | -0.646 |
Fail | -0.645 |
Token | that |
Token ID | 326 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
trop | +0.796 |
soc | +0.751 |
lest | +0.715 |
ftime | +0.713 |
othe | +0.709 |
Neg logit contributions | |
hyde | -0.708 |
zyk | -0.656 |
ortmund | -0.645 |
learnt | -0.644 |
Fail | -0.641 |
Token | the |
Token ID | 262 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
hyde | +0.241 |
zyk | +0.223 |
learnt | +0.220 |
ortmund | +0.219 |
Fail | +0.218 |
Neg logit contributions | |
trop | -0.277 |
soc | -0.261 |
ftime | -0.248 |
lest | -0.248 |
othe | -0.247 |
Token | asteroid |
Token ID | 27460 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
hyde | +0.754 |
zyk | +0.702 |
learnt | +0.698 |
Fail | +0.692 |
ortmund | +0.688 |
Neg logit contributions | |
trop | -0.731 |
soc | -0.687 |
ftime | -0.654 |
lest | -0.649 |
othe | -0.646 |
Token | was |
Token ID | 373 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
trop | +5.431 |
soc | +5.180 |
age | +5.007 |
Cros | +4.991 |
going | +4.957 |
Neg logit contributions | |
hyde | -3.421 |
zyk | -3.082 |
Fail | -3.004 |
ortmund | -2.995 |
�� | -2.977 |
Token | not |
Token ID | 407 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
trop | +0.685 |
soc | +0.648 |
lest | +0.618 |
ftime | +0.615 |
othe | +0.614 |
Neg logit contributions | |
hyde | -0.552 |
zyk | -0.508 |
ortmund | -0.499 |
learnt | -0.496 |
Fail | -0.495 |
Token | bright |
Token ID | 6016 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
hyde | +0.137 |
zyk | +0.127 |
learnt | +0.125 |
ortmund | +0.123 |
Fail | +0.123 |
Neg logit contributions | |
trop | -0.171 |
soc | -0.162 |
lest | -0.154 |
ftime | -0.154 |
othe | -0.153 |
Token | enough |
Token ID | 1576 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
hyde | +0.373 |
zyk | +0.324 |
learnt | +0.318 |
ortmund | +0.313 |
Fail | +0.311 |
Neg logit contributions | |
trop | -0.952 |
soc | -0.916 |
othe | -0.883 |
ftime | -0.881 |
lest | -0.880 |
Token | for |
Token ID | 329 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
trop | +2.278 |
soc | +2.138 |
lest | +2.042 |
ftime | +2.020 |
othe | +2.015 |
Neg logit contributions | |
hyde | -2.189 |
zyk | -2.028 |
ortmund | -1.999 |
learnt | -1.986 |
Fail | -1.982 |
Token | . |
Token ID | 13 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
hyde | +2.205 |
zyk | +2.150 |
learnt | +2.049 |
XT | +2.048 |
Fail | +2.041 |
Neg logit contributions | |
trop | -3.482 |
soc | -3.261 |
ftime | -3.201 |
nomine | -3.159 |
lest | -3.124 |
Token | Obama |
Token ID | 2486 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
hyde | +2.573 |
zyk | +2.505 |
learnt | +2.438 |
Fail | +2.378 |
XT | +2.360 |
Neg logit contributions | |
trop | -2.957 |
soc | -2.779 |
ftime | -2.667 |
lest | -2.623 |
othe | -2.614 |
Token | said |
Token ID | 531 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
trop | +2.986 |
soc | +2.806 |
age | +2.678 |
lest | +2.678 |
othe | +2.657 |
Neg logit contributions | |
hyde | -3.224 |
ortmund | -2.994 |
Fail | -2.956 |
zyk | -2.951 |
XT | -2.915 |
Token | with |
Token ID | 351 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
trop | +0.816 |
soc | +0.770 |
lest | +0.733 |
ftime | +0.728 |
othe | +0.727 |
Neg logit contributions | |
hyde | -0.688 |
zyk | -0.636 |
learnt | -0.625 |
ortmund | -0.621 |
Fail | -0.616 |
Token | damp |
Token ID | 21151 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
trop | +2.101 |
soc | +1.999 |
going | +1.913 |
lest | +1.907 |
Cros | +1.904 |
Neg logit contributions | |
hyde | -1.722 |
zyk | -1.574 |
ortmund | -1.564 |
Fail | -1.541 |
learnt | -1.519 |
Token | eyes |
Token ID | 2951 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
trop | +7.958 |
soc | +7.591 |
othe | +7.542 |
going | +7.451 |
age | +7.370 |
Neg logit contributions | |
hyde | -7.762 |
zyk | -7.262 |
ortmund | -7.177 |
XT | -6.957 |
Fail | -6.934 |
Token |
|
Token ID | 198 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
trop | +4.260 |
soc | +4.015 |
lest | +3.843 |
ftime | +3.829 |
othe | +3.813 |
Neg logit contributions | |
hyde | -4.167 |
zyk | -3.860 |
ortmund | -3.851 |
Fail | -3.798 |
learnt | -3.734 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
hyde | +0.076 |
zyk | +0.072 |
Fail | +0.069 |
learnt | +0.069 |
ortmund | +0.068 |
Neg logit contributions | |
trop | -0.126 |
soc | -0.119 |
ftime | -0.116 |
lest | -0.114 |
othe | -0.114 |
Token | Mrs |
Token ID | 27034 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
trop | +0.138 |
soc | +0.130 |
lest | +0.123 |
ftime | +0.123 |
othe | +0.123 |
Neg logit contributions | |
hyde | -0.131 |
zyk | -0.122 |
ortmund | -0.120 |
learnt | -0.119 |
Fail | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
hyde | +1.312 |
zyk | +1.252 |
learnt | +1.210 |
Fail | +1.201 |
XT | +1.199 |
Neg logit contributions | |
trop | -1.837 |
soc | -1.726 |
ftime | -1.670 |
lest | -1.647 |
othe | -1.643 |
Token | Obama |
Token ID | 2486 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
hyde | +2.385 |
zyk | +2.329 |
learnt | +2.245 |
ortmund | +2.213 |
Fail | +2.183 |
Neg logit contributions | |
trop | -2.626 |
soc | -2.472 |
lest | -2.342 |
ftime | -2.341 |
othe | -2.326 |
Token | icle |
Token ID | 1548 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
trop | +2.184 |
soc | +1.995 |
lest | +1.866 |
age | +1.834 |
ftime | +1.818 |
Neg logit contributions | |
hyde | -4.369 |
zyk | -4.136 |
ortmund | -4.111 |
learnt | -4.109 |
Fail | -4.044 |
Token | > |
Token ID | 1875 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
trop | +3.670 |
soc | +3.493 |
lest | +3.352 |
age | +3.321 |
ftime | +3.299 |
Neg logit contributions | |
hyde | -2.889 |
zyk | -2.631 |
ortmund | -2.600 |
learnt | -2.551 |
Fail | -2.499 |
Token | & |
Token ID | 1222 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
hyde | +0.290 |
zyk | +0.270 |
learnt | +0.267 |
ortmund | +0.267 |
Fail | +0.265 |
Neg logit contributions | |
trop | -0.266 |
soc | -0.249 |
lest | -0.235 |
othe | -0.235 |
ftime | -0.234 |
Token | particles |
Token ID | 13166 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
hyde | +1.369 |
zyk | +1.259 |
learnt | +1.246 |
ortmund | +1.234 |
Fail | +1.229 |
Neg logit contributions | |
trop | -1.755 |
soc | -1.658 |
othe | -1.590 |
lest | -1.586 |
ftime | -1.577 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
hyde | +0.430 |
zyk | +0.383 |
Fail | +0.372 |
learnt | +0.372 |
ortmund | +0.372 |
Neg logit contributions | |
trop | -0.968 |
soc | -0.926 |
lest | -0.891 |
othe | -0.889 |
ftime | -0.888 |
Token | { |
Token ID | 1391 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
hyde | +1.521 |
zyk | +1.397 |
learnt | +1.384 |
Fail | +1.379 |
ortmund | +1.371 |
Neg logit contributions | |
trop | -2.038 |
soc | -1.927 |
ftime | -1.853 |
lest | -1.837 |
othe | -1.836 |
Token | density |
Token ID | 12109 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
trop | +0.243 |
soc | +0.230 |
lest | +0.220 |
ftime | +0.219 |
othe | +0.219 |
Neg logit contributions | |
hyde | -0.168 |
zyk | -0.153 |
ortmund | -0.150 |
learnt | -0.149 |
Fail | -0.149 |
Token | Grid |
Token ID | 41339 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
hyde | +0.660 |
zyk | +0.581 |
Fail | +0.579 |
learnt | +0.572 |
ortmund | +0.572 |
Neg logit contributions | |
trop | -1.492 |
soc | -1.424 |
othe | -1.380 |
ftime | -1.378 |
lest | -1.373 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
trop | +1.189 |
soc | +1.127 |
lest | +1.075 |
ftime | +1.068 |
othe | +1.065 |
Neg logit contributions | |
hyde | -0.953 |
zyk | -0.880 |
ortmund | -0.864 |
learnt | -0.856 |
Fail | -0.850 |
Token | Clear |
Token ID | 19856 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
trop | +0.596 |
soc | +0.563 |
lest | +0.536 |
ftime | +0.533 |
othe | +0.532 |
Neg logit contributions | |
hyde | -0.510 |
zyk | -0.471 |
ortmund | -0.463 |
learnt | -0.461 |
Fail | -0.458 |
Token | () |
Token ID | 3419 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
trop | +0.546 |
soc | +0.517 |
lest | +0.494 |
ftime | +0.490 |
othe | +0.489 |
Neg logit contributions | |
hyde | -0.441 |
zyk | -0.407 |
ortmund | -0.400 |
learnt | -0.398 |
Fail | -0.393 |
Token | just |
Token ID | 655 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
trop | +2.277 |
soc | +2.157 |
othe | +2.090 |
lest | +2.079 |
age | +2.069 |
Neg logit contributions | |
hyde | -1.702 |
ortmund | -1.555 |
zyk | -1.541 |
XT | -1.509 |
Fail | -1.507 |
Token | chew |
Token ID | 34722 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
trop | +0.214 |
soc | +0.203 |
lest | +0.194 |
othe | +0.193 |
ftime | +0.192 |
Neg logit contributions | |
hyde | -0.157 |
zyk | -0.143 |
ortmund | -0.141 |
Fail | -0.139 |
learnt | -0.139 |
Token | them |
Token ID | 606 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
hyde | +2.343 |
zyk | +2.174 |
learnt | +2.134 |
ortmund | +2.109 |
Fail | +2.106 |
Neg logit contributions | |
trop | -2.597 |
soc | -2.448 |
ftime | -2.382 |
lest | -2.328 |
othe | -2.305 |
Token | up |
Token ID | 510 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
trop | +0.168 |
soc | +0.158 |
lest | +0.150 |
ftime | +0.149 |
othe | +0.149 |
Neg logit contributions | |
hyde | -0.169 |
zyk | -0.157 |
ortmund | -0.155 |
learnt | -0.154 |
Fail | -0.153 |
Token | and |
Token ID | 290 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
hyde | +1.186 |
zyk | +1.103 |
learnt | +1.087 |
ortmund | +1.078 |
Fail | +1.073 |
Neg logit contributions | |
trop | -1.139 |
soc | -1.071 |
ftime | -1.016 |
lest | -1.012 |
othe | -1.007 |
Token | wash |
Token ID | 13502 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
hyde | +1.089 |
zyk | +1.005 |
learnt | +0.987 |
ortmund | +0.982 |
Fail | +0.980 |
Neg logit contributions | |
trop | -1.331 |
soc | -1.258 |
lest | -1.200 |
ftime | -1.198 |
othe | -1.189 |
Token | them |
Token ID | 606 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
hyde | +0.583 |
zyk | +0.539 |
ortmund | +0.530 |
learnt | +0.530 |
Fail | +0.527 |
Neg logit contributions | |
trop | -0.610 |
soc | -0.573 |
ftime | -0.546 |
lest | -0.545 |
othe | -0.541 |
Token | down |
Token ID | 866 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
trop | +1.570 |
soc | +1.479 |
othe | +1.397 |
lest | +1.396 |
age | +1.390 |
Neg logit contributions | |
hyde | -1.542 |
zyk | -1.431 |
ortmund | -1.416 |
Fail | -1.404 |
learnt | -1.398 |
Token | with |
Token ID | 351 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
hyde | +1.969 |
zyk | +1.787 |
learnt | +1.761 |
ortmund | +1.737 |
Fail | +1.728 |
Neg logit contributions | |
trop | -2.734 |
soc | -2.595 |
ftime | -2.476 |
lest | -2.475 |
othe | -2.459 |
Token | orange |
Token ID | 10912 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
trop | +1.360 |
soc | +1.291 |
lest | +1.233 |
othe | +1.226 |
ftime | +1.225 |
Neg logit contributions | |
hyde | -1.019 |
zyk | -0.936 |
ortmund | -0.921 |
learnt | -0.914 |
Fail | -0.911 |
Token | juice |
Token ID | 13135 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
hyde | +1.131 |
zyk | +1.028 |
learnt | +1.011 |
Fail | +0.998 |
XT | +0.993 |
Neg logit contributions | |
trop | -1.812 |
soc | -1.725 |
ftime | -1.675 |
lest | -1.660 |
othe | -1.646 |
Token | UCT |
Token ID | 18415 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
hyde | +2.279 |
zyk | +2.197 |
Fail | +2.187 |
XT | +2.177 |
learnt | +2.119 |
Neg logit contributions | |
trop | -2.896 |
soc | -2.660 |
lest | -2.593 |
going | -2.540 |
ftime | -2.535 |
Token | URE |
Token ID | 11335 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
trop | +2.773 |
soc | +2.639 |
ERA | +2.511 |
Cros | +2.501 |
age | +2.490 |
Neg logit contributions | |
hyde | -3.055 |
ortmund | -2.783 |
zyk | -2.780 |
learnt | -2.691 |
Fail | -2.682 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
trop | +3.510 |
soc | +3.358 |
Cros | +3.259 |
ERA | +3.211 |
age | +3.194 |
Neg logit contributions | |
hyde | -3.133 |
zyk | -2.855 |
ortmund | -2.845 |
learnt | -2.740 |
Fail | -2.739 |
Token |
|
Token ID | 198 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
trop | +1.610 |
soc | +1.530 |
lest | +1.462 |
othe | +1.452 |
ftime | +1.449 |
Neg logit contributions | |
hyde | -1.171 |
zyk | -1.065 |
ortmund | -1.050 |
learnt | -1.043 |
Fail | -1.035 |
Token | Please |
Token ID | 5492 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
trop | +2.546 |
soc | +2.438 |
age | +2.297 |
lest | +2.292 |
going | +2.290 |
Neg logit contributions | |
hyde | -2.157 |
zyk | -1.967 |
learnt | -1.944 |
ortmund | -1.941 |
�� | -1.882 |
Token | find |
Token ID | 1064 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
trop | +5.017 |
soc | +4.837 |
othe | +4.623 |
age | +4.604 |
Cros | +4.539 |
Neg logit contributions | |
hyde | -5.208 |
ortmund | -4.712 |
Fail | -4.613 |
zyk | -4.608 |
XT | -4.575 |
Token | a |
Token ID | 257 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
trop | +2.052 |
soc | +1.955 |
lest | +1.847 |
othe | +1.840 |
ftime | +1.828 |
Neg logit contributions | |
hyde | -1.866 |
zyk | -1.721 |
Fail | -1.691 |
ortmund | -1.688 |
learnt | -1.676 |
Token | full |
Token ID | 1336 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
trop | +2.722 |
soc | +2.631 |
lest | +2.491 |
age | +2.485 |
othe | +2.481 |
Neg logit contributions | |
hyde | -1.850 |
zyk | -1.666 |
Fail | -1.644 |
ortmund | -1.636 |
XT | -1.613 |
Token | list |
Token ID | 1351 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
hyde | +0.229 |
zyk | +0.205 |
ortmund | +0.200 |
learnt | +0.199 |
Fail | +0.196 |
Neg logit contributions | |
trop | -0.542 |
soc | -0.516 |
lest | -0.501 |
ftime | -0.499 |
othe | -0.496 |
Token | of |
Token ID | 286 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
trop | +2.528 |
soc | +2.382 |
lest | +2.255 |
othe | +2.247 |
ftime | +2.235 |
Neg logit contributions | |
hyde | -2.788 |
zyk | -2.601 |
Fail | -2.553 |
ortmund | -2.543 |
learnt | -2.539 |
Token | supporter |
Token ID | 15525 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
trop | +1.576 |
soc | +1.487 |
lest | +1.399 |
othe | +1.395 |
ftime | +1.392 |
Neg logit contributions | |
hyde | -1.682 |
zyk | -1.561 |
ortmund | -1.537 |
Fail | -1.528 |
learnt | -1.524 |
Token | her |
Token ID | 607 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
trop | +0.073 |
soc | +0.068 |
lest | +0.065 |
ftime | +0.065 |
othe | +0.065 |
Neg logit contributions | |
hyde | -0.060 |
zyk | -0.055 |
learnt | -0.054 |
ortmund | -0.054 |
Fail | -0.054 |
Token | little |
Token ID | 1310 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
trop | +0.734 |
soc | +0.688 |
lest | +0.652 |
ftime | +0.649 |
othe | +0.647 |
Neg logit contributions | |
hyde | -0.781 |
zyk | -0.728 |
ortmund | -0.717 |
learnt | -0.716 |
Fail | -0.712 |
Token | fist |
Token ID | 18606 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
hyde | +0.275 |
zyk | +0.255 |
learnt | +0.252 |
Fail | +0.251 |
ortmund | +0.250 |
Neg logit contributions | |
trop | -0.299 |
soc | -0.282 |
ftime | -0.267 |
lest | -0.267 |
othe | -0.265 |
Token | while |
Token ID | 981 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
trop | +1.498 |
soc | +1.414 |
lest | +1.340 |
ftime | +1.336 |
othe | +1.331 |
Neg logit contributions | |
hyde | -1.407 |
zyk | -1.304 |
ortmund | -1.279 |
learnt | -1.277 |
Fail | -1.271 |
Token | an |
Token ID | 281 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
hyde | +0.303 |
zyk | +0.283 |
learnt | +0.279 |
ortmund | +0.277 |
Fail | +0.277 |
Neg logit contributions | |
trop | -0.279 |
soc | -0.261 |
lest | -0.246 |
ftime | -0.245 |
othe | -0.243 |
Token | ambulance |
Token ID | 22536 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
trop | +0.691 |
soc | +0.653 |
lest | +0.621 |
othe | +0.619 |
ftime | +0.618 |
Neg logit contributions | |
hyde | -0.616 |
zyk | -0.570 |
ortmund | -0.561 |
learnt | -0.558 |
Fail | -0.556 |
Token | s |
Token ID | 264 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
trop | +0.599 |
soc | +0.567 |
lest | +0.539 |
ftime | +0.537 |
othe | +0.535 |
Neg logit contributions | |
hyde | -0.488 |
zyk | -0.450 |
learnt | -0.444 |
ortmund | -0.438 |
Fail | -0.436 |
Token | iren |
Token ID | 24080 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
hyde | +0.392 |
zyk | +0.369 |
ortmund | +0.361 |
learnt | +0.359 |
Fail | +0.358 |
Neg logit contributions | |
trop | -0.319 |
soc | -0.298 |
lest | -0.281 |
ftime | -0.279 |
othe | -0.277 |
Token | w |
Token ID | 266 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
trop | +2.948 |
soc | +2.782 |
lest | +2.658 |
othe | +2.648 |
ftime | +2.646 |
Neg logit contributions | |
hyde | -2.615 |
zyk | -2.411 |
ortmund | -2.388 |
Fail | -2.365 |
learnt | -2.332 |
Token | ailed |
Token ID | 6255 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
hyde | +0.037 |
zyk | +0.034 |
ortmund | +0.033 |
learnt | +0.033 |
Fail | +0.032 |
Neg logit contributions | |
trop | -0.057 |
soc | -0.054 |
lest | -0.052 |
ftime | -0.052 |
othe | -0.052 |
Token | outside |
Token ID | 2354 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
trop | +2.939 |
soc | +2.773 |
lest | +2.644 |
ftime | +2.630 |
othe | +2.630 |
Neg logit contributions | |
hyde | -2.733 |
zyk | -2.532 |
ortmund | -2.506 |
Fail | -2.482 |
learnt | -2.472 |
Token | boot |
Token ID | 6297 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
trop | +0.205 |
soc | +0.193 |
lest | +0.184 |
ftime | +0.183 |
othe | +0.182 |
Neg logit contributions | |
hyde | -0.196 |
zyk | -0.182 |
ortmund | -0.179 |
learnt | -0.179 |
Fail | -0.178 |
Token | loop |
Token ID | 26268 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
trop | +0.289 |
soc | +0.263 |
lest | +0.242 |
ftime | +0.241 |
othe | +0.240 |
Neg logit contributions | |
hyde | -0.569 |
zyk | -0.539 |
ortmund | -0.532 |
learnt | -0.531 |
Fail | -0.530 |
Token | is |
Token ID | 318 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
hyde | +0.700 |
zyk | +0.643 |
learnt | +0.636 |
Fail | +0.630 |
ortmund | +0.625 |
Neg logit contributions | |
trop | -0.955 |
soc | -0.907 |
lest | -0.871 |
ftime | -0.866 |
othe | -0.862 |
Token | a |
Token ID | 257 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
hyde | +1.438 |
learnt | +1.337 |
zyk | +1.331 |
ortmund | +1.299 |
Fail | +1.298 |
Neg logit contributions | |
trop | -2.021 |
soc | -1.907 |
ftime | -1.833 |
lest | -1.833 |
othe | -1.812 |
Token | combination |
Token ID | 6087 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
hyde | +0.547 |
zyk | +0.502 |
learnt | +0.493 |
ortmund | +0.491 |
Fail | +0.488 |
Neg logit contributions | |
trop | -0.772 |
soc | -0.731 |
lest | -0.702 |
ftime | -0.698 |
othe | -0.694 |
Token | of |
Token ID | 286 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
hyde | +1.217 |
zyk | +1.134 |
learnt | +1.123 |
ortmund | +1.121 |
Fail | +1.114 |
Neg logit contributions | |
trop | -1.331 |
soc | -1.250 |
lest | -1.193 |
ftime | -1.186 |
othe | -1.175 |
Token | some |
Token ID | 617 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
trop | +0.732 |
soc | +0.694 |
lest | +0.659 |
ftime | +0.657 |
othe | +0.656 |
Neg logit contributions | |
hyde | -0.609 |
zyk | -0.559 |
ortmund | -0.551 |
learnt | -0.546 |
Fail | -0.544 |
Token | factors |
Token ID | 5087 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
trop | +1.604 |
soc | +1.520 |
lest | +1.440 |
othe | +1.440 |
ftime | +1.437 |
Neg logit contributions | |
hyde | -1.356 |
zyk | -1.244 |
ortmund | -1.221 |
Fail | -1.209 |
learnt | -1.206 |
Token | : |
Token ID | 25 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
trop | +3.427 |
soc | +3.239 |
age | +3.075 |
lest | +3.055 |
going | +3.051 |
Neg logit contributions | |
hyde | -3.765 |
zyk | -3.466 |
ortmund | -3.418 |
Fail | -3.379 |
�� | -3.341 |
Token |
|
Token ID | 198 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
trop | +1.382 |
soc | +1.317 |
lest | +1.253 |
othe | +1.246 |
ftime | +1.245 |
Neg logit contributions | |
hyde | -1.048 |
zyk | -0.960 |
ortmund | -0.944 |
learnt | -0.930 |
Fail | -0.927 |
Token |
|
Token ID | 198 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
hyde | +2.024 |
zyk | +1.986 |
Fail | +1.927 |
XT | +1.884 |
learnt | +1.873 |
Neg logit contributions | |
trop | -4.499 |
nomine | -4.391 |
ftime | -4.266 |
soc | -4.239 |
Wem | -4.161 |
Token | for |
Token ID | 329 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
hyde | +0.175 |
zyk | +0.162 |
learnt | +0.159 |
ortmund | +0.159 |
Fail | +0.157 |
Neg logit contributions | |
trop | -0.206 |
soc | -0.194 |
lest | -0.185 |
ftime | -0.184 |
othe | -0.184 |
Token | putting |
Token ID | 5137 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
trop | +1.094 |
soc | +1.031 |
lest | +0.977 |
ftime | +0.969 |
othe | +0.968 |
Neg logit contributions | |
hyde | -1.070 |
zyk | -0.990 |
ortmund | -0.977 |
learnt | -0.971 |
Fail | -0.967 |
Token | American |
Token ID | 1605 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
hyde | +0.303 |
zyk | +0.282 |
learnt | +0.278 |
ortmund | +0.277 |
Fail | +0.275 |
Neg logit contributions | |
trop | -0.327 |
soc | -0.307 |
lest | -0.293 |
ftime | -0.292 |
othe | -0.292 |
Token | lives |
Token ID | 3160 |
Feature activation | -1.70e-04 |
Pos logit contributions | |
hyde | +0.760 |
zyk | +0.688 |
learnt | +0.680 |
Fail | +0.670 |
XT | +0.664 |
Neg logit contributions | |
trop | -1.338 |
soc | -1.264 |
lest | -1.218 |
ftime | -1.217 |
othe | -1.211 |
Token | at |
Token ID | 379 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
hyde | +0.001 |
zyk | +0.001 |
learnt | +0.001 |
ortmund | +0.001 |
XT | +0.001 |
Neg logit contributions | |
trop | -0.001 |
soc | -0.001 |
ftime | -0.001 |
othe | -0.001 |
lest | -0.001 |
Token | risk |
Token ID | 2526 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
hyde | +1.506 |
zyk | +1.381 |
ortmund | +1.347 |
Fail | +1.342 |
learnt | +1.330 |
Neg logit contributions | |
trop | -3.385 |
soc | -3.188 |
ftime | -3.114 |
othe | -3.075 |
lest | -3.049 |
Token | . |
Token ID | 13 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
hyde | +3.078 |
zyk | +2.915 |
learnt | +2.877 |
ortmund | +2.772 |
Fail | +2.733 |
Neg logit contributions | |
trop | -4.256 |
soc | -3.994 |
Cros | -3.813 |
othe | -3.800 |
lest | -3.798 |
Token |
|
Token ID | 198 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
hyde | +0.372 |
zyk | +0.343 |
ortmund | +0.335 |
Fail | +0.334 |
learnt | +0.334 |
Neg logit contributions | |
trop | -0.529 |
soc | -0.501 |
ftime | -0.479 |
lest | -0.479 |
othe | -0.478 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
trop | +1.496 |
soc | +1.421 |
lest | +1.359 |
ftime | +1.352 |
othe | +1.351 |
Neg logit contributions | |
hyde | -1.050 |
zyk | -0.959 |
ortmund | -0.941 |
learnt | -0.938 |
Fail | -0.932 |
Token | While |
Token ID | 3633 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
trop | +0.629 |
soc | +0.598 |
lest | +0.571 |
ftime | +0.562 |
othe | +0.562 |
Neg logit contributions | |
hyde | -0.510 |
zyk | -0.465 |
learnt | -0.459 |
ortmund | -0.459 |
Fail | -0.447 |
Token | the |
Token ID | 262 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
hyde | +0.573 |
zyk | +0.535 |
learnt | +0.526 |
ortmund | +0.524 |
Fail | +0.520 |
Neg logit contributions | |
trop | -0.652 |
soc | -0.611 |
lest | -0.584 |
ftime | -0.583 |
othe | -0.582 |
Token | 2006 |
Token ID | 4793 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
hyde | +1.110 |
zyk | +1.036 |
learnt | +1.019 |
ortmund | +1.013 |
Fail | +1.008 |
Neg logit contributions | |
trop | -1.544 |
soc | -1.459 |
ftime | -1.403 |
lest | -1.403 |
othe | -1.394 |
Token | . |
Token ID | 13 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
trop | +2.778 |
soc | +2.608 |
lest | +2.476 |
Cros | +2.455 |
going | +2.452 |
Neg logit contributions | |
hyde | -2.908 |
zyk | -2.684 |
ortmund | -2.652 |
Fail | -2.638 |
learnt | -2.616 |
Token | This |
Token ID | 770 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
hyde | +0.351 |
zyk | +0.324 |
ortmund | +0.316 |
learnt | +0.315 |
Fail | +0.314 |
Neg logit contributions | |
trop | -0.502 |
soc | -0.477 |
ftime | -0.456 |
lest | -0.456 |
othe | -0.453 |
Token | Finnish |
Token ID | 26838 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
hyde | +0.475 |
zyk | +0.436 |
ortmund | +0.428 |
learnt | +0.428 |
Fail | +0.424 |
Neg logit contributions | |
trop | -0.639 |
soc | -0.606 |
lest | -0.580 |
ftime | -0.577 |
othe | -0.576 |
Token | album |
Token ID | 5062 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
hyde | +3.666 |
zyk | +3.435 |
learnt | +3.432 |
XT | +3.368 |
Fail | +3.336 |
Neg logit contributions | |
trop | -4.713 |
soc | -4.468 |
lest | -4.322 |
ftime | -4.279 |
acements | -4.206 |
Token | contains |
Token ID | 4909 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
trop | +3.500 |
soc | +3.334 |
age | +3.221 |
Cros | +3.202 |
othe | +3.200 |
Neg logit contributions | |
hyde | -2.503 |
zyk | -2.258 |
ortmund | -2.218 |
Fail | -2.216 |
XT | -2.182 |
Token | no |
Token ID | 645 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
hyde | +1.942 |
zyk | +1.803 |
learnt | +1.797 |
ortmund | +1.769 |
Fail | +1.750 |
Neg logit contributions | |
trop | -2.565 |
soc | -2.439 |
lest | -2.330 |
ftime | -2.326 |
othe | -2.307 |
Token | original |
Token ID | 2656 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
hyde | +0.870 |
zyk | +0.797 |
ortmund | +0.784 |
learnt | +0.784 |
Fail | +0.776 |
Neg logit contributions | |
trop | -1.222 |
soc | -1.162 |
lest | -1.111 |
ftime | -1.106 |
othe | -1.102 |
Token | lyrics |
Token ID | 15844 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
hyde | +2.668 |
learnt | +2.445 |
zyk | +2.445 |
ortmund | +2.409 |
XT | +2.371 |
Neg logit contributions | |
trop | -4.117 |
soc | -3.937 |
ftime | -3.775 |
lest | -3.773 |
othe | -3.736 |
Token | by |
Token ID | 416 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
hyde | +1.919 |
learnt | +1.798 |
zyk | +1.792 |
ortmund | +1.752 |
XT | +1.734 |
Neg logit contributions | |
trop | -1.983 |
soc | -1.883 |
ftime | -1.778 |
othe | -1.776 |
lest | -1.775 |
Token | J |
Token ID | 449 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
hyde | +0.354 |
zyk | +0.327 |
ortmund | +0.322 |
learnt | +0.322 |
Fail | +0.316 |
Neg logit contributions | |
trop | -0.491 |
soc | -0.465 |
lest | -0.448 |
ftime | -0.445 |
othe | -0.444 |
Token | that |
Token ID | 326 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
trop | +1.743 |
soc | +1.648 |
lest | +1.569 |
ftime | +1.562 |
othe | +1.560 |
Neg logit contributions | |
hyde | -1.470 |
zyk | -1.356 |
ortmund | -1.333 |
learnt | -1.327 |
Fail | -1.322 |
Token | Republican |
Token ID | 3415 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
trop | +0.563 |
soc | +0.533 |
lest | +0.511 |
othe | +0.506 |
ftime | +0.506 |
Neg logit contributions | |
hyde | -0.416 |
zyk | -0.380 |
learnt | -0.374 |
ortmund | -0.373 |
Fail | -0.371 |
Token | Rep |
Token ID | 1432 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
trop | +1.694 |
soc | +1.582 |
lest | +1.481 |
ftime | +1.474 |
othe | +1.469 |
Neg logit contributions | |
hyde | -2.264 |
zyk | -2.122 |
ortmund | -2.099 |
learnt | -2.085 |
Fail | -2.077 |
Token | . |
Token ID | 13 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
hyde | +1.277 |
zyk | +1.214 |
XT | +1.175 |
Fail | +1.175 |
learnt | +1.157 |
Neg logit contributions | |
trop | -1.806 |
soc | -1.694 |
ftime | -1.652 |
othe | -1.627 |
lest | -1.624 |
Token | Ryan |
Token ID | 6047 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
trop | +1.628 |
soc | +1.519 |
lest | +1.437 |
Cros | +1.434 |
othe | +1.422 |
Neg logit contributions | |
hyde | -1.972 |
zyk | -1.835 |
ortmund | -1.828 |
learnt | -1.804 |
Fail | -1.799 |
Token | Zin |
Token ID | 36971 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
trop | +0.579 |
soc | +0.539 |
lest | +0.507 |
ftime | +0.505 |
Cros | +0.504 |
Neg logit contributions | |
hyde | -0.780 |
zyk | -0.730 |
ortmund | -0.723 |
learnt | -0.717 |
Fail | -0.715 |
Token | ke |
Token ID | 365 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
hyde | +1.753 |
zyk | +1.649 |
learnt | +1.596 |
XT | +1.582 |
Fail | +1.576 |
Neg logit contributions | |
trop | -1.931 |
soc | -1.807 |
ftime | -1.712 |
Cros | -1.698 |
othe | -1.698 |
Token | won |
Token ID | 1839 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
trop | +0.241 |
soc | +0.228 |
lest | +0.217 |
ftime | +0.215 |
othe | +0.215 |
Neg logit contributions | |
hyde | -0.207 |
zyk | -0.193 |
learnt | -0.189 |
ortmund | -0.188 |
Fail | -0.187 |
Token | by |
Token ID | 416 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
hyde | +0.521 |
zyk | +0.485 |
ortmund | +0.473 |
learnt | +0.471 |
Fail | +0.470 |
Neg logit contributions | |
trop | -0.650 |
soc | -0.616 |
ftime | -0.587 |
lest | -0.586 |
othe | -0.581 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
hyde | +0.333 |
zyk | +0.306 |
ortmund | +0.300 |
learnt | +0.300 |
Fail | +0.298 |
Neg logit contributions | |
trop | -0.440 |
soc | -0.417 |
lest | -0.398 |
ftime | -0.396 |
othe | -0.396 |
Token | points |
Token ID | 2173 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
trop | +0.081 |
soc | +0.076 |
lest | +0.072 |
ftime | +0.072 |
othe | +0.071 |
Neg logit contributions | |
hyde | -0.083 |
zyk | -0.077 |
learnt | -0.076 |
ortmund | -0.076 |
Fail | -0.076 |
Token | The |
Token ID | 383 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
trop | +0.577 |
soc | +0.547 |
lest | +0.521 |
othe | +0.518 |
ftime | +0.517 |
Neg logit contributions | |
hyde | -0.497 |
zyk | -0.459 |
ortmund | -0.451 |
learnt | -0.447 |
Fail | -0.446 |
Token | fear |
Token ID | 3252 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
hyde | +2.031 |
zyk | +1.868 |
learnt | +1.851 |
Fail | +1.834 |
ortmund | +1.831 |
Neg logit contributions | |
trop | -2.370 |
soc | -2.220 |
ftime | -2.130 |
lest | -2.117 |
othe | -2.081 |
Token | of |
Token ID | 286 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
hyde | +1.249 |
learnt | +1.141 |
zyk | +1.141 |
ortmund | +1.119 |
Fail | +1.110 |
Neg logit contributions | |
trop | -1.603 |
soc | -1.517 |
ftime | -1.444 |
lest | -1.444 |
othe | -1.434 |
Token | the |
Token ID | 262 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
hyde | +2.135 |
zyk | +1.966 |
learnt | +1.960 |
Fail | +1.908 |
ortmund | +1.904 |
Neg logit contributions | |
trop | -2.901 |
soc | -2.709 |
ftime | -2.627 |
lest | -2.600 |
othe | -2.583 |
Token | unknown |
Token ID | 6439 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
hyde | +0.656 |
zyk | +0.603 |
learnt | +0.597 |
ortmund | +0.592 |
Fail | +0.590 |
Neg logit contributions | |
trop | -0.783 |
soc | -0.736 |
lest | -0.705 |
ftime | -0.703 |
othe | -0.696 |
Token | . |
Token ID | 13 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
hyde | +0.674 |
zyk | +0.615 |
learnt | +0.610 |
ortmund | +0.601 |
Fail | +0.596 |
Neg logit contributions | |
trop | -0.955 |
soc | -0.906 |
lest | -0.866 |
ftime | -0.865 |
othe | -0.861 |
Token |
|
Token ID | 198 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
hyde | +1.285 |
zyk | +1.185 |
Fail | +1.158 |
learnt | +1.156 |
ortmund | +1.148 |
Neg logit contributions | |
trop | -1.880 |
soc | -1.774 |
ftime | -1.703 |
lest | -1.686 |
othe | -1.683 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
trop | +0.192 |
soc | +0.182 |
ftime | +0.176 |
lest | +0.175 |
othe | +0.174 |
Neg logit contributions | |
hyde | -0.124 |
zyk | -0.114 |
Fail | -0.111 |
learnt | -0.111 |
ortmund | -0.111 |
Token | What |
Token ID | 2061 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
hyde | +0.514 |
zyk | +0.474 |
ortmund | +0.466 |
learnt | +0.464 |
Fail | +0.463 |
Neg logit contributions | |
trop | -0.631 |
soc | -0.597 |
lest | -0.569 |
ftime | -0.567 |
othe | -0.565 |
Token | Eid |
Token ID | 31022 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
hyde | +0.702 |
zyk | +0.643 |
learnt | +0.631 |
ortmund | +0.631 |
Fail | +0.625 |
Neg logit contributions | |
trop | -0.980 |
soc | -0.929 |
lest | -0.888 |
ftime | -0.884 |
othe | -0.882 |
Token | olon |
Token ID | 43645 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
hyde | +1.270 |
zyk | +1.192 |
learnt | +1.176 |
ortmund | +1.166 |
Fail | +1.152 |
Neg logit contributions | |
trop | -1.058 |
soc | -0.991 |
ftime | -0.928 |
lest | -0.920 |
Cros | -0.920 |
Token | questions |
Token ID | 2683 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
hyde | +1.057 |
zyk | +0.979 |
learnt | +0.964 |
ortmund | +0.961 |
Fail | +0.955 |
Neg logit contributions | |
trop | -1.258 |
soc | -1.181 |
lest | -1.128 |
ftime | -1.126 |
othe | -1.120 |
Token | : |
Token ID | 25 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
trop | +0.670 |
soc | +0.634 |
lest | +0.604 |
ftime | +0.601 |
othe | +0.600 |
Neg logit contributions | |
hyde | -0.569 |
zyk | -0.525 |
ortmund | -0.516 |
learnt | -0.514 |
Fail | -0.512 |
Token | � |
Token ID | 564 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
trop | +1.989 |
soc | +1.883 |
lest | +1.772 |
Cros | +1.770 |
othe | +1.765 |
Neg logit contributions | |
hyde | -1.953 |
zyk | -1.809 |
ortmund | -1.784 |
Fail | -1.765 |
learnt | -1.756 |
Token | � |
Token ID | 250 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
hyde | +0.888 |
zyk | +0.800 |
learnt | +0.790 |
Fail | +0.784 |
XT | +0.778 |
Neg logit contributions | |
trop | -1.424 |
soc | -1.346 |
ftime | -1.289 |
lest | -1.286 |
othe | -1.271 |
Token | Do |
Token ID | 5211 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
trop | +0.396 |
soc | +0.374 |
lest | +0.356 |
ftime | +0.354 |
othe | +0.354 |
Neg logit contributions | |
hyde | -0.344 |
zyk | -0.318 |
ortmund | -0.313 |
learnt | -0.312 |
Fail | -0.310 |
Token | you |
Token ID | 345 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
hyde | +0.156 |
zyk | +0.142 |
learnt | +0.139 |
ortmund | +0.138 |
Fail | +0.138 |
Neg logit contributions | |
trop | -0.262 |
soc | -0.248 |
lest | -0.238 |
ftime | -0.238 |
othe | -0.237 |
Token | want |
Token ID | 765 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
hyde | +2.916 |
learnt | +2.788 |
zyk | +2.747 |
Fail | +2.645 |
XT | +2.620 |
Neg logit contributions | |
trop | -4.345 |
soc | -3.992 |
lest | -3.883 |
ftime | -3.871 |
ERA | -3.791 |
Token | Catalonia |
Token ID | 33859 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
hyde | +1.720 |
learnt | +1.607 |
zyk | +1.604 |
ortmund | +1.580 |
XT | +1.567 |
Neg logit contributions | |
trop | -2.072 |
soc | -1.936 |
ftime | -1.886 |
lest | -1.873 |
othe | -1.844 |
Token | to |
Token ID | 284 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
hyde | +1.854 |
zyk | +1.739 |
learnt | +1.729 |
ortmund | +1.672 |
Fail | +1.672 |
Neg logit contributions | |
trop | -2.223 |
soc | -2.081 |
ftime | -1.993 |
othe | -1.977 |
lest | -1.974 |
Token | become |
Token ID | 1716 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
hyde | +0.400 |
zyk | +0.370 |
learnt | +0.364 |
ortmund | +0.362 |
Fail | +0.361 |
Neg logit contributions | |
trop | -0.458 |
soc | -0.431 |
lest | -0.410 |
ftime | -0.410 |
othe | -0.407 |
Token | a |
Token ID | 257 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
hyde | +2.051 |
zyk | +1.858 |
learnt | +1.856 |
XT | +1.813 |
ortmund | +1.783 |
Neg logit contributions | |
trop | -3.537 |
soc | -3.357 |
ftime | -3.303 |
lest | -3.254 |
othe | -3.243 |
Token | , |
Token ID | 11 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
trop | +0.948 |
soc | +0.893 |
lest | +0.849 |
ftime | +0.845 |
othe | +0.843 |
Neg logit contributions | |
hyde | -0.923 |
zyk | -0.854 |
ortmund | -0.846 |
learnt | -0.840 |
Fail | -0.839 |
Token | a |
Token ID | 257 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
trop | +1.261 |
soc | +1.194 |
lest | +1.137 |
ftime | +1.132 |
othe | +1.130 |
Neg logit contributions | |
hyde | -1.058 |
zyk | -0.973 |
ortmund | -0.958 |
learnt | -0.954 |
Fail | -0.951 |
Token | University |
Token ID | 2059 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
trop | +0.824 |
soc | +0.775 |
lest | +0.736 |
ftime | +0.732 |
othe | +0.731 |
Neg logit contributions | |
hyde | -0.803 |
zyk | -0.746 |
ortmund | -0.734 |
learnt | -0.732 |
Fail | -0.728 |
Token | of |
Token ID | 286 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
hyde | +0.510 |
zyk | +0.476 |
ortmund | +0.466 |
Fail | +0.464 |
learnt | +0.464 |
Neg logit contributions | |
trop | -0.554 |
soc | -0.517 |
lest | -0.494 |
othe | -0.489 |
ftime | -0.487 |
Token | Edinburgh |
Token ID | 23475 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
hyde | +1.625 |
zyk | +1.540 |
learnt | +1.517 |
Fail | +1.510 |
XT | +1.503 |
Neg logit contributions | |
trop | -1.248 |
soc | -1.156 |
lest | -1.096 |
ftime | -1.094 |
othe | -1.064 |
Token | lingu |
Token ID | 20280 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
hyde | +2.100 |
zyk | +1.998 |
learnt | +1.967 |
ortmund | +1.912 |
XT | +1.911 |
Neg logit contributions | |
trop | -2.546 |
soc | -2.376 |
lest | -2.304 |
othe | -2.282 |
ftime | -2.244 |
Token | ist |
Token ID | 396 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
zyk | +5.277 |
hyde | +5.190 |
XT | +5.057 |
learnt | +4.861 |
Po | +4.794 |
Neg logit contributions | |
trop | -5.692 |
soc | -5.120 |
ftime | -5.065 |
acements | -5.026 |
Wem | -5.009 |
Token | who |
Token ID | 508 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
trop | +3.139 |
soc | +2.927 |
ftime | +2.778 |
age | +2.765 |
lest | +2.760 |
Neg logit contributions | |
hyde | -3.889 |
ortmund | -3.604 |
Fail | -3.578 |
zyk | -3.572 |
XT | -3.521 |
Token | co |
Token ID | 763 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
trop | +1.879 |
soc | +1.786 |
ftime | +1.727 |
lest | +1.713 |
othe | +1.698 |
Neg logit contributions | |
hyde | -1.441 |
zyk | -1.304 |
ortmund | -1.302 |
Fail | -1.297 |
XT | -1.278 |
Token | - |
Token ID | 12 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
hyde | +0.224 |
zyk | +0.209 |
learnt | +0.205 |
Fail | +0.203 |
ortmund | +0.203 |
Neg logit contributions | |
trop | -0.237 |
soc | -0.222 |
lest | -0.211 |
ftime | -0.210 |
othe | -0.210 |
Token | authored |
Token ID | 39351 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
trop | +2.615 |
soc | +2.466 |
lest | +2.338 |
ftime | +2.299 |
age | +2.289 |
Neg logit contributions | |
hyde | -2.928 |
ortmund | -2.711 |
zyk | -2.700 |
Fail | -2.674 |
learnt | -2.672 |
Token | 36 |
Token ID | 4570 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
hyde | +1.833 |
zyk | +1.709 |
learnt | +1.701 |
ortmund | +1.677 |
Fail | +1.667 |
Neg logit contributions | |
trop | -2.323 |
soc | -2.218 |
ftime | -2.121 |
lest | -2.110 |
othe | -2.108 |
Token | i |
Token ID | 72 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
hyde | +1.405 |
zyk | +1.312 |
learnt | +1.295 |
XT | +1.294 |
ortmund | +1.291 |
Neg logit contributions | |
trop | -1.367 |
soc | -1.283 |
lest | -1.228 |
ftime | -1.227 |
othe | -1.222 |
Token | departing |
Token ID | 37717 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
hyde | +1.798 |
learnt | +1.688 |
zyk | +1.687 |
ortmund | +1.667 |
XT | +1.659 |
Neg logit contributions | |
trop | -1.352 |
soc | -1.275 |
lest | -1.196 |
ftime | -1.192 |
othe | -1.190 |
Token | on |
Token ID | 319 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
hyde | +0.462 |
zyk | +0.430 |
learnt | +0.428 |
ortmund | +0.426 |
XT | +0.420 |
Neg logit contributions | |
trop | -0.438 |
soc | -0.412 |
lest | -0.392 |
ftime | -0.390 |
othe | -0.387 |
Token | December |
Token ID | 3426 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
hyde | +0.431 |
zyk | +0.399 |
learnt | +0.395 |
ortmund | +0.393 |
Fail | +0.387 |
Neg logit contributions | |
trop | -0.515 |
soc | -0.493 |
lest | -0.470 |
ftime | -0.464 |
othe | -0.464 |
Token | 30 |
Token ID | 1542 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
trop | +1.431 |
soc | +1.352 |
Cros | +1.282 |
lest | +1.281 |
othe | +1.279 |
Neg logit contributions | |
hyde | -1.390 |
zyk | -1.266 |
ortmund | -1.253 |
learnt | -1.244 |
Fail | -1.232 |
Token | at |
Token ID | 379 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
hyde | +4.930 |
learnt | +4.759 |
zyk | +4.646 |
XT | +4.530 |
ortmund | +4.499 |
Neg logit contributions | |
trop | -6.530 |
soc | -6.352 |
lest | -6.042 |
ERA | -5.987 |
ftime | -5.978 |
Token | £ |
Token ID | 4248 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
hyde | +1.726 |
learnt | +1.552 |
zyk | +1.535 |
ortmund | +1.510 |
Fail | +1.491 |
Neg logit contributions | |
trop | -3.483 |
soc | -3.327 |
lest | -3.196 |
ftime | -3.194 |
othe | -3.162 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
hyde | +1.805 |
zyk | +1.653 |
XT | +1.601 |
ortmund | +1.601 |
Fail | +1.587 |
Neg logit contributions | |
trop | -2.442 |
soc | -2.305 |
ftime | -2.227 |
lest | -2.215 |
othe | -2.192 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
trop | +1.170 |
soc | +1.095 |
lest | +1.034 |
ftime | +1.028 |
othe | +1.027 |
Neg logit contributions | |
hyde | -1.356 |
zyk | -1.265 |
ortmund | -1.247 |
learnt | -1.244 |
Fail | -1.238 |
Token | 999 |
Token ID | 17032 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
hyde | +0.417 |
zyk | +0.382 |
ortmund | +0.374 |
learnt | +0.373 |
Fail | +0.371 |
Neg logit contributions | |
trop | -0.585 |
soc | -0.555 |
lest | -0.531 |
ftime | -0.529 |
othe | -0.527 |
Token | : |
Token ID | 25 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
hyde | +1.177 |
learnt | +1.102 |
zyk | +1.100 |
ortmund | +1.073 |
Fail | +1.066 |
Neg logit contributions | |
trop | -1.491 |
soc | -1.401 |
ftime | -1.339 |
lest | -1.339 |
othe | -1.324 |
Token | In |
Token ID | 554 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
trop | +1.085 |
soc | +1.030 |
lest | +0.980 |
Cros | +0.974 |
ftime | +0.974 |
Neg logit contributions | |
hyde | -0.928 |
zyk | -0.852 |
ortmund | -0.838 |
Fail | -0.831 |
learnt | -0.829 |
Token | the |
Token ID | 262 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
hyde | +1.308 |
zyk | +1.214 |
learnt | +1.190 |
ortmund | +1.190 |
Fail | +1.184 |
Neg logit contributions | |
trop | -1.467 |
soc | -1.378 |
lest | -1.314 |
othe | -1.308 |
ftime | -1.307 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
trop | +3.301 |
soc | +3.151 |
Cros | +3.007 |
going | +2.982 |
othe | +2.969 |
Neg logit contributions | |
hyde | -3.130 |
zyk | -2.834 |
ortmund | -2.821 |
XT | -2.763 |
learnt | -2.762 |
Token | Journal |
Token ID | 4913 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
hyde | +2.252 |
zyk | +2.102 |
Fail | +2.082 |
learnt | +2.061 |
XT | +2.044 |
Neg logit contributions | |
trop | -2.903 |
soc | -2.700 |
lest | -2.598 |
ftime | -2.588 |
othe | -2.560 |
Token | - |
Token ID | 12 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
XT | +5.391 |
zyk | +5.302 |
hyde | +5.242 |
Fail | +5.172 |
Po | +5.137 |
Neg logit contributions | |
trop | -8.350 |
soc | -7.337 |
lest | -7.308 |
stood | -7.122 |
ulum | -7.043 |
Token | Const |
Token ID | 34184 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
Fail | +4.389 |
hyde | +4.341 |
zyk | +4.208 |
XT | +4.196 |
learnt | +4.104 |
Neg logit contributions | |
trop | -6.663 |
soc | -6.116 |
lest | -6.102 |
ftime | -6.086 |
Cros | -5.961 |
Token | itution |
Token ID | 2738 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
hyde | +3.247 |
zyk | +3.118 |
learnt | +3.117 |
Fail | +3.063 |
XT | +3.004 |
Neg logit contributions | |
trop | -5.220 |
soc | -4.919 |
ftime | -4.787 |
stood | -4.731 |
going | -4.730 |
Token | 's |
Token ID | 338 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
hyde | +2.707 |
zyk | +2.565 |
learnt | +2.528 |
ortmund | +2.509 |
Fail | +2.502 |
Neg logit contributions | |
trop | -2.909 |
soc | -2.700 |
lest | -2.607 |
ftime | -2.554 |
othe | -2.545 |
Token | published |
Token ID | 3199 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
trop | +1.236 |
soc | +1.174 |
lest | +1.118 |
ftime | +1.113 |
Cros | +1.111 |
Neg logit contributions | |
hyde | -0.985 |
zyk | -0.900 |
ortmund | -0.885 |
learnt | -0.878 |
Fail | -0.875 |
Token | scouting |
Token ID | 27088 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
trop | +1.547 |
soc | +1.474 |
lest | +1.406 |
ftime | +1.400 |
othe | +1.397 |
Neg logit contributions | |
hyde | -1.121 |
zyk | -1.020 |
ortmund | -1.005 |
learnt | -0.996 |
Fail | -0.992 |
Token |
|
Token ID | 198 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
hyde | +1.138 |
zyk | +1.055 |
learnt | +1.027 |
ortmund | +1.021 |
Fail | +1.020 |
Neg logit contributions | |
trop | -1.631 |
soc | -1.547 |
ftime | -1.481 |
lest | -1.479 |
othe | -1.472 |
Token |
|
Token ID | 198 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
hyde | +1.890 |
zyk | +1.862 |
Fail | +1.819 |
XT | +1.766 |
learnt | +1.736 |
Neg logit contributions | |
trop | -4.196 |
nomine | -4.073 |
ftime | -3.961 |
soc | -3.956 |
Wem | -3.839 |
Token | What |
Token ID | 2061 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
hyde | +2.271 |
zyk | +2.118 |
Fail | +2.106 |
XT | +2.064 |
ortmund | +2.010 |
Neg logit contributions | |
trop | -3.487 |
soc | -3.309 |
ftime | -3.212 |
othe | -3.195 |
Cros | -3.193 |
Token | was |
Token ID | 373 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
hyde | +0.812 |
zyk | +0.746 |
learnt | +0.734 |
ortmund | +0.730 |
Fail | +0.726 |
Neg logit contributions | |
trop | -1.122 |
soc | -1.061 |
lest | -1.018 |
ftime | -1.009 |
othe | -1.009 |
Token | the |
Token ID | 262 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
hyde | +2.520 |
learnt | +2.410 |
Fail | +2.360 |
zyk | +2.329 |
ortmund | +2.298 |
Neg logit contributions | |
trop | -3.676 |
soc | -3.457 |
ftime | -3.292 |
othe | -3.284 |
lest | -3.264 |
Token | most |
Token ID | 749 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
hyde | +1.676 |
zyk | +1.539 |
Fail | +1.511 |
learnt | +1.511 |
ortmund | +1.496 |
Neg logit contributions | |
trop | -2.562 |
soc | -2.435 |
othe | -2.321 |
lest | -2.320 |
ftime | -2.312 |
Token | interesting |
Token ID | 3499 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
learnt | +4.452 |
hyde | +4.124 |
discovery | +4.015 |
Fail | +4.010 |
text | +3.815 |
Neg logit contributions | |
trop | -8.682 |
soc | -8.312 |
ERA | -8.058 |
othe | -7.975 |
ftime | -7.944 |
Token | thing |
Token ID | 1517 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
learnt | +3.761 |
hyde | +3.645 |
discovery | +3.557 |
zyk | +3.527 |
Fail | +3.513 |
Neg logit contributions | |
trop | -6.532 |
soc | -6.241 |
othe | -6.059 |
ftime | -5.996 |
lest | -5.993 |
Token | you |
Token ID | 345 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
learnt | +4.035 |
hyde | +3.608 |
zyk | +3.578 |
XT | +3.478 |
Fail | +3.419 |
Neg logit contributions | |
trop | -9.393 |
soc | -8.645 |
ftime | -8.511 |
othe | -8.436 |
acements | -8.407 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
learnt | +5.505 |
zyk | +4.553 |
hyde | +4.313 |
Fail | +4.009 |
text | +3.893 |
Neg logit contributions | |
trop | -11.642 |
soc | -10.866 |
ftime | -10.799 |
othe | -10.669 |
Wem | -10.611 |
Token | from |
Token ID | 422 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
learnt | +4.329 |
hyde | +4.183 |
zyk | +3.984 |
XT | +3.708 |
ortmund | +3.687 |
Neg logit contributions | |
trop | -7.444 |
soc | -6.908 |
acements | -6.876 |
ftime | -6.862 |
othe | -6.778 |
Token | . |
Token ID | 13 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
trop | +1.662 |
soc | +1.576 |
lest | +1.504 |
othe | +1.494 |
ftime | +1.493 |
Neg logit contributions | |
hyde | -1.331 |
zyk | -1.222 |
ortmund | -1.205 |
learnt | -1.195 |
Fail | -1.192 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
trop | +0.521 |
soc | +0.493 |
lest | +0.472 |
ftime | +0.471 |
othe | +0.470 |
Neg logit contributions | |
hyde | -0.350 |
zyk | -0.320 |
ortmund | -0.312 |
Fail | -0.312 |
learnt | -0.311 |
Token |
|
Token ID | 198 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
trop | +0.788 |
soc | +0.747 |
ftime | +0.718 |
lest | +0.716 |
othe | +0.713 |
Neg logit contributions | |
hyde | -0.514 |
zyk | -0.474 |
learnt | -0.461 |
ortmund | -0.460 |
Fail | -0.460 |
Token | He |
Token ID | 1544 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
hyde | +0.255 |
zyk | +0.235 |
Fail | +0.233 |
XT | +0.230 |
ortmund | +0.229 |
Neg logit contributions | |
trop | -0.320 |
soc | -0.302 |
ftime | -0.288 |
Cros | -0.288 |
lest | -0.288 |
Token | was |
Token ID | 373 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
hyde | +0.107 |
zyk | +0.098 |
learnt | +0.096 |
ortmund | +0.095 |
Fail | +0.094 |
Neg logit contributions | |
trop | -0.154 |
soc | -0.146 |
lest | -0.139 |
ftime | -0.139 |
othe | -0.138 |
Token | facing |
Token ID | 6476 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
hyde | +1.480 |
zyk | +1.367 |
learnt | +1.362 |
Fail | +1.321 |
ortmund | +1.320 |
Neg logit contributions | |
trop | -1.947 |
soc | -1.829 |
lest | -1.744 |
ftime | -1.732 |
othe | -1.726 |
Token | a |
Token ID | 257 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
hyde | +4.238 |
learnt | +4.089 |
discovery | +4.035 |
zyk | +3.999 |
text | +3.891 |
Neg logit contributions | |
trop | -6.579 |
soc | -6.281 |
ftime | -6.021 |
othe | -5.989 |
lest | -5.988 |
Token | one |
Token ID | 530 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
hyde | +3.590 |
learnt | +3.406 |
zyk | +3.340 |
discovery | +3.296 |
Fail | +3.258 |
Neg logit contributions | |
trop | -5.012 |
soc | -4.749 |
lest | -4.619 |
othe | -4.531 |
ftime | -4.502 |
Token | - |
Token ID | 12 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
hyde | +4.223 |
zyk | +3.940 |
learnt | +3.881 |
Fail | +3.771 |
discovery | +3.687 |
Neg logit contributions | |
trop | -6.908 |
soc | -6.477 |
ftime | -6.274 |
lest | -6.196 |
othe | -6.095 |
Token | year |
Token ID | 1941 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
hyde | +0.263 |
zyk | +0.248 |
learnt | +0.244 |
Fail | +0.244 |
ortmund | +0.243 |
Neg logit contributions | |
trop | -0.159 |
soc | -0.145 |
ftime | -0.136 |
othe | -0.135 |
lest | -0.135 |
Token | suspension |
Token ID | 11461 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
trop | +1.751 |
soc | +1.658 |
lest | +1.583 |
ftime | +1.580 |
going | +1.580 |
Neg logit contributions | |
hyde | -1.278 |
zyk | -1.169 |
ortmund | -1.152 |
learnt | -1.133 |
Fail | -1.131 |