Token | sight |
Token ID | 6504 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ikes | +2.004 |
Stras | +1.839 |
hene | +1.806 |
Spr | +1.789 |
saddle | +1.769 |
Neg logit contributions | |
Alam | -1.897 |
Antar | -1.854 |
Aman | -1.692 |
Negro | -1.658 |
Jama | -1.639 |
Token | does |
Token ID | 857 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ikes | +1.008 |
Stras | +0.902 |
hene | +0.898 |
Spr | +0.889 |
Stage | +0.869 |
Neg logit contributions | |
Alam | -1.099 |
Antar | -1.068 |
Aman | -0.984 |
Negro | -0.965 |
Jama | -0.955 |
Token | not |
Token ID | 407 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Alam | +1.238 |
Antar | +1.199 |
Aman | +1.104 |
Negro | +1.083 |
Jama | +1.074 |
Neg logit contributions | |
ikes | -1.154 |
hene | -1.038 |
Stras | -1.037 |
Spr | -1.014 |
Stage | -1.001 |
Token | mean |
Token ID | 1612 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Alam | +1.508 |
Antar | +1.465 |
Aman | +1.357 |
Negro | +1.335 |
Jama | +1.320 |
Neg logit contributions | |
ikes | -1.275 |
Stras | -1.143 |
hene | -1.137 |
Spr | -1.124 |
Stage | -1.102 |
Token | out |
Token ID | 503 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
Alam | +1.188 |
Antar | +1.148 |
Aman | +1.046 |
Negro | +1.028 |
Jama | +1.012 |
Neg logit contributions | |
ikes | -1.394 |
hene | -1.269 |
Stras | -1.261 |
Spr | -1.249 |
Stage | -1.231 |
Token | of |
Token ID | 286 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
ikes | +4.301 |
Spr | +3.764 |
Stras | +3.746 |
hene | +3.713 |
saddle | +3.672 |
Neg logit contributions | |
Alam | -5.895 |
Antar | -5.663 |
Aman | -5.385 |
Malays | -5.187 |
Negro | -5.186 |
Token | the |
Token ID | 262 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ikes | +4.958 |
Stras | +4.425 |
saddle | +4.411 |
hene | +4.190 |
Spr | +4.134 |
Neg logit contributions | |
Alam | -10.407 |
Antar | -10.310 |
Aman | -9.734 |
Negro | -9.562 |
Malays | -9.419 |
Token | ocean |
Token ID | 9151 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
ikes | +1.847 |
Stras | +1.672 |
hene | +1.664 |
Spr | +1.646 |
saddle | +1.625 |
Neg logit contributions | |
Alam | -1.713 |
Antar | -1.661 |
Aman | -1.517 |
Negro | -1.483 |
Jama | -1.465 |
Token | . |
Token ID | 13 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ikes | +0.575 |
Stras | +0.513 |
hene | +0.511 |
Spr | +0.505 |
Stage | +0.494 |
Neg logit contributions | |
Alam | -0.671 |
Antar | -0.652 |
Aman | -0.602 |
Negro | -0.591 |
Jama | -0.585 |
Token | Life |
Token ID | 5155 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Alam | +2.120 |
Antar | +2.039 |
Aman | +1.894 |
Jama | +1.848 |
Negro | +1.846 |
Neg logit contributions | |
ikes | -1.887 |
hene | -1.683 |
Stras | -1.643 |
saddle | -1.631 |
Spr | -1.628 |
Token | in |
Token ID | 287 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ikes | +0.176 |
Stras | +0.157 |
hene | +0.157 |
Spr | +0.156 |
Stage | +0.152 |
Neg logit contributions | |
Alam | -0.192 |
Antar | -0.186 |
Aman | -0.172 |
Negro | -0.169 |
Jama | -0.167 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ikes | +1.648 |
Stras | +1.493 |
hene | +1.486 |
Spr | +1.468 |
Stage | +1.443 |
Neg logit contributions | |
Alam | -1.479 |
Antar | -1.433 |
Aman | -1.307 |
Negro | -1.275 |
Jama | -1.261 |
Token | them |
Token ID | 606 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ikes | +0.881 |
Stras | +0.788 |
hene | +0.780 |
Spr | +0.770 |
saddle | +0.754 |
Neg logit contributions | |
Alam | -1.049 |
Antar | -1.022 |
Aman | -0.942 |
Negro | -0.923 |
Jama | -0.913 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Alam | +0.098 |
Antar | +0.095 |
Aman | +0.087 |
Negro | +0.085 |
Jama | +0.084 |
Neg logit contributions | |
ikes | -0.104 |
Stras | -0.094 |
hene | -0.094 |
Spr | -0.093 |
Stage | -0.091 |
Token | way |
Token ID | 835 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ikes | +0.103 |
Stras | +0.094 |
hene | +0.093 |
Spr | +0.092 |
Stage | +0.091 |
Neg logit contributions | |
Alam | -0.087 |
Antar | -0.084 |
Aman | -0.077 |
Negro | -0.075 |
Jama | -0.074 |
Token | they |
Token ID | 484 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
Alam | +0.801 |
Antar | +0.773 |
Aman | +0.710 |
Negro | +0.696 |
Jama | +0.689 |
Neg logit contributions | |
ikes | -0.887 |
hene | -0.802 |
Stras | -0.798 |
Spr | -0.794 |
Stage | -0.778 |
Token | talk |
Token ID | 1561 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
ikes | +0.465 |
Stras | +0.419 |
hene | +0.418 |
Spr | +0.412 |
Stage | +0.405 |
Neg logit contributions | |
Alam | -0.449 |
Antar | -0.435 |
Aman | -0.398 |
Negro | -0.390 |
Jama | -0.385 |
Token | to |
Token ID | 284 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
ikes | +6.268 |
Stras | +5.651 |
saddle | +5.473 |
Spr | +5.472 |
hene | +5.414 |
Neg logit contributions | |
Alam | -7.865 |
Antar | -7.697 |
Aman | -7.019 |
Negro | -6.868 |
negro | -6.830 |
Token | each |
Token ID | 1123 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ikes | +3.329 |
Stras | +3.049 |
hene | +2.971 |
Spr | +2.950 |
saddle | +2.931 |
Neg logit contributions | |
Alam | -3.310 |
Antar | -3.229 |
Aman | -2.935 |
Negro | -2.855 |
Malays | -2.841 |
Token | other |
Token ID | 584 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
ikes | +1.587 |
Stras | +1.442 |
hene | +1.437 |
Spr | +1.422 |
Stage | +1.397 |
Neg logit contributions | |
Alam | -1.358 |
Antar | -1.313 |
Aman | -1.196 |
Negro | -1.167 |
Jama | -1.153 |
Token | . |
Token ID | 13 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
ikes | +0.360 |
Stras | +0.322 |
hene | +0.321 |
Spr | +0.317 |
Stage | +0.311 |
Neg logit contributions | |
Alam | -0.392 |
Antar | -0.380 |
Aman | -0.350 |
Negro | -0.343 |
Jama | -0.340 |
Token | But |
Token ID | 887 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
ikes | +0.531 |
Stras | +0.475 |
hene | +0.472 |
Spr | +0.466 |
Stage | +0.457 |
Neg logit contributions | |
Alam | -0.635 |
Antar | -0.618 |
Aman | -0.571 |
Negro | -0.560 |
Jama | -0.554 |
Token | 3 |
Token ID | 18 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
ikes | +0.357 |
Stras | +0.313 |
hene | +0.311 |
Spr | +0.305 |
saddle | +0.299 |
Neg logit contributions | |
Alam | -0.542 |
Antar | -0.523 |
Aman | -0.493 |
Negro | -0.485 |
Jama | -0.480 |
Token | minutes |
Token ID | 2431 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
Alam | +0.583 |
Antar | +0.557 |
Aman | +0.504 |
Negro | +0.491 |
Jama | +0.485 |
Neg logit contributions | |
ikes | -0.853 |
Stras | -0.782 |
hene | -0.780 |
Spr | -0.773 |
Stage | -0.761 |
Token | until |
Token ID | 1566 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ikes | +2.235 |
Stras | +1.990 |
hene | +1.974 |
Spr | +1.950 |
saddle | +1.911 |
Neg logit contributions | |
Alam | -2.724 |
Antar | -2.671 |
Aman | -2.449 |
Negro | -2.400 |
Jama | -2.386 |
Token | golden |
Token ID | 10861 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
ikes | +1.071 |
Stras | +0.959 |
hene | +0.953 |
Spr | +0.937 |
saddle | +0.925 |
Neg logit contributions | |
Alam | -1.255 |
Antar | -1.230 |
Aman | -1.125 |
Negro | -1.100 |
Jama | -1.090 |
Token | brown |
Token ID | 7586 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Alam | +0.295 |
Antar | +0.280 |
Aman | +0.237 |
Negro | +0.227 |
Jama | +0.222 |
Neg logit contributions | |
ikes | -0.759 |
Stras | -0.706 |
hene | -0.705 |
Spr | -0.699 |
Stage | -0.690 |
Token | . |
Token ID | 13 |
Feature activation | +8.92e+00 |
Pos logit contributions | |
ikes | +1.623 |
Stras | +1.438 |
hene | +1.438 |
Spr | +1.418 |
Stage | +1.384 |
Neg logit contributions | |
Alam | -2.043 |
Antar | -2.015 |
Aman | -1.839 |
Negro | -1.804 |
negro | -1.789 |
Token | These |
Token ID | 2312 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
ikes | +5.197 |
Stras | +4.803 |
Spr | +4.628 |
hene | +4.533 |
Stage | +4.520 |
Neg logit contributions | |
Alam | -8.620 |
Antar | -8.434 |
negro | -7.911 |
Aman | -7.731 |
Negro | -7.636 |
Token | are |
Token ID | 389 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
ikes | +2.831 |
Stras | +2.541 |
hene | +2.531 |
Spr | +2.496 |
saddle | +2.467 |
Neg logit contributions | |
Alam | -2.932 |
Antar | -2.896 |
Aman | -2.616 |
Negro | -2.553 |
Jama | -2.546 |
Token | lightly |
Token ID | 15376 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
ikes | +3.123 |
hene | +2.854 |
Stras | +2.840 |
Spr | +2.826 |
saddle | +2.802 |
Neg logit contributions | |
Alam | -2.295 |
Antar | -2.194 |
Aman | -1.965 |
Jama | -1.899 |
Negro | -1.897 |
Token | fried |
Token ID | 23018 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ikes | +0.729 |
Stras | +0.655 |
hene | +0.653 |
Spr | +0.645 |
Stage | +0.630 |
Neg logit contributions | |
Alam | -0.752 |
Antar | -0.733 |
Aman | -0.670 |
Negro | -0.654 |
Jama | -0.647 |
Token | and |
Token ID | 290 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ikes | +1.116 |
Stras | +1.000 |
hene | +0.998 |
Spr | +0.986 |
Stage | +0.965 |
Neg logit contributions | |
Alam | -1.205 |
Antar | -1.174 |
Aman | -1.077 |
Negro | -1.055 |
Jama | -1.045 |
Token | be |
Token ID | 307 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ikes | +1.198 |
Stras | +1.063 |
hene | +1.060 |
Spr | +1.045 |
Stage | +1.022 |
Neg logit contributions | |
Alam | -1.489 |
Antar | -1.446 |
Aman | -1.341 |
Negro | -1.316 |
Jama | -1.303 |
Token | explored |
Token ID | 18782 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
ikes | +0.453 |
Stras | +0.422 |
hene | +0.419 |
Spr | +0.415 |
Stage | +0.411 |
Neg logit contributions | |
Alam | -0.196 |
Antar | -0.187 |
Aman | -0.160 |
Malays | -0.153 |
Negro | -0.153 |
Token | in |
Token ID | 287 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
ikes | +0.350 |
Stras | +0.314 |
hene | +0.314 |
Spr | +0.310 |
Stage | +0.303 |
Neg logit contributions | |
Alam | -0.358 |
Antar | -0.345 |
Aman | -0.319 |
Negro | -0.313 |
Jama | -0.309 |
Token | 3 |
Token ID | 513 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
ikes | +2.919 |
Spr | +2.544 |
hene | +2.544 |
Stras | +2.540 |
Stage | +2.478 |
Neg logit contributions | |
Alam | -4.266 |
Antar | -4.200 |
Aman | -3.887 |
Negro | -3.831 |
Malays | -3.810 |
Token | D |
Token ID | 35 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
Alam | +0.486 |
Antar | +0.461 |
Aman | +0.426 |
Negro | +0.417 |
Jama | +0.410 |
Neg logit contributions | |
ikes | -0.580 |
Stras | -0.525 |
hene | -0.523 |
Spr | -0.513 |
saddle | -0.509 |
Token | with |
Token ID | 351 |
Feature activation | +8.62e+00 |
Pos logit contributions | |
ikes | +2.842 |
Stras | +2.498 |
Spr | +2.481 |
hene | +2.477 |
Stage | +2.415 |
Neg logit contributions | |
Alam | -3.729 |
Antar | -3.709 |
Aman | -3.375 |
Negro | -3.303 |
Malays | -3.295 |
Token | Google |
Token ID | 3012 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ikes | +6.888 |
Spr | +6.264 |
Stras | +6.166 |
hene | +6.144 |
Stage | +6.058 |
Neg logit contributions | |
Antar | -6.622 |
Alam | -6.577 |
Aman | -5.913 |
Negro | -5.875 |
Malays | -5.851 |
Token | Maps |
Token ID | 20347 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Alam | +1.016 |
Antar | +0.966 |
Aman | +0.880 |
Negro | +0.858 |
Jama | +0.848 |
Neg logit contributions | |
ikes | -1.224 |
hene | -1.117 |
Stras | -1.112 |
Spr | -1.090 |
EStreamFrame | -1.082 |
Token |
|
Token ID | 198 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Alam | +0.106 |
Antar | +0.102 |
Aman | +0.095 |
Negro | +0.093 |
Jama | +0.092 |
Neg logit contributions | |
ikes | -0.097 |
Stras | -0.087 |
hene | -0.087 |
Spr | -0.085 |
Stage | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Alam | +1.754 |
Antar | +1.608 |
Aman | +1.572 |
Negro | +1.551 |
Jama | +1.530 |
Neg logit contributions | |
ikes | -1.490 |
hene | -1.333 |
Stras | -1.321 |
saddle | -1.287 |
Spr | -1.279 |
Token | The |
Token ID | 464 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
ikes | +0.475 |
Stras | +0.421 |
hene | +0.420 |
Spr | +0.411 |
saddle | +0.403 |
Neg logit contributions | |
Alam | -0.613 |
Antar | -0.594 |
Aman | -0.552 |
Negro | -0.543 |
Jama | -0.537 |
Token | IS |
Token ID | 1797 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ikes | +1.916 |
Spr | +1.600 |
Stras | +1.525 |
hene | +1.474 |
Stage | +1.471 |
Neg logit contributions | |
Alam | -4.823 |
Antar | -4.731 |
Aman | -4.453 |
Negro | -4.418 |
negro | -4.410 |
Token | I |
Token ID | 40 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
ikes | +0.739 |
Stras | +0.665 |
Spr | +0.660 |
hene | +0.647 |
saddle | +0.632 |
Neg logit contributions | |
Alam | -0.948 |
Antar | -0.929 |
Aman | -0.857 |
Malays | -0.846 |
negro | -0.836 |
Token | Books |
Token ID | 13661 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ikes | +2.370 |
Stras | +2.128 |
Spr | +2.101 |
hene | +2.068 |
saddle | +2.039 |
Neg logit contributions | |
Alam | -2.645 |
Antar | -2.570 |
Aman | -2.353 |
Malays | -2.335 |
Negro | -2.318 |
Token | , |
Token ID | 11 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ikes | +1.929 |
Stras | +1.736 |
hene | +1.700 |
Spr | +1.669 |
Stage | +1.641 |
Neg logit contributions | |
Alam | -2.486 |
Antar | -2.456 |
Aman | -2.262 |
Malays | -2.196 |
Jama | -2.187 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
ikes | +2.303 |
Stras | +2.121 |
Spr | +2.088 |
saddle | +1.992 |
hene | +1.976 |
Neg logit contributions | |
Antar | -2.797 |
Alam | -2.755 |
Malays | -2.469 |
Aman | -2.468 |
negro | -2.408 |
Token | ). |
Token ID | 737 |
Feature activation | +8.62e+00 |
Pos logit contributions | |
ikes | +2.975 |
Stras | +2.677 |
Spr | +2.653 |
hene | +2.641 |
Jesus | +2.539 |
Neg logit contributions | |
Alam | -3.233 |
Antar | -3.172 |
Aman | -2.917 |
Malays | -2.821 |
Jama | -2.807 |
Token |
|
Token ID | 198 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
ikes | +4.575 |
Spr | +4.253 |
Stras | +4.116 |
SPR | +3.947 |
Jesus | +3.929 |
Neg logit contributions | |
Alam | -8.819 |
Antar | -8.707 |
negro | -7.931 |
Aman | -7.838 |
Negro | -7.809 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ikes | +2.301 |
Stras | +2.001 |
hene | +1.991 |
Spr | +1.985 |
Stage | +1.937 |
Neg logit contributions | |
Alam | -3.545 |
Antar | -3.521 |
Aman | -3.225 |
Negro | -3.165 |
negro | -3.155 |
Token | You |
Token ID | 1639 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ikes | +2.313 |
Spr | +2.029 |
Jesus | +1.943 |
Stage | +1.935 |
Pope | +1.877 |
Neg logit contributions | |
Alam | -3.592 |
Antar | -3.555 |
Aman | -3.221 |
Negro | -3.180 |
negro | -3.178 |
Token | can |
Token ID | 460 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
ikes | +1.367 |
hene | +1.212 |
Spr | +1.197 |
Stras | +1.195 |
Stage | +1.167 |
Neg logit contributions | |
Alam | -1.686 |
Antar | -1.636 |
Aman | -1.522 |
Negro | -1.485 |
Jama | -1.471 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ikes | +0.935 |
hene | +0.862 |
Stras | +0.862 |
Spr | +0.853 |
Stage | +0.842 |
Neg logit contributions | |
Alam | -0.540 |
Antar | -0.520 |
Aman | -0.461 |
Negro | -0.446 |
Jama | -0.438 |
Token | only |
Token ID | 691 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ikes | +3.495 |
Stras | +3.085 |
hene | +3.072 |
saddle | +2.987 |
Spr | +2.981 |
Neg logit contributions | |
Alam | -4.234 |
Antar | -4.110 |
Aman | -3.761 |
Negro | -3.699 |
negro | -3.657 |
Token | $ |
Token ID | 720 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ikes | +1.858 |
Stras | +1.719 |
hene | +1.657 |
Spr | +1.602 |
SPR | +1.589 |
Neg logit contributions | |
Alam | -1.893 |
Antar | -1.826 |
Aman | -1.640 |
negro | -1.625 |
Malays | -1.616 |
Token | 19 |
Token ID | 1129 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ikes | +1.589 |
hene | +1.448 |
Stras | +1.437 |
Spr | +1.415 |
saddle | +1.384 |
Neg logit contributions | |
Alam | -1.732 |
Antar | -1.672 |
Aman | -1.543 |
Negro | -1.521 |
Jama | -1.512 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ikes | +1.538 |
Stras | +1.315 |
hene | +1.302 |
Spr | +1.292 |
saddle | +1.279 |
Neg logit contributions | |
Alam | -2.118 |
Antar | -2.066 |
Aman | -1.904 |
Negro | -1.889 |
negro | -1.874 |
Token | 99 |
Token ID | 2079 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ikes | +2.095 |
Stras | +1.897 |
hene | +1.876 |
Spr | +1.867 |
saddle | +1.839 |
Neg logit contributions | |
Alam | -1.650 |
Antar | -1.611 |
Aman | -1.425 |
Negro | -1.396 |
Malays | -1.395 |
Token | ... |
Token ID | 986 |
Feature activation | +8.58e+00 |
Pos logit contributions | |
ikes | +1.632 |
Stras | +1.510 |
Spr | +1.506 |
hene | +1.495 |
saddle | +1.475 |
Neg logit contributions | |
Alam | -0.588 |
Antar | -0.558 |
Aman | -0.469 |
Negro | -0.439 |
Malays | -0.435 |
Token |
|
Token ID | 198 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
ikes | +4.789 |
Spr | +3.895 |
SPR | +3.835 |
Jesus | +3.762 |
Stage | +3.759 |
Neg logit contributions | |
Alam | -8.804 |
Antar | -8.744 |
Aman | -8.050 |
negro | -8.031 |
adem | -7.993 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ikes | +0.690 |
Stras | +0.608 |
hene | +0.608 |
Spr | +0.595 |
saddle | +0.583 |
Neg logit contributions | |
Alam | -0.928 |
Antar | -0.890 |
Aman | -0.839 |
Negro | -0.826 |
Jama | -0.816 |
Token | Because |
Token ID | 8128 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
ikes | +0.721 |
Stras | +0.640 |
hene | +0.637 |
Spr | +0.626 |
saddle | +0.612 |
Neg logit contributions | |
Alam | -0.921 |
Antar | -0.894 |
Aman | -0.831 |
Negro | -0.816 |
Jama | -0.807 |
Token | the |
Token ID | 262 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
Alam | +0.351 |
Antar | +0.339 |
Aman | +0.311 |
Negro | +0.305 |
Jama | +0.301 |
Neg logit contributions | |
ikes | -0.366 |
Stras | -0.329 |
hene | -0.329 |
Spr | -0.325 |
Stage | -0.319 |
Token | doctor |
Token ID | 6253 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ikes | +0.786 |
Stras | +0.708 |
hene | +0.704 |
Spr | +0.695 |
Stage | +0.681 |
Neg logit contributions | |
Alam | -0.819 |
Antar | -0.795 |
Aman | -0.730 |
Negro | -0.714 |
Jama | -0.708 |
Token | out |
Token ID | 503 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Alam | +1.446 |
Antar | +1.403 |
Aman | +1.285 |
Negro | +1.265 |
Jama | +1.251 |
Neg logit contributions | |
ikes | -1.519 |
hene | -1.367 |
Stras | -1.364 |
Spr | -1.352 |
Stage | -1.325 |
Token | there |
Token ID | 612 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Alam | +0.113 |
Antar | +0.109 |
Aman | +0.100 |
Negro | +0.098 |
Jama | +0.097 |
Neg logit contributions | |
ikes | -0.107 |
Stras | -0.096 |
hene | -0.095 |
Spr | -0.094 |
Stage | -0.092 |
Token | than |
Token ID | 621 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
Alam | +1.578 |
Antar | +1.525 |
Aman | +1.406 |
Negro | +1.378 |
Jama | +1.361 |
Neg logit contributions | |
ikes | -1.611 |
Stras | -1.453 |
hene | -1.452 |
Spr | -1.432 |
Stage | -1.405 |
Token | most |
Token ID | 749 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
Alam | +2.470 |
Antar | +2.384 |
Aman | +2.180 |
Negro | +2.156 |
Jama | +2.130 |
Neg logit contributions | |
ikes | -2.783 |
hene | -2.562 |
Stras | -2.506 |
Spr | -2.487 |
Stage | -2.444 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Alam | +3.087 |
Antar | +2.965 |
Negro | +2.748 |
Aman | +2.739 |
Jama | +2.704 |
Neg logit contributions | |
ikes | -3.136 |
hene | -2.861 |
Stras | -2.837 |
Spr | -2.811 |
Stage | -2.749 |
Token | - |
Token ID | 532 |
Feature activation | +8.55e+00 |
Pos logit contributions | |
Alam | +1.558 |
Antar | +1.500 |
Aman | +1.384 |
Negro | +1.358 |
Jama | +1.342 |
Neg logit contributions | |
ikes | -1.625 |
hene | -1.464 |
Stras | -1.449 |
Spr | -1.431 |
saddle | -1.410 |
Token | July |
Token ID | 2901 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
ikes | +5.505 |
Stras | +5.058 |
Spr | +4.932 |
hene | +4.904 |
SPR | +4.802 |
Neg logit contributions | |
Antar | -8.073 |
Alam | -7.844 |
Aman | -7.096 |
negro | -7.037 |
Negro | -6.935 |
Token | 6 |
Token ID | 718 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
ikes | +0.534 |
Stras | +0.475 |
hene | +0.475 |
Spr | +0.468 |
Stage | +0.458 |
Neg logit contributions | |
Alam | -0.629 |
Antar | -0.608 |
Aman | -0.565 |
Negro | -0.555 |
Jama | -0.548 |
Token | , |
Token ID | 11 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
ikes | +3.353 |
Spr | +3.001 |
Stras | +2.998 |
hene | +2.967 |
Stage | +2.929 |
Neg logit contributions | |
Antar | -4.455 |
Alam | -4.380 |
Aman | -3.953 |
negro | -3.891 |
Malays | -3.868 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +7.71e+00 |
Pos logit contributions | |
ikes | +4.939 |
Spr | +4.615 |
Stras | +4.595 |
hene | +4.495 |
SPR | +4.451 |
Neg logit contributions | |
Antar | -5.300 |
Alam | -5.197 |
Aman | -4.570 |
Malays | -4.539 |
negro | -4.528 |
Token | R |
Token ID | 49 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ikes | +4.205 |
Spr | +3.820 |
Stage | +3.764 |
Jesus | +3.634 |
Rock | +3.604 |
Neg logit contributions | |
Antar | -8.144 |
Alam | -8.079 |
Aman | -7.437 |
negro | -7.241 |
Malays | -7.211 |
Token | is |
Token ID | 318 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ikes | +2.764 |
Stras | +2.473 |
hene | +2.467 |
Spr | +2.418 |
saddle | +2.393 |
Neg logit contributions | |
Alam | -2.983 |
Antar | -2.932 |
Aman | -2.668 |
Negro | -2.611 |
Jama | -2.595 |
Token | the |
Token ID | 262 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
ikes | +1.469 |
Stras | +1.325 |
hene | +1.321 |
Spr | +1.304 |
Stage | +1.278 |
Neg logit contributions | |
Alam | -1.417 |
Antar | -1.376 |
Aman | -1.256 |
Negro | -1.229 |
Malays | -1.217 |
Token | argument |
Token ID | 4578 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ikes | +2.158 |
Stras | +1.953 |
hene | +1.942 |
Spr | +1.917 |
saddle | +1.883 |
Neg logit contributions | |
Alam | -2.171 |
Antar | -2.109 |
Aman | -1.927 |
Negro | -1.885 |
Malays | -1.873 |
Token | for |
Token ID | 329 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
Alam | +1.024 |
Antar | +0.986 |
Aman | +0.896 |
Negro | +0.876 |
Jama | +0.868 |
Neg logit contributions | |
ikes | -1.303 |
hene | -1.189 |
Stras | -1.184 |
Spr | -1.171 |
Stage | -1.152 |
Token | a |
Token ID | 257 |
Feature activation | +7.82e+00 |
Pos logit contributions | |
ikes | +4.375 |
Stras | +3.948 |
Spr | +3.881 |
hene | +3.834 |
saddle | +3.806 |
Neg logit contributions | |
Alam | -4.632 |
Antar | -4.532 |
Aman | -4.134 |
Malays | -4.038 |
Negro | -4.020 |
Token | " |
Token ID | 366 |
Feature activation | +8.45e+00 |
Pos logit contributions | |
ikes | +5.270 |
Stras | +4.771 |
Spr | +4.654 |
hene | +4.629 |
saddle | +4.621 |
Neg logit contributions | |
Alam | -7.034 |
Antar | -6.910 |
Aman | -6.366 |
Malays | -6.292 |
Jama | -6.177 |
Token | : |
Token ID | 25 |
Feature activation | +6.33e+00 |
Pos logit contributions | |
ikes | +5.599 |
hene | +4.923 |
Spr | +4.895 |
Stras | +4.855 |
Stage | +4.740 |
Neg logit contributions | |
Alam | -7.821 |
Antar | -7.693 |
Aman | -7.149 |
Jama | -6.985 |
Malays | -6.966 |
Token | set |
Token ID | 2617 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
ikes | +4.846 |
hene | +4.338 |
Spr | +4.274 |
Stras | +4.257 |
Stage | +4.180 |
Neg logit contributions | |
Alam | -5.329 |
Antar | -5.285 |
Aman | -4.812 |
Jama | -4.700 |
Malays | -4.691 |
Token | " |
Token ID | 1 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
ikes | +3.259 |
hene | +2.854 |
Stras | +2.829 |
Spr | +2.827 |
Stage | +2.749 |
Neg logit contributions | |
Alam | -4.849 |
Antar | -4.841 |
Aman | -4.429 |
Malays | -4.315 |
Negro | -4.298 |
Token | command |
Token ID | 3141 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
ikes | +0.803 |
Stras | +0.660 |
hene | +0.650 |
Spr | +0.633 |
saddle | +0.611 |
Neg logit contributions | |
Alam | -2.315 |
Antar | -2.278 |
Aman | -2.140 |
Negro | -2.107 |
Malays | -2.103 |
Token | : |
Token ID | 1058 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ikes | +3.314 |
Stras | +3.012 |
hene | +2.967 |
Spr | +2.946 |
Stage | +2.891 |
Neg logit contributions | |
Alam | -3.365 |
Antar | -3.281 |
Aman | -2.984 |
Negro | -2.936 |
Malays | -2.916 |
Token | " |
Token ID | 366 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ikes | +0.568 |
hene | +0.510 |
Stras | +0.510 |
Spr | +0.504 |
Stage | +0.494 |
Neg logit contributions | |
Alam | -0.568 |
Antar | -0.550 |
Aman | -0.506 |
Negro | -0.495 |
Jama | -0.490 |
Token | he |
Token ID | 258 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
ikes | +0.908 |
Stras | +0.809 |
hene | +0.808 |
Spr | +0.799 |
Stage | +0.783 |
Neg logit contributions | |
Alam | -1.044 |
Antar | -1.018 |
Aman | -0.938 |
Negro | -0.919 |
Jama | -0.910 |
Token | said |
Token ID | 531 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
Alam | +0.717 |
Antar | +0.693 |
Aman | +0.641 |
Negro | +0.629 |
Jama | +0.622 |
Neg logit contributions | |
ikes | -0.670 |
Stras | -0.603 |
hene | -0.599 |
Spr | -0.593 |
Stage | -0.581 |
Token | / |
Token ID | 14 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ikes | +3.172 |
Stras | +2.814 |
hene | +2.803 |
Spr | +2.753 |
saddle | +2.723 |
Neg logit contributions | |
Alam | -3.957 |
Antar | -3.871 |
Aman | -3.530 |
Malays | -3.446 |
Negro | -3.420 |
Token | she |
Token ID | 7091 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ikes | +1.309 |
hene | +1.185 |
Stras | +1.183 |
Spr | +1.172 |
Stage | +1.149 |
Neg logit contributions | |
Alam | -1.103 |
Antar | -1.068 |
Aman | -0.971 |
Negro | -0.945 |
Jama | -0.937 |
Token | said |
Token ID | 531 |
Feature activation | +8.22e+00 |
Pos logit contributions | |
ikes | +1.451 |
Stras | +1.323 |
hene | +1.320 |
Spr | +1.307 |
saddle | +1.286 |
Neg logit contributions | |
Alam | -0.968 |
Antar | -0.935 |
Aman | -0.835 |
Negro | -0.808 |
Jama | -0.801 |
Token | " |
Token ID | 1 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ikes | +5.100 |
Stras | +4.574 |
hene | +4.392 |
saddle | +4.370 |
Spr | +4.346 |
Neg logit contributions | |
Alam | -7.850 |
Antar | -7.778 |
Aman | -7.110 |
Malays | -7.008 |
Jama | -6.843 |
Token | nature |
Token ID | 3450 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
Alam | +1.065 |
Antar | +1.027 |
Aman | +0.945 |
Negro | +0.928 |
Jama | +0.917 |
Neg logit contributions | |
ikes | -1.129 |
hene | -1.016 |
Stras | -1.011 |
Spr | -1.006 |
Stage | -0.987 |
Token | of |
Token ID | 286 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
Alam | +0.422 |
Antar | +0.408 |
Aman | +0.377 |
Negro | +0.370 |
Jama | +0.366 |
Neg logit contributions | |
ikes | -0.396 |
hene | -0.354 |
Stras | -0.352 |
Spr | -0.349 |
Stage | -0.342 |
Token | the |
Token ID | 262 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Alam | +0.742 |
Antar | +0.715 |
Aman | +0.655 |
Negro | +0.644 |
Jama | +0.637 |
Neg logit contributions | |
ikes | -0.798 |
hene | -0.723 |
Stras | -0.714 |
Spr | -0.712 |
Stage | -0.700 |
Token | case |
Token ID | 1339 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Alam | +0.451 |
Antar | +0.436 |
Aman | +0.400 |
Negro | +0.391 |
Jama | +0.387 |
Neg logit contributions | |
ikes | -0.476 |
hene | -0.429 |
Stras | -0.428 |
Spr | -0.424 |
Stage | -0.416 |
Token | Patrick |
Token ID | 9925 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
ikes | +2.804 |
Stras | +2.439 |
Spr | +2.363 |
saddle | +2.349 |
hene | +2.339 |
Neg logit contributions | |
Alam | -4.246 |
Antar | -4.112 |
Malays | -3.817 |
Negro | -3.812 |
negro | -3.799 |
Token | J |
Token ID | 449 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ikes | +0.028 |
Stras | +0.025 |
hene | +0.025 |
Spr | +0.025 |
Stage | +0.024 |
Neg logit contributions | |
Alam | -0.030 |
Antar | -0.029 |
Aman | -0.027 |
Negro | -0.027 |
negro | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Alam | +1.235 |
Antar | +1.201 |
Aman | +1.110 |
Negro | +1.090 |
Jama | +1.079 |
Neg logit contributions | |
ikes | -1.036 |
Stras | -0.922 |
hene | -0.920 |
Spr | -0.906 |
Stage | -0.886 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
Alam | +0.110 |
Antar | +0.105 |
Aman | +0.095 |
Negro | +0.093 |
Jama | +0.092 |
Neg logit contributions | |
ikes | -0.148 |
Stras | -0.135 |
hene | -0.135 |
Spr | -0.133 |
Stage | -0.132 |
Token | , |
Token ID | 11 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
ikes | +0.391 |
Stras | +0.351 |
hene | +0.347 |
Spr | +0.346 |
Stage | +0.339 |
Neg logit contributions | |
Alam | -0.479 |
Antar | -0.468 |
Aman | -0.438 |
Negro | -0.425 |
Malays | -0.423 |
Token | and |
Token ID | 290 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
ikes | +3.797 |
Stras | +3.393 |
Spr | +3.364 |
hene | +3.355 |
Stage | +3.241 |
Neg logit contributions | |
Alam | -4.612 |
Antar | -4.549 |
Aman | -4.171 |
Malays | -4.129 |
negro | -4.109 |
Token | critical |
Token ID | 4688 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
ikes | +4.237 |
Spr | +3.660 |
Stras | +3.554 |
hene | +3.467 |
Stage | +3.365 |
Neg logit contributions | |
Alam | -8.919 |
Antar | -8.553 |
Aman | -8.051 |
negro | -8.023 |
Malays | -7.950 |
Token | essays |
Token ID | 27126 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
ikes | +2.775 |
Spr | +2.409 |
Stras | +2.400 |
hene | +2.378 |
saddle | +2.306 |
Neg logit contributions | |
Alam | -4.503 |
Antar | -4.334 |
Aman | -4.047 |
Malays | -4.000 |
Negro | -3.999 |
Token | by |
Token ID | 416 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
ikes | +3.482 |
hene | +3.088 |
Spr | +3.042 |
Stras | +3.009 |
SPR | +2.979 |
Neg logit contributions | |
Antar | -4.717 |
Alam | -4.714 |
Malays | -4.264 |
Aman | -4.244 |
negro | -4.219 |
Token | Scott |
Token ID | 4746 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ikes | +3.604 |
Stras | +3.177 |
Spr | +3.135 |
hene | +3.115 |
saddle | +3.103 |
Neg logit contributions | |
Alam | -4.194 |
Antar | -4.063 |
Malays | -3.734 |
Aman | -3.724 |
Negro | -3.696 |
Token | Ric |
Token ID | 15868 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
ikes | +1.626 |
Stras | +1.483 |
hene | +1.448 |
Spr | +1.433 |
Stage | +1.389 |
Neg logit contributions | |
Alam | -1.783 |
Antar | -1.754 |
Aman | -1.589 |
Malays | -1.563 |
Negro | -1.559 |
Token | forms |
Token ID | 23914 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ikes | +0.677 |
Stras | +0.552 |
hene | +0.544 |
Spr | +0.530 |
Stage | +0.509 |
Neg logit contributions | |
Alam | -1.893 |
Antar | -1.852 |
Aman | -1.752 |
Negro | -1.729 |
Jama | -1.715 |
Token | . |
Token ID | 13 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Alam | +2.117 |
Antar | +1.919 |
Aman | +1.872 |
Negro | +1.847 |
Jama | +1.808 |
Neg logit contributions | |
ikes | -2.152 |
Stras | -1.957 |
hene | -1.930 |
Spr | -1.895 |
saddle | -1.891 |
Token | text |
Token ID | 5239 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Alam | +3.298 |
Antar | +3.139 |
Aman | +2.919 |
Negro | +2.908 |
negro | +2.849 |
Neg logit contributions | |
ikes | -2.611 |
Stras | -2.362 |
hene | -2.284 |
saddle | -2.229 |
Spr | -2.197 |
Token | rend |
Token ID | 10920 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Alam | +2.341 |
Antar | +2.212 |
Aman | +2.107 |
Negro | +2.095 |
adem | +2.065 |
Neg logit contributions | |
ikes | -1.436 |
Stras | -1.271 |
hene | -1.226 |
saddle | -1.210 |
Spr | -1.201 |
Token | erer |
Token ID | 11882 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
Alam | +1.718 |
Antar | +1.636 |
Aman | +1.573 |
Negro | +1.558 |
Jama | +1.540 |
Neg logit contributions | |
ikes | -0.665 |
Stras | -0.559 |
hene | -0.533 |
Spr | -0.528 |
saddle | -0.517 |
Token | ] |
Token ID | 60 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
ikes | +0.908 |
Stras | +0.832 |
hene | +0.830 |
Spr | +0.820 |
saddle | +0.807 |
Neg logit contributions | |
Alam | -0.629 |
Antar | -0.596 |
Aman | -0.543 |
Negro | -0.530 |
Jama | -0.521 |
Token | :: |
Token ID | 3712 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
ikes | +5.544 |
Spr | +5.009 |
Stage | +4.963 |
Stras | +4.871 |
hene | +4.851 |
Neg logit contributions | |
Antar | -7.320 |
Alam | -7.036 |
Aman | -6.366 |
negro | -6.298 |
Jama | -6.263 |
Token | Measure |
Token ID | 47384 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
Alam | +2.215 |
Antar | +2.123 |
Aman | +1.965 |
Negro | +1.950 |
Jama | +1.910 |
Neg logit contributions | |
ikes | -1.943 |
Stras | -1.747 |
hene | -1.731 |
saddle | -1.680 |
Spr | -1.652 |
Token | Text |
Token ID | 8206 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
Alam | +5.809 |
Antar | +5.427 |
Negro | +5.065 |
Aman | +4.995 |
Deep | +4.935 |
Neg logit contributions | |
ikes | -5.607 |
Stras | -4.982 |
hene | -4.942 |
saddle | -4.813 |
SPR | -4.660 |
Token | ($ |
Token ID | 16763 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
ikes | +0.461 |
Stras | +0.417 |
hene | +0.415 |
Spr | +0.407 |
saddle | +0.402 |
Neg logit contributions | |
Alam | -0.430 |
Antar | -0.416 |
Aman | -0.381 |
Negro | -0.374 |
Jama | -0.369 |
Token | art |
Token ID | 433 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Alam | +2.058 |
Antar | +1.770 |
Aman | +1.600 |
Negro | +1.551 |
adem | +1.535 |
Neg logit contributions | |
ikes | -5.310 |
Stras | -5.001 |
hene | -4.963 |
saddle | -4.839 |
Spr | -4.793 |
Token | to |
Token ID | 284 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
ikes | +0.935 |
Stras | +0.841 |
hene | +0.839 |
Spr | +0.829 |
Stage | +0.812 |
Neg logit contributions | |
Alam | -0.944 |
Antar | -0.913 |
Aman | -0.841 |
Negro | -0.824 |
Jama | -0.814 |
Token | discern |
Token ID | 22024 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ikes | +2.193 |
hene | +1.952 |
Stras | +1.946 |
Spr | +1.879 |
saddle | +1.875 |
Neg logit contributions | |
Alam | -2.651 |
Antar | -2.609 |
Aman | -2.409 |
Jama | -2.318 |
Negro | -2.312 |
Token | the |
Token ID | 262 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
ikes | +1.862 |
Stras | +1.688 |
hene | +1.681 |
Spr | +1.665 |
Stage | +1.634 |
Neg logit contributions | |
Alam | -1.669 |
Antar | -1.629 |
Aman | -1.473 |
Negro | -1.438 |
Jama | -1.424 |
Token | size |
Token ID | 2546 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ikes | +2.621 |
Stras | +2.373 |
hene | +2.370 |
Spr | +2.350 |
saddle | +2.314 |
Neg logit contributions | |
Alam | -2.358 |
Antar | -2.302 |
Aman | -2.078 |
Negro | -2.024 |
Jama | -2.009 |
Token | of |
Token ID | 286 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
ikes | +1.589 |
Stras | +1.422 |
hene | +1.414 |
Spr | +1.399 |
Stage | +1.371 |
Neg logit contributions | |
Alam | -1.816 |
Antar | -1.777 |
Aman | -1.630 |
Negro | -1.595 |
Jama | -1.582 |
Token | individual |
Token ID | 1981 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
ikes | +2.261 |
hene | +2.015 |
Stras | +2.010 |
Spr | +1.981 |
saddle | +1.961 |
Neg logit contributions | |
Alam | -2.910 |
Antar | -2.867 |
Aman | -2.625 |
Negro | -2.570 |
Malays | -2.556 |
Token | pixels |
Token ID | 17848 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ikes | +2.053 |
Stras | +1.380 |
Spr | +1.334 |
hene | +1.276 |
EStreamFrame | +1.144 |
Neg logit contributions | |
Antar | -10.621 |
Alam | -10.615 |
Aman | -9.882 |
Jama | -9.650 |
Negro | -9.623 |
Token | due |
Token ID | 2233 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ikes | +2.973 |
Stras | +2.748 |
hene | +2.746 |
Spr | +2.719 |
Stage | +2.693 |
Neg logit contributions | |
Alam | -1.710 |
Antar | -1.658 |
Aman | -1.442 |
Negro | -1.410 |
Jama | -1.385 |
Token | to |
Token ID | 284 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ikes | +2.464 |
Stras | +2.219 |
hene | +2.201 |
Spr | +2.190 |
Stage | +2.154 |
Neg logit contributions | |
Alam | -2.733 |
Antar | -2.705 |
Aman | -2.446 |
Negro | -2.389 |
negro | -2.373 |
Token | the |
Token ID | 262 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
ikes | +2.945 |
Stras | +2.669 |
hene | +2.646 |
Spr | +2.635 |
Stage | +2.580 |
Neg logit contributions | |
Alam | -2.827 |
Antar | -2.812 |
Aman | -2.504 |
Negro | -2.444 |
negro | -2.430 |
Token | amount |
Token ID | 2033 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
ikes | +3.949 |
Spr | +3.540 |
hene | +3.519 |
Stras | +3.516 |
saddle | +3.486 |
Neg logit contributions | |
Antar | -4.315 |
Alam | -4.313 |
Aman | -3.839 |
Malays | -3.767 |
Negro | -3.757 |
Token | which |
Token ID | 543 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
ikes | +4.017 |
Stras | +3.593 |
hene | +3.557 |
Spr | +3.498 |
saddle | +3.468 |
Neg logit contributions | |
Alam | -4.491 |
Antar | -4.419 |
Aman | -4.013 |
Negro | -3.927 |
Malays | -3.918 |
Token | is |
Token ID | 318 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ikes | +2.764 |
Stras | +2.473 |
hene | +2.467 |
Spr | +2.418 |
saddle | +2.393 |
Neg logit contributions | |
Alam | -2.983 |
Antar | -2.932 |
Aman | -2.668 |
Negro | -2.611 |
Jama | -2.595 |
Token | the |
Token ID | 262 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
ikes | +1.469 |
Stras | +1.325 |
hene | +1.321 |
Spr | +1.304 |
Stage | +1.278 |
Neg logit contributions | |
Alam | -1.417 |
Antar | -1.376 |
Aman | -1.256 |
Negro | -1.229 |
Malays | -1.217 |
Token | argument |
Token ID | 4578 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ikes | +2.158 |
Stras | +1.953 |
hene | +1.942 |
Spr | +1.917 |
saddle | +1.883 |
Neg logit contributions | |
Alam | -2.171 |
Antar | -2.109 |
Aman | -1.927 |
Negro | -1.885 |
Malays | -1.873 |
Token | for |
Token ID | 329 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
Alam | +1.024 |
Antar | +0.986 |
Aman | +0.896 |
Negro | +0.876 |
Jama | +0.868 |
Neg logit contributions | |
ikes | -1.303 |
hene | -1.189 |
Stras | -1.184 |
Spr | -1.171 |
Stage | -1.152 |
Token | a |
Token ID | 257 |
Feature activation | +7.82e+00 |
Pos logit contributions | |
ikes | +4.375 |
Stras | +3.948 |
Spr | +3.881 |
hene | +3.834 |
saddle | +3.806 |
Neg logit contributions | |
Alam | -4.632 |
Antar | -4.532 |
Aman | -4.134 |
Malays | -4.038 |
Negro | -4.020 |
Token | " |
Token ID | 366 |
Feature activation | +8.45e+00 |
Pos logit contributions | |
ikes | +5.270 |
Stras | +4.771 |
Spr | +4.654 |
hene | +4.629 |
saddle | +4.621 |
Neg logit contributions | |
Alam | -7.034 |
Antar | -6.910 |
Aman | -6.366 |
Malays | -6.292 |
Jama | -6.177 |
Token | : |
Token ID | 25 |
Feature activation | +6.33e+00 |
Pos logit contributions | |
ikes | +5.599 |
hene | +4.923 |
Spr | +4.895 |
Stras | +4.855 |
Stage | +4.740 |
Neg logit contributions | |
Alam | -7.821 |
Antar | -7.693 |
Aman | -7.149 |
Jama | -6.985 |
Malays | -6.966 |
Token | set |
Token ID | 2617 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
ikes | +4.846 |
hene | +4.338 |
Spr | +4.274 |
Stras | +4.257 |
Stage | +4.180 |
Neg logit contributions | |
Alam | -5.329 |
Antar | -5.285 |
Aman | -4.812 |
Jama | -4.700 |
Malays | -4.691 |
Token | " |
Token ID | 1 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
ikes | +3.259 |
hene | +2.854 |
Stras | +2.829 |
Spr | +2.827 |
Stage | +2.749 |
Neg logit contributions | |
Alam | -4.849 |
Antar | -4.841 |
Aman | -4.429 |
Malays | -4.315 |
Negro | -4.298 |
Token | command |
Token ID | 3141 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
ikes | +0.803 |
Stras | +0.660 |
hene | +0.650 |
Spr | +0.633 |
saddle | +0.611 |
Neg logit contributions | |
Alam | -2.315 |
Antar | -2.278 |
Aman | -2.140 |
Negro | -2.107 |
Malays | -2.103 |
Token | Dec |
Token ID | 4280 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ikes | +1.390 |
Stras | +1.290 |
hene | +1.277 |
Spr | +1.260 |
Stage | +1.246 |
Neg logit contributions | |
Alam | -0.880 |
Antar | -0.848 |
Aman | -0.758 |
Negro | -0.732 |
Malays | -0.730 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ikes | +1.251 |
hene | +1.107 |
Stras | +1.107 |
Spr | +1.085 |
Stage | +1.065 |
Neg logit contributions | |
Alam | -1.596 |
Antar | -1.569 |
Aman | -1.435 |
Negro | -1.409 |
Malays | -1.401 |
Token | 27 |
Token ID | 2681 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ikes | +0.813 |
Stras | +0.730 |
hene | +0.723 |
Spr | +0.715 |
Stage | +0.700 |
Neg logit contributions | |
Alam | -0.974 |
Antar | -0.949 |
Aman | -0.874 |
Negro | -0.855 |
negro | -0.848 |
Token | , |
Token ID | 11 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
ikes | +1.676 |
Stras | +1.495 |
hene | +1.492 |
Spr | +1.478 |
Stage | +1.444 |
Neg logit contributions | |
Alam | -1.978 |
Antar | -1.946 |
Aman | -1.776 |
Negro | -1.739 |
Jama | -1.725 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
Alam | +0.579 |
Antar | +0.559 |
Aman | +0.505 |
Negro | +0.492 |
Jama | +0.485 |
Neg logit contributions | |
ikes | -0.776 |
Stras | -0.709 |
hene | -0.706 |
Spr | -0.699 |
Stage | -0.688 |
Token | ) |
Token ID | 8 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
ikes | +2.223 |
Stras | +1.992 |
hene | +1.978 |
Spr | +1.973 |
Stage | +1.932 |
Neg logit contributions | |
Alam | -2.708 |
Antar | -2.680 |
Aman | -2.429 |
Negro | -2.382 |
Malays | -2.375 |
Token |
|
Token ID | 198 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
ikes | +4.269 |
Spr | +3.768 |
Stras | +3.738 |
Stage | +3.689 |
hene | +3.617 |
Neg logit contributions | |
Antar | -8.123 |
Alam | -7.905 |
negro | -7.312 |
Aman | -7.249 |
Malays | -7.197 |
Token |
|
Token ID | 198 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
ikes | +2.184 |
Stras | +1.923 |
hene | +1.897 |
Spr | +1.896 |
Stage | +1.855 |
Neg logit contributions | |
Alam | -3.358 |
Antar | -3.333 |
Aman | -3.053 |
Negro | -2.996 |
negro | -2.992 |
Token | A |
Token ID | 32 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ikes | +2.229 |
Spr | +1.974 |
hene | +1.945 |
Stras | +1.943 |
Stage | +1.927 |
Neg logit contributions | |
Alam | -3.267 |
Antar | -3.219 |
Aman | -2.951 |
Negro | -2.889 |
negro | -2.882 |
Token | 24 |
Token ID | 1987 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Alam | +0.085 |
Antar | +0.083 |
Aman | +0.076 |
Negro | +0.075 |
Jama | +0.074 |
Neg logit contributions | |
ikes | -0.083 |
Stras | -0.074 |
hene | -0.074 |
Spr | -0.074 |
Stage | -0.072 |
Token | - |
Token ID | 12 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Alam | +1.123 |
Antar | +1.069 |
Aman | +1.005 |
Negro | +0.993 |
Jama | +0.976 |
Neg logit contributions | |
ikes | -1.046 |
Stras | -0.942 |
hene | -0.937 |
Spr | -0.925 |
saddle | -0.903 |
Token | years |
Token ID | 812 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
Alam | +0.368 |
Antar | +0.355 |
Aman | +0.322 |
Negro | +0.314 |
Jama | +0.310 |
Neg logit contributions | |
ikes | -0.494 |
hene | -0.449 |
Stras | -0.449 |
Spr | -0.446 |
Stage | -0.439 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Alam | +0.550 |
Antar | +0.533 |
Aman | +0.493 |
Negro | +0.483 |
Jama | +0.479 |
Neg logit contributions | |
ikes | -0.483 |
Stras | -0.431 |
hene | -0.430 |
Spr | -0.425 |
Stage | -0.416 |
Token | The |
Token ID | 383 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
Alam | +1.136 |
Antar | +1.100 |
Aman | +1.026 |
Negro | +1.001 |
Jama | +0.992 |
Neg logit contributions | |
ikes | -0.991 |
hene | -0.878 |
Stras | -0.868 |
Spr | -0.858 |
saddle | -0.848 |
Token | few |
Token ID | 1178 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
ikes | +0.650 |
Stras | +0.583 |
hene | +0.579 |
Spr | +0.572 |
Stage | +0.560 |
Neg logit contributions | |
Alam | -0.716 |
Antar | -0.695 |
Aman | -0.640 |
Negro | -0.628 |
Jama | -0.621 |
Token | in |
Token ID | 287 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Alam | +0.576 |
Antar | +0.558 |
Aman | +0.514 |
Negro | +0.505 |
Jama | +0.499 |
Neg logit contributions | |
ikes | -0.554 |
Stras | -0.497 |
hene | -0.496 |
Spr | -0.491 |
Stage | -0.482 |
Token | - |
Token ID | 12 |
Feature activation | +7.72e+00 |
Pos logit contributions | |
Alam | +0.084 |
Antar | +0.081 |
Aman | +0.074 |
Negro | +0.072 |
Jama | +0.071 |
Neg logit contributions | |
ikes | -0.096 |
hene | -0.087 |
Stras | -0.087 |
Spr | -0.086 |
Stage | -0.084 |
Token | depth |
Token ID | 18053 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ikes | +4.751 |
Stras | +4.231 |
Spr | +4.220 |
hene | +4.194 |
saddle | +4.045 |
Neg logit contributions | |
Alam | -7.460 |
Antar | -7.377 |
Aman | -6.789 |
Jama | -6.697 |
Malays | -6.696 |
Token | stories |
Token ID | 3923 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
ikes | +1.291 |
Stras | +1.158 |
hene | +1.146 |
Spr | +1.130 |
saddle | +1.109 |
Neg logit contributions | |
Alam | -1.441 |
Antar | -1.399 |
Aman | -1.289 |
Negro | -1.262 |
Jama | -1.248 |
Token | about |
Token ID | 546 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Alam | +0.439 |
Antar | +0.425 |
Aman | +0.389 |
Negro | +0.380 |
Jama | +0.376 |
Neg logit contributions | |
ikes | -0.477 |
Stras | -0.429 |
hene | -0.429 |
Spr | -0.424 |
Stage | -0.417 |
Token | her |
Token ID | 607 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Alam | +0.241 |
Antar | +0.233 |
Aman | +0.214 |
Negro | +0.209 |
Jama | +0.207 |
Neg logit contributions | |
ikes | -0.254 |
hene | -0.230 |
Stras | -0.228 |
Spr | -0.227 |
Stage | -0.222 |
Token | getting |
Token ID | 1972 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
Alam | +0.389 |
Antar | +0.376 |
Aman | +0.345 |
Negro | +0.338 |
Jama | +0.334 |
Neg logit contributions | |
ikes | -0.407 |
Stras | -0.367 |
hene | -0.366 |
Spr | -0.362 |
Stage | -0.356 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Alam | +3.087 |
Antar | +2.965 |
Negro | +2.748 |
Aman | +2.739 |
Jama | +2.704 |
Neg logit contributions | |
ikes | -3.136 |
hene | -2.861 |
Stras | -2.837 |
Spr | -2.811 |
Stage | -2.749 |
Token | - |
Token ID | 532 |
Feature activation | +8.55e+00 |
Pos logit contributions | |
Alam | +1.558 |
Antar | +1.500 |
Aman | +1.384 |
Negro | +1.358 |
Jama | +1.342 |
Neg logit contributions | |
ikes | -1.625 |
hene | -1.464 |
Stras | -1.449 |
Spr | -1.431 |
saddle | -1.410 |
Token | July |
Token ID | 2901 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
ikes | +5.505 |
Stras | +5.058 |
Spr | +4.932 |
hene | +4.904 |
SPR | +4.802 |
Neg logit contributions | |
Antar | -8.073 |
Alam | -7.844 |
Aman | -7.096 |
negro | -7.037 |
Negro | -6.935 |
Token | 6 |
Token ID | 718 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
ikes | +0.534 |
Stras | +0.475 |
hene | +0.475 |
Spr | +0.468 |
Stage | +0.458 |
Neg logit contributions | |
Alam | -0.629 |
Antar | -0.608 |
Aman | -0.565 |
Negro | -0.555 |
Jama | -0.548 |
Token | , |
Token ID | 11 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
ikes | +3.353 |
Spr | +3.001 |
Stras | +2.998 |
hene | +2.967 |
Stage | +2.929 |
Neg logit contributions | |
Antar | -4.455 |
Alam | -4.380 |
Aman | -3.953 |
negro | -3.891 |
Malays | -3.868 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +7.71e+00 |
Pos logit contributions | |
ikes | +4.939 |
Spr | +4.615 |
Stras | +4.595 |
hene | +4.495 |
SPR | +4.451 |
Neg logit contributions | |
Antar | -5.300 |
Alam | -5.197 |
Aman | -4.570 |
Malays | -4.539 |
negro | -4.528 |
Token | R |
Token ID | 49 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ikes | +4.205 |
Spr | +3.820 |
Stage | +3.764 |
Jesus | +3.634 |
Rock | +3.604 |
Neg logit contributions | |
Antar | -8.144 |
Alam | -8.079 |
Aman | -7.437 |
negro | -7.241 |
Malays | -7.211 |
Token | iff |
Token ID | 733 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
ikes | +1.343 |
hene | +1.205 |
Stras | +1.198 |
Spr | +1.189 |
Stage | +1.169 |
Neg logit contributions | |
Alam | -1.320 |
Antar | -1.293 |
Aman | -1.178 |
Negro | -1.147 |
Jama | -1.136 |
Token | Tra |
Token ID | 15721 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ikes | +0.445 |
Stras | +0.383 |
hene | +0.381 |
Spr | +0.372 |
saddle | +0.361 |
Neg logit contributions | |
Alam | -0.818 |
Antar | -0.795 |
Aman | -0.748 |
Negro | -0.739 |
Jama | -0.731 |
Token | x |
Token ID | 87 |
Feature activation | +6.88e+00 |
Pos logit contributions | |
Alam | +0.730 |
Antar | +0.662 |
Aman | +0.611 |
Negro | +0.601 |
Malays | +0.580 |
Neg logit contributions | |
ikes | -1.254 |
Stras | -1.166 |
hene | -1.155 |
Spr | -1.142 |
saddle | -1.133 |
Token |
|
Token ID | 198 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
ikes | +4.206 |
Spr | +3.620 |
Stras | +3.600 |
hene | +3.559 |
Stage | +3.546 |
Neg logit contributions | |
Alam | -6.606 |
Antar | -6.498 |
Aman | -5.997 |
Malays | -5.917 |
negro | -5.884 |
Token | June |
Token ID | 2795 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
ikes | +0.309 |
Stras | +0.282 |
hene | +0.280 |
Spr | +0.277 |
Stage | +0.272 |
Neg logit contributions | |
Alam | -0.267 |
Antar | -0.259 |
Aman | -0.235 |
Negro | -0.229 |
Jama | -0.227 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
Alam | +0.017 |
Antar | +0.017 |
Aman | +0.015 |
Negro | +0.015 |
Jama | +0.015 |
Neg logit contributions | |
ikes | -0.020 |
Stras | -0.018 |
hene | -0.018 |
Spr | -0.018 |
Stage | -0.018 |
Token | Germany |
Token ID | 4486 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ikes | +0.921 |
Stras | +0.839 |
hene | +0.838 |
Spr | +0.830 |
Stage | +0.816 |
Neg logit contributions | |
Alam | -0.683 |
Antar | -0.658 |
Aman | -0.595 |
Negro | -0.580 |
Jama | -0.573 |
Token | 247 |
Token ID | 30179 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
ikes | +2.166 |
Stras | +1.972 |
hene | +1.920 |
Spr | +1.919 |
Stage | +1.866 |
Neg logit contributions | |
Alam | -2.520 |
Antar | -2.466 |
Aman | -2.250 |
Negro | -2.210 |
negro | -2.202 |
Token | 34 |
Token ID | 2682 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ikes | +3.543 |
Stras | +3.169 |
Spr | +3.097 |
SPR | +2.996 |
hene | +2.984 |
Neg logit contributions | |
Alam | -4.885 |
Antar | -4.831 |
Aman | -4.379 |
negro | -4.359 |
Negro | -4.326 |
Token | Posts |
Token ID | 12043 |
Feature activation | +7.68e+00 |
Pos logit contributions | |
ikes | +0.546 |
Stras | +0.433 |
hene | +0.425 |
Spr | +0.418 |
Stage | +0.398 |
Neg logit contributions | |
Alam | -1.763 |
Antar | -1.734 |
Aman | -1.634 |
Negro | -1.614 |
Jama | -1.603 |
Token | # |
Token ID | 1303 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
ikes | +5.601 |
Stras | +5.081 |
hene | +4.984 |
Spr | +4.934 |
Stage | +4.838 |
Neg logit contributions | |
Alam | -6.529 |
Antar | -6.397 |
Aman | -5.822 |
Malays | -5.639 |
Negro | -5.631 |
Token | 20 |
Token ID | 1238 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
ikes | +2.993 |
Spr | +2.706 |
hene | +2.685 |
Stage | +2.675 |
Stras | +2.661 |
Neg logit contributions | |
Antar | -2.908 |
Alam | -2.897 |
Aman | -2.542 |
Jama | -2.485 |
Malays | -2.481 |
Token | Nice |
Token ID | 18460 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Alam | +2.565 |
Antar | +2.475 |
Aman | +2.303 |
Negro | +2.247 |
Jama | +2.226 |
Neg logit contributions | |
ikes | -2.451 |
hene | -2.207 |
Stras | -2.187 |
Spr | -2.173 |
Stage | -2.126 |
Token | , |
Token ID | 11 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ikes | +1.044 |
Stras | +0.939 |
hene | +0.933 |
Spr | +0.924 |
Stage | +0.906 |
Neg logit contributions | |
Alam | -1.071 |
Antar | -1.038 |
Aman | -0.953 |
Negro | -0.934 |
Jama | -0.923 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
ikes | +0.441 |
Stras | +0.396 |
hene | +0.394 |
Spr | +0.390 |
Stage | +0.382 |
Neg logit contributions | |
Alam | -0.453 |
Antar | -0.439 |
Aman | -0.404 |
Negro | -0.396 |
Jama | -0.391 |
Token | aj |
Token ID | 1228 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Alam | +1.027 |
Antar | +0.996 |
Aman | +0.921 |
Negro | +0.903 |
Jama | +0.894 |
Neg logit contributions | |
ikes | -0.887 |
Stras | -0.795 |
hene | -0.790 |
Spr | -0.782 |
Stage | -0.766 |
Token | s |
Token ID | 82 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ikes | +0.099 |
hene | +0.089 |
Stras | +0.089 |
Spr | +0.087 |
Stage | +0.085 |
Neg logit contributions | |
Alam | -0.111 |
Antar | -0.108 |
Aman | -0.100 |
Negro | -0.098 |
Jama | -0.097 |
Token | 41 |
Token ID | 6073 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
ikes | +1.100 |
hene | +0.991 |
Stras | +0.983 |
Spr | +0.969 |
Stage | +0.948 |
Neg logit contributions | |
Alam | -1.114 |
Antar | -1.085 |
Aman | -0.997 |
Negro | -0.980 |
Malays | -0.968 |
Token | ), |
Token ID | 828 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ikes | +1.638 |
Stras | +1.435 |
hene | +1.423 |
Spr | +1.402 |
saddle | +1.360 |
Neg logit contributions | |
Alam | -2.559 |
Antar | -2.504 |
Aman | -2.327 |
Negro | -2.297 |
Malays | -2.274 |
Token | K |
Token ID | 509 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ikes | +1.087 |
Stras | +0.991 |
hene | +0.982 |
Spr | +0.972 |
Stage | +0.952 |
Neg logit contributions | |
Alam | -0.993 |
Antar | -0.966 |
Aman | -0.877 |
Negro | -0.861 |
negro | -0.853 |
Token | ond |
Token ID | 623 |
Feature activation | +7.67e+00 |
Pos logit contributions | |
Alam | +1.764 |
Antar | +1.708 |
Aman | +1.583 |
Negro | +1.547 |
Jama | +1.533 |
Neg logit contributions | |
ikes | -1.545 |
Stras | -1.381 |
hene | -1.376 |
Spr | -1.368 |
Stage | -1.339 |
Token | rl |
Token ID | 45895 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ikes | +5.409 |
hene | +4.824 |
Spr | +4.674 |
Stras | +4.663 |
Stage | +4.544 |
Neg logit contributions | |
Alam | -6.749 |
Antar | -6.748 |
Aman | -6.149 |
Malays | -6.098 |
Negro | -6.096 |
Token | í |
Token ID | 8836 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ikes | +1.560 |
hene | +1.336 |
Stras | +1.316 |
Spr | +1.310 |
Stage | +1.262 |
Neg logit contributions | |
Alam | -2.588 |
Antar | -2.533 |
Aman | -2.361 |
Negro | -2.333 |
Malays | -2.325 |
Token | k |
Token ID | 74 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
ikes | +1.308 |
hene | +1.167 |
Stras | +1.167 |
Spr | +1.150 |
Stage | +1.124 |
Neg logit contributions | |
Alam | -1.385 |
Antar | -1.352 |
Aman | -1.235 |
Negro | -1.219 |
Malays | -1.201 |
Token | , |
Token ID | 11 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
ikes | +0.654 |
hene | +0.586 |
Stras | +0.585 |
Spr | +0.578 |
Stage | +0.565 |
Neg logit contributions | |
Alam | -0.698 |
Antar | -0.679 |
Aman | -0.624 |
Negro | -0.613 |
Malays | -0.605 |
Token | � |
Token ID | 25370 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
ikes | +0.647 |
Stras | +0.589 |
hene | +0.585 |
Spr | +0.578 |
Stage | +0.566 |
Neg logit contributions | |
Alam | -0.589 |
Antar | -0.572 |
Aman | -0.519 |
Negro | -0.510 |
Malays | -0.504 |
Token | comment |
Token ID | 2912 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Alam | +1.369 |
Antar | +1.317 |
Aman | +1.212 |
Negro | +1.178 |
Jama | +1.169 |
Neg logit contributions | |
ikes | -1.513 |
hene | -1.381 |
Stras | -1.373 |
Spr | -1.352 |
Stage | -1.332 |
Token | here |
Token ID | 994 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ikes | +1.570 |
Stras | +1.388 |
hene | +1.383 |
Spr | +1.359 |
saddle | +1.321 |
Neg logit contributions | |
Alam | -2.068 |
Antar | -2.035 |
Aman | -1.866 |
Negro | -1.849 |
negro | -1.843 |
Token | Ver |
Token ID | 4643 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ikes | +1.569 |
Stras | +1.413 |
hene | +1.409 |
Spr | +1.392 |
Stage | +1.365 |
Neg logit contributions | |
Alam | -1.536 |
Antar | -1.489 |
Aman | -1.364 |
Negro | -1.337 |
Jama | -1.321 |
Token | ification |
Token ID | 2649 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ikes | +1.309 |
Stras | +1.178 |
hene | +1.166 |
Spr | +1.148 |
saddle | +1.121 |
Neg logit contributions | |
Alam | -1.618 |
Antar | -1.560 |
Aman | -1.456 |
Negro | -1.422 |
Jama | -1.410 |
Token | Send |
Token ID | 16290 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Alam | +0.608 |
Antar | +0.576 |
Aman | +0.550 |
Negro | +0.540 |
Jama | +0.539 |
Neg logit contributions | |
ikes | -0.405 |
Stras | -0.355 |
Spr | -0.351 |
hene | -0.346 |
EStreamFrame | -0.345 |
Token | Email |
Token ID | 9570 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
ikes | +0.452 |
Stras | +0.393 |
hene | +0.389 |
Spr | +0.387 |
Stage | +0.373 |
Neg logit contributions | |
Alam | -0.688 |
Antar | -0.661 |
Aman | -0.627 |
Jama | -0.612 |
Negro | -0.607 |
Token | Cancel |
Token ID | 27910 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
ikes | +4.906 |
hene | +4.335 |
Stras | +4.239 |
Spr | +4.187 |
Stage | +4.186 |
Neg logit contributions | |
Alam | -7.338 |
Antar | -7.209 |
Negro | -6.607 |
Aman | -6.570 |
negro | -6.547 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ikes | +2.378 |
Stras | +2.086 |
hene | +2.065 |
Spr | +2.037 |
Stage | +1.989 |
Neg logit contributions | |
Alam | -3.532 |
Antar | -3.453 |
Aman | -3.211 |
Negro | -3.159 |
negro | -3.131 |
Token |
|
Token ID | 198 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
ikes | +0.737 |
Stras | +0.648 |
hene | +0.648 |
Spr | +0.635 |
saddle | +0.621 |
Neg logit contributions | |
Alam | -1.010 |
Antar | -0.974 |
Aman | -0.914 |
Negro | -0.899 |
Jama | -0.890 |
Token | Brown |
Token ID | 20644 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ikes | +0.375 |
Stras | +0.332 |
hene | +0.330 |
Spr | +0.323 |
saddle | +0.318 |
Neg logit contributions | |
Alam | -0.487 |
Antar | -0.472 |
Aman | -0.440 |
Negro | -0.432 |
Jama | -0.428 |
Token | - |
Token ID | 12 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Alam | +1.466 |
Antar | +1.406 |
Aman | +1.292 |
Negro | +1.262 |
Jama | +1.254 |
Neg logit contributions | |
ikes | -1.554 |
Stras | -1.407 |
hene | -1.405 |
Spr | -1.385 |
Stage | -1.362 |
Token | oen |
Token ID | 6571 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ikes | +0.155 |
Stras | +0.139 |
hene | +0.138 |
Spr | +0.137 |
Stage | +0.134 |
Neg logit contributions | |
Alam | -0.178 |
Antar | -0.172 |
Aman | -0.159 |
Negro | -0.156 |
Jama | -0.155 |
Token | hard |
Token ID | 10424 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
ikes | +1.471 |
hene | +1.302 |
Stras | +1.297 |
Spr | +1.270 |
Stage | +1.240 |
Neg logit contributions | |
Alam | -1.901 |
Antar | -1.855 |
Aman | -1.718 |
Negro | -1.687 |
Jama | -1.679 |
Token | — |
Token ID | 851 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
ikes | +0.560 |
Stras | +0.503 |
hene | +0.502 |
Spr | +0.496 |
Stage | +0.486 |
Neg logit contributions | |
Alam | -0.563 |
Antar | -0.546 |
Aman | -0.501 |
Negro | -0.491 |
Jama | -0.485 |
Token | were |
Token ID | 547 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Alam | +1.911 |
Antar | +1.847 |
Aman | +1.686 |
Negro | +1.655 |
Jama | +1.633 |
Neg logit contributions | |
ikes | -2.132 |
Stras | -1.935 |
hene | -1.924 |
Spr | -1.914 |
Stage | -1.877 |
Token | in |
Token ID | 287 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
Alam | +0.335 |
Antar | +0.324 |
Aman | +0.297 |
Negro | +0.291 |
Jama | +0.288 |
Neg logit contributions | |
ikes | -0.347 |
Stras | -0.313 |
hene | -0.312 |
Spr | -0.308 |
Stage | -0.302 |
Token | good |
Token ID | 922 |
Feature activation | +7.64e+00 |
Pos logit contributions | |
ikes | +0.347 |
Stras | +0.314 |
hene | +0.313 |
Spr | +0.309 |
Stage | +0.304 |
Neg logit contributions | |
Alam | -0.320 |
Antar | -0.310 |
Aman | -0.283 |
Negro | -0.277 |
Jama | -0.274 |
Token | condition |
Token ID | 4006 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ikes | +6.219 |
Stras | +5.855 |
saddle | +5.802 |
Spr | +5.655 |
hene | +5.601 |
Neg logit contributions | |
Alam | -5.517 |
Antar | -5.504 |
Malays | -4.849 |
Aman | -4.796 |
adem | -4.727 |
Token | after |
Token ID | 706 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
ikes | +0.463 |
Stras | +0.413 |
hene | +0.412 |
Spr | +0.406 |
Stage | +0.398 |
Neg logit contributions | |
Alam | -0.533 |
Antar | -0.519 |
Aman | -0.479 |
Negro | -0.469 |
Jama | -0.464 |
Token | being |
Token ID | 852 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ikes | +1.565 |
Stras | +1.418 |
hene | +1.402 |
Spr | +1.389 |
saddle | +1.363 |
Neg logit contributions | |
Alam | -1.560 |
Antar | -1.515 |
Aman | -1.391 |
Negro | -1.360 |
negro | -1.344 |
Token | shot |
Token ID | 2823 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
ikes | +1.608 |
Stras | +1.464 |
hene | +1.455 |
Spr | +1.431 |
saddle | +1.422 |
Neg logit contributions | |
Alam | -1.597 |
Antar | -1.556 |
Aman | -1.420 |
Negro | -1.378 |
Malays | -1.374 |
Token | and |
Token ID | 290 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
Alam | +0.650 |
Antar | +0.630 |
Aman | +0.579 |
Negro | +0.567 |
Jama | +0.562 |
Neg logit contributions | |
ikes | -0.632 |
Stras | -0.567 |
hene | -0.567 |
Spr | -0.560 |
Stage | -0.549 |
Token | . |
Token ID | 13 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
ikes | +0.060 |
Stras | +0.053 |
hene | +0.053 |
Spr | +0.053 |
Stage | +0.052 |
Neg logit contributions | |
Alam | -0.064 |
Antar | -0.062 |
Aman | -0.057 |
Negro | -0.056 |
Jama | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Alam | +0.590 |
Antar | +0.573 |
Aman | +0.531 |
Negro | +0.519 |
Jama | +0.515 |
Neg logit contributions | |
ikes | -0.514 |
hene | -0.458 |
Stras | -0.455 |
Spr | -0.448 |
saddle | -0.442 |
Token |
|
Token ID | 198 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
ikes | +0.148 |
hene | +0.131 |
Stras | +0.131 |
Spr | +0.128 |
saddle | +0.126 |
Neg logit contributions | |
Alam | -0.194 |
Antar | -0.184 |
Aman | -0.175 |
Negro | -0.172 |
Jama | -0.170 |
Token | Th |
Token ID | 817 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
ikes | +0.507 |
Stras | +0.448 |
hene | +0.447 |
Spr | +0.440 |
Stage | +0.430 |
Neg logit contributions | |
Alam | -0.669 |
Antar | -0.651 |
Aman | -0.604 |
Negro | -0.594 |
Jama | -0.588 |
Token | ad |
Token ID | 324 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
ikes | +2.195 |
hene | +1.970 |
Stras | +1.964 |
Spr | +1.932 |
Stage | +1.909 |
Neg logit contributions | |
Alam | -2.026 |
Antar | -1.969 |
Aman | -1.796 |
Negro | -1.764 |
negro | -1.744 |
Token | ik |
Token ID | 1134 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
ikes | +0.067 |
Stras | +0.060 |
hene | +0.060 |
Spr | +0.059 |
Stage | +0.058 |
Neg logit contributions | |
Alam | -0.073 |
Antar | -0.071 |
Aman | -0.066 |
Negro | -0.064 |
Jama | -0.064 |
Token | omb |
Token ID | 2381 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
Alam | +7.567 |
Antar | +7.530 |
Negro | +6.584 |
Aman | +6.556 |
Jama | +6.470 |
Neg logit contributions | |
ikes | -8.720 |
Stras | -8.549 |
Spr | -8.364 |
SPR | -8.070 |
saddle | -8.038 |
Token | u |
Token ID | 84 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Alam | +0.705 |
Antar | +0.686 |
Aman | +0.637 |
Negro | +0.626 |
Jama | +0.621 |
Neg logit contributions | |
ikes | -0.504 |
Stras | -0.447 |
hene | -0.443 |
Spr | -0.439 |
Stage | -0.428 |
Token | Pillar |
Token ID | 39179 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
Alam | +0.409 |
Antar | +0.396 |
Aman | +0.364 |
Negro | +0.357 |
Jama | +0.353 |
Neg logit contributions | |
ikes | -0.399 |
Stras | -0.359 |
hene | -0.358 |
Spr | -0.354 |
Stage | -0.347 |
Token | Hall |
Token ID | 4789 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ikes | +0.042 |
Stras | +0.037 |
hene | +0.037 |
Spr | +0.037 |
Stage | +0.036 |
Neg logit contributions | |
Alam | -0.047 |
Antar | -0.045 |
Aman | -0.042 |
Negro | -0.041 |
Jama | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Alam | +1.442 |
Antar | +1.397 |
Aman | +1.295 |
Negro | +1.268 |
Jama | +1.254 |
Neg logit contributions | |
ikes | -1.238 |
Stras | -1.108 |
hene | -1.102 |
Spr | -1.093 |
saddle | -1.065 |
Token | Va |
Token ID | 17668 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ikes | +0.338 |
Stras | +0.308 |
hene | +0.307 |
Spr | +0.304 |
Stage | +0.298 |
Neg logit contributions | |
Alam | -0.261 |
Antar | -0.251 |
Aman | -0.228 |
Negro | -0.222 |
Jama | -0.219 |
Token | ik |
Token ID | 1134 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
Alam | +1.008 |
Antar | +0.975 |
Aman | +0.912 |
Negro | +0.892 |
Jama | +0.886 |
Neg logit contributions | |
ikes | -0.712 |
Stras | -0.637 |
hene | -0.630 |
Spr | -0.625 |
Stage | -0.609 |
Token | unta |
Token ID | 44424 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
Alam | +3.094 |
Antar | +2.984 |
Aman | +2.754 |
Negro | +2.693 |
Jama | +2.667 |
Neg logit contributions | |
ikes | -2.819 |
Stras | -2.553 |
Spr | -2.506 |
hene | -2.501 |
EStreamFrame | -2.451 |
Token | Th |
Token ID | 536 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
Alam | +0.746 |
Antar | +0.723 |
Aman | +0.666 |
Negro | +0.652 |
Jama | +0.645 |
Neg logit contributions | |
ikes | -0.701 |
Stras | -0.629 |
hene | -0.625 |
Spr | -0.619 |
Stage | -0.606 |
Token | ad |
Token ID | 324 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
Alam | +0.761 |
Antar | +0.735 |
Aman | +0.674 |
Negro | +0.659 |
Jama | +0.652 |
Neg logit contributions | |
ikes | -0.790 |
Stras | -0.718 |
hene | -0.711 |
Spr | -0.706 |
Stage | -0.691 |
Token | ik |
Token ID | 1134 |
Feature activation | -9.98e+00 |
Pos logit contributions | |
Alam | +0.784 |
Antar | +0.760 |
Aman | +0.700 |
Negro | +0.686 |
Jama | +0.680 |
Neg logit contributions | |
ikes | -0.723 |
Stras | -0.651 |
hene | -0.647 |
Spr | -0.640 |
Stage | -0.627 |
Token | omb |
Token ID | 2381 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Alam | +7.480 |
Antar | +7.448 |
Negro | +6.548 |
Aman | +6.538 |
Jama | +6.460 |
Neg logit contributions | |
ikes | -7.796 |
Stras | -7.528 |
Spr | -7.367 |
saddle | -7.105 |
SPR | -7.096 |
Token | u |
Token ID | 84 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Alam | +1.226 |
Antar | +1.192 |
Aman | +1.107 |
Negro | +1.087 |
Jama | +1.078 |
Neg logit contributions | |
ikes | -0.885 |
Stras | -0.785 |
hene | -0.776 |
Spr | -0.770 |
Stage | -0.751 |
Token |
|
Token ID | 198 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
Alam | +0.131 |
Antar | +0.127 |
Aman | +0.117 |
Negro | +0.115 |
Jama | +0.113 |
Neg logit contributions | |
ikes | -0.120 |
Stras | -0.107 |
hene | -0.107 |
Spr | -0.105 |
Stage | -0.103 |
Token |
|
Token ID | 198 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
Alam | +0.053 |
Antar | +0.050 |
Aman | +0.048 |
Negro | +0.047 |
Jama | +0.046 |
Neg logit contributions | |
ikes | -0.041 |
hene | -0.036 |
Stras | -0.036 |
Spr | -0.035 |
saddle | -0.035 |
Token | Sound |
Token ID | 21369 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
ikes | +0.052 |
Stras | +0.046 |
hene | +0.046 |
Spr | +0.045 |
saddle | +0.044 |
Neg logit contributions | |
Alam | -0.064 |
Antar | -0.062 |
Aman | -0.057 |
Negro | -0.056 |
Jama | -0.056 |
Token | t |
Token ID | 83 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
Alam | +0.899 |
Antar | +0.862 |
Aman | +0.783 |
Negro | +0.762 |
Jama | +0.752 |
Neg logit contributions | |
ikes | -1.172 |
Stras | -1.072 |
hene | -1.066 |
Spr | -1.055 |
Stage | -1.039 |
Token | ... |
Token ID | 986 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Alam | +2.195 |
Antar | +2.125 |
Aman | +1.941 |
Negro | +1.911 |
Jama | +1.898 |
Neg logit contributions | |
ikes | -2.229 |
Stras | -1.992 |
hene | -1.990 |
Spr | -1.973 |
Stage | -1.942 |
Token | 15 |
Token ID | 1315 |
Feature activation | -8.96e+00 |
Pos logit contributions | |
Alam | +0.893 |
Antar | +0.862 |
Aman | +0.795 |
Negro | +0.777 |
Jama | +0.770 |
Neg logit contributions | |
ikes | -0.884 |
Stras | -0.798 |
hene | -0.794 |
Spr | -0.781 |
Stage | -0.773 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
Alam | +6.363 |
Antar | +6.031 |
Aman | +5.654 |
Jama | +5.616 |
Deep | +5.488 |
Neg logit contributions | |
ikes | -7.547 |
Stras | -7.082 |
hene | -6.979 |
EStreamFrame | -6.947 |
Stage | -6.815 |
Token | of |
Token ID | 286 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
Alam | +4.993 |
Antar | +4.566 |
Jama | +4.528 |
Deep | +4.394 |
Aman | +4.384 |
Neg logit contributions | |
Stras | -7.284 |
ikes | -7.279 |
hene | -7.026 |
EStreamFrame | -6.863 |
Stage | -6.729 |
Token | 15 |
Token ID | 1315 |
Feature activation | -9.25e+00 |
Pos logit contributions | |
Alam | +4.239 |
Antar | +4.022 |
Aman | +3.809 |
Negro | +3.709 |
Jama | +3.656 |
Neg logit contributions | |
ikes | -4.412 |
hene | -4.034 |
Stras | -3.990 |
Spr | -3.892 |
EStreamFrame | -3.874 |
Token | Photo |
Token ID | 5555 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Alam | +6.841 |
Antar | +6.419 |
Aman | +6.182 |
Jama | +6.082 |
negro | +5.978 |
Neg logit contributions | |
ikes | -7.588 |
hene | -7.044 |
Stras | -7.014 |
EStreamFrame | -6.832 |
Spr | -6.828 |
Token | : |
Token ID | 25 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Alam | +1.330 |
Antar | +1.273 |
Aman | +1.196 |
Negro | +1.170 |
Jama | +1.154 |
Neg logit contributions | |
ikes | -1.135 |
hene | -1.023 |
Stras | -1.023 |
Spr | -0.996 |
EStreamFrame | -0.977 |
Token | Le |
Token ID | 1004 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Alam | +1.199 |
Antar | +1.161 |
Aman | +1.075 |
Negro | +1.048 |
Jama | +1.042 |
Neg logit contributions | |
ikes | -1.134 |
hene | -1.012 |
Stras | -1.005 |
Spr | -0.997 |
Stage | -0.977 |
Token | a |
Token ID | 64 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Alam | +2.214 |
Antar | +2.153 |
Aman | +2.003 |
Negro | +1.971 |
Jama | +1.950 |
Neg logit contributions | |
ikes | -1.579 |
Stras | -1.387 |
hene | -1.379 |
Spr | -1.357 |
Stage | -1.330 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
Alam | +0.160 |
Antar | +0.156 |
Aman | +0.147 |
Negro | +0.145 |
Jama | +0.144 |
Neg logit contributions | |
ikes | -0.065 |
Stras | -0.053 |
hene | -0.053 |
Spr | -0.052 |
Stage | -0.050 |
Token | fn |
Token ID | 24714 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
Alam | +3.259 |
Antar | +3.128 |
Aman | +2.854 |
Negro | +2.787 |
Jama | +2.745 |
Neg logit contributions | |
ikes | -3.911 |
Stras | -3.552 |
hene | -3.548 |
Spr | -3.499 |
Stage | -3.437 |
Token | null |
Token ID | 9242 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Alam | +4.733 |
Antar | +4.515 |
Aman | +4.188 |
Negro | +4.057 |
negro | +4.025 |
Neg logit contributions | |
ikes | -4.934 |
Stras | -4.453 |
hene | -4.422 |
Spr | -4.409 |
Stage | -4.294 |
Token | () |
Token ID | 7499 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
Alam | +1.364 |
Antar | +1.323 |
Aman | +1.230 |
Negro | +1.205 |
Jama | +1.190 |
Neg logit contributions | |
ikes | -1.031 |
Stras | -0.918 |
hene | -0.913 |
Spr | -0.894 |
saddle | -0.873 |
Token | -> |
Token ID | 4613 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Alam | +3.599 |
Antar | +3.343 |
Aman | +3.092 |
Negro | +3.014 |
negro | +2.958 |
Neg logit contributions | |
ikes | -4.803 |
hene | -4.423 |
Stras | -4.420 |
Spr | -4.318 |
Stage | -4.264 |
Token | Atomic |
Token ID | 28976 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Alam | +1.483 |
Antar | +1.433 |
Aman | +1.290 |
Negro | +1.258 |
Jama | +1.242 |
Neg logit contributions | |
ikes | -2.075 |
Stras | -1.896 |
hene | -1.891 |
Spr | -1.873 |
Stage | -1.842 |
Token | < |
Token ID | 1279 |
Feature activation | -9.12e+00 |
Pos logit contributions | |
Alam | +2.481 |
Antar | +2.349 |
Aman | +2.084 |
Negro | +2.022 |
Jama | +1.968 |
Neg logit contributions | |
ikes | -4.453 |
Stras | -4.152 |
hene | -4.119 |
Spr | -4.042 |
saddle | -4.017 |
Token | T |
Token ID | 309 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
Alam | +5.430 |
Antar | +5.108 |
Aman | +4.565 |
Negro | +4.413 |
negro | +4.270 |
Neg logit contributions | |
ikes | -9.083 |
Stras | -8.390 |
hene | -8.372 |
Spr | -8.199 |
saddle | -8.128 |
Token | > |
Token ID | 1875 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
Alam | +3.788 |
Antar | +3.613 |
Aman | +3.370 |
Negro | +3.278 |
negro | +3.233 |
Neg logit contributions | |
ikes | -3.385 |
Stras | -3.068 |
hene | -3.048 |
Spr | -3.005 |
saddle | -2.940 |
Token | ; |
Token ID | 2162 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
Alam | +2.971 |
Antar | +2.786 |
Aman | +2.476 |
Negro | +2.404 |
negro | +2.349 |
Neg logit contributions | |
ikes | -5.515 |
Stras | -5.155 |
hene | -5.108 |
Spr | -5.056 |
Stage | -4.982 |
Token | } |
Token ID | 1782 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Alam | +4.913 |
Antar | +4.670 |
Aman | +4.332 |
Negro | +4.251 |
negro | +4.166 |
Neg logit contributions | |
ikes | -4.734 |
Stras | -4.244 |
hene | -4.217 |
Spr | -4.190 |
Stage | -4.104 |
Token |
|
Token ID | 198 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
Alam | +1.134 |
Antar | +1.097 |
Aman | +0.993 |
Negro | +0.970 |
Jama | +0.959 |
Neg logit contributions | |
ikes | -1.452 |
Stras | -1.323 |
hene | -1.320 |
Spr | -1.305 |
Stage | -1.283 |
Token | can |
Token ID | 460 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ikes | +0.169 |
Stras | +0.152 |
hene | +0.151 |
Spr | +0.149 |
saddle | +0.147 |
Neg logit contributions | |
Alam | -0.172 |
Antar | -0.167 |
Aman | -0.153 |
Negro | -0.150 |
Jama | -0.148 |
Token | � |
Token ID | 447 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Alam | +1.958 |
Antar | +1.885 |
Aman | +1.722 |
Negro | +1.692 |
Jama | +1.676 |
Neg logit contributions | |
ikes | -2.076 |
Stras | -1.868 |
hene | -1.859 |
Spr | -1.841 |
Stage | -1.818 |
Token | � |
Token ID | 247 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Alam | +1.526 |
Antar | +1.450 |
Aman | +1.318 |
Negro | +1.285 |
Malays | +1.269 |
Neg logit contributions | |
ikes | -2.191 |
Stras | -2.010 |
hene | -1.997 |
Spr | -1.972 |
Stage | -1.953 |
Token | t |
Token ID | 83 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
Alam | +0.899 |
Antar | +0.862 |
Aman | +0.783 |
Negro | +0.762 |
Jama | +0.752 |
Neg logit contributions | |
ikes | -1.172 |
Stras | -1.072 |
hene | -1.066 |
Spr | -1.055 |
Stage | -1.039 |
Token | ... |
Token ID | 986 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Alam | +2.195 |
Antar | +2.125 |
Aman | +1.941 |
Negro | +1.911 |
Jama | +1.898 |
Neg logit contributions | |
ikes | -2.229 |
Stras | -1.992 |
hene | -1.990 |
Spr | -1.973 |
Stage | -1.942 |
Token | 15 |
Token ID | 1315 |
Feature activation | -8.96e+00 |
Pos logit contributions | |
Alam | +0.893 |
Antar | +0.862 |
Aman | +0.795 |
Negro | +0.777 |
Jama | +0.770 |
Neg logit contributions | |
ikes | -0.884 |
Stras | -0.798 |
hene | -0.794 |
Spr | -0.781 |
Stage | -0.773 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
Alam | +6.363 |
Antar | +6.031 |
Aman | +5.654 |
Jama | +5.616 |
Deep | +5.488 |
Neg logit contributions | |
ikes | -7.547 |
Stras | -7.082 |
hene | -6.979 |
EStreamFrame | -6.947 |
Stage | -6.815 |
Token | of |
Token ID | 286 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
Alam | +4.993 |
Antar | +4.566 |
Jama | +4.528 |
Deep | +4.394 |
Aman | +4.384 |
Neg logit contributions | |
Stras | -7.284 |
ikes | -7.279 |
hene | -7.026 |
EStreamFrame | -6.863 |
Stage | -6.729 |
Token | 15 |
Token ID | 1315 |
Feature activation | -9.25e+00 |
Pos logit contributions | |
Alam | +4.239 |
Antar | +4.022 |
Aman | +3.809 |
Negro | +3.709 |
Jama | +3.656 |
Neg logit contributions | |
ikes | -4.412 |
hene | -4.034 |
Stras | -3.990 |
Spr | -3.892 |
EStreamFrame | -3.874 |
Token | Photo |
Token ID | 5555 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Alam | +6.841 |
Antar | +6.419 |
Aman | +6.182 |
Jama | +6.082 |
negro | +5.978 |
Neg logit contributions | |
ikes | -7.588 |
hene | -7.044 |
Stras | -7.014 |
EStreamFrame | -6.832 |
Spr | -6.828 |
Token | : |
Token ID | 25 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Alam | +1.330 |
Antar | +1.273 |
Aman | +1.196 |
Negro | +1.170 |
Jama | +1.154 |
Neg logit contributions | |
ikes | -1.135 |
hene | -1.023 |
Stras | -1.023 |
Spr | -0.996 |
EStreamFrame | -0.977 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Alam | +0.321 |
Antar | +0.314 |
Aman | +0.292 |
Negro | +0.287 |
Jama | +0.284 |
Neg logit contributions | |
ikes | -0.227 |
Stras | -0.199 |
hene | -0.199 |
Spr | -0.196 |
Stage | -0.191 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Alam | +0.177 |
Antar | +0.167 |
Aman | +0.160 |
Negro | +0.157 |
Jama | +0.155 |
Neg logit contributions | |
ikes | -0.138 |
Stras | -0.122 |
hene | -0.122 |
Spr | -0.119 |
saddle | -0.117 |
Token | pub |
Token ID | 12984 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
Alam | +1.238 |
Antar | +1.190 |
Aman | +1.082 |
Negro | +1.055 |
Jama | +1.040 |
Neg logit contributions | |
ikes | -1.576 |
Stras | -1.441 |
hene | -1.432 |
Spr | -1.414 |
saddle | -1.391 |
Token | struct |
Token ID | 2878 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
Alam | +2.390 |
Antar | +2.295 |
Aman | +2.088 |
Negro | +2.039 |
Jama | +2.014 |
Neg logit contributions | |
ikes | -2.978 |
Stras | -2.712 |
hene | -2.706 |
Spr | -2.674 |
Stage | -2.628 |
Token | Atomic |
Token ID | 28976 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ikes | +0.561 |
Stras | +0.513 |
hene | +0.511 |
Spr | +0.505 |
Stage | +0.498 |
Neg logit contributions | |
Alam | -0.418 |
Antar | -0.410 |
Aman | -0.368 |
Negro | -0.360 |
Malays | -0.360 |
Token | < |
Token ID | 1279 |
Feature activation | -8.69e+00 |
Pos logit contributions | |
Alam | +0.265 |
Antar | +0.256 |
Aman | +0.227 |
Negro | +0.220 |
Malays | +0.218 |
Neg logit contributions | |
ikes | -0.445 |
hene | -0.406 |
Stras | -0.406 |
Spr | -0.406 |
Stage | -0.399 |
Token | T |
Token ID | 309 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Alam | +5.597 |
Antar | +5.303 |
Aman | +4.821 |
Negro | +4.678 |
negro | +4.523 |
Neg logit contributions | |
ikes | -8.255 |
Stras | -7.574 |
hene | -7.552 |
Spr | -7.477 |
Stage | -7.356 |
Token | > |
Token ID | 1875 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
Alam | +3.152 |
Antar | +3.014 |
Aman | +2.803 |
Negro | +2.735 |
Jama | +2.691 |
Neg logit contributions | |
ikes | -2.837 |
Stras | -2.558 |
hene | -2.549 |
Spr | -2.509 |
saddle | -2.457 |
Token | { |
Token ID | 1391 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
Alam | +2.706 |
Antar | +2.527 |
Aman | +2.239 |
Negro | +2.167 |
Jama | +2.108 |
Neg logit contributions | |
ikes | -5.338 |
Stras | -4.978 |
hene | -4.967 |
Spr | -4.897 |
Stage | -4.827 |
Token | ... |
Token ID | 2644 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Alam | +3.933 |
Antar | +3.713 |
Aman | +3.364 |
Negro | +3.263 |
negro | +3.179 |
Neg logit contributions | |
ikes | -5.891 |
Stras | -5.444 |
hene | -5.414 |
Spr | -5.345 |
Stage | -5.261 |
Token | } |
Token ID | 1782 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
Alam | +1.553 |
Antar | +1.505 |
Aman | +1.368 |
Negro | +1.339 |
Jama | +1.324 |
Neg logit contributions | |
ikes | -1.821 |
Stras | -1.651 |
hene | -1.647 |
Spr | -1.628 |
Stage | -1.601 |
Token | c |
Token ID | 269 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
ikes | +0.429 |
Stras | +0.391 |
hene | +0.389 |
Spr | +0.385 |
Stage | +0.378 |
Neg logit contributions | |
Alam | -0.344 |
Antar | -0.335 |
Aman | -0.302 |
Negro | -0.295 |
Jama | -0.291 |
Token | v |
Token ID | 85 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Alam | +1.646 |
Antar | +1.470 |
Aman | +1.405 |
Negro | +1.393 |
Jama | +1.343 |
Neg logit contributions | |
ikes | -2.489 |
Stras | -2.312 |
hene | -2.275 |
saddle | -2.244 |
Spr | -2.225 |
Token | 2 |
Token ID | 17 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
ikes | +0.922 |
Stras | +0.817 |
hene | +0.816 |
Spr | +0.807 |
Stage | +0.789 |
Neg logit contributions | |
Alam | -1.156 |
Antar | -1.129 |
Aman | -1.041 |
Negro | -1.020 |
Jama | -1.012 |
Token | . |
Token ID | 764 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ikes | +0.767 |
Stras | +0.700 |
hene | +0.699 |
Spr | +0.691 |
Stage | +0.680 |
Neg logit contributions | |
Alam | -0.563 |
Antar | -0.540 |
Aman | -0.490 |
Negro | -0.478 |
Jama | -0.471 |
Token | Ga |
Token ID | 12822 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Alam | +1.809 |
Antar | +1.752 |
Aman | +1.603 |
Negro | +1.578 |
Jama | +1.555 |
Neg logit contributions | |
ikes | -1.901 |
Stras | -1.713 |
hene | -1.710 |
Spr | -1.690 |
Stage | -1.663 |
Token | ussian |
Token ID | 31562 |
Feature activation | -8.69e+00 |
Pos logit contributions | |
Alam | +1.733 |
Antar | +1.655 |
Aman | +1.589 |
Negro | +1.583 |
Jama | +1.551 |
Neg logit contributions | |
ikes | -0.998 |
Stras | -0.881 |
hene | -0.859 |
Spr | -0.847 |
saddle | -0.838 |
Token | Bl |
Token ID | 3629 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
Alam | +4.850 |
Negro | +4.261 |
Antar | +4.258 |
Jama | +4.016 |
Deep | +3.988 |
Neg logit contributions | |
ikes | -8.943 |
hene | -8.253 |
saddle | -8.152 |
Stras | -8.125 |
eneg | -7.800 |
Token | ur |
Token ID | 333 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Alam | +2.892 |
Antar | +2.672 |
Negro | +2.576 |
Aman | +2.548 |
adem | +2.496 |
Neg logit contributions | |
ikes | -2.622 |
Stras | -2.414 |
saddle | -2.336 |
Spr | -2.330 |
hene | -2.329 |
Token | ( |
Token ID | 357 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
Alam | +0.950 |
Antar | +0.899 |
Aman | +0.834 |
Negro | +0.818 |
Jama | +0.805 |
Neg logit contributions | |
ikes | -1.105 |
hene | -0.999 |
Stras | -0.998 |
Spr | -0.976 |
saddle | -0.964 |
Token | gray |
Token ID | 12768 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Alam | +1.902 |
Antar | +1.798 |
Negro | +1.621 |
Aman | +1.604 |
negro | +1.574 |
Neg logit contributions | |
ikes | -3.941 |
Stras | -3.642 |
hene | -3.620 |
Spr | -3.613 |
Stage | -3.611 |
Token | , |
Token ID | 837 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
ikes | +2.239 |
Stras | +2.038 |
hene | +2.036 |
Spr | +2.019 |
Stage | +1.982 |
Neg logit contributions | |
Alam | -1.741 |
Antar | -1.702 |
Aman | -1.523 |
Negro | -1.484 |
Malays | -1.471 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Alam | +1.627 |
Antar | +1.493 |
Aman | +1.446 |
Negro | +1.421 |
Jama | +1.396 |
Neg logit contributions | |
ikes | -1.592 |
Stras | -1.429 |
hene | -1.425 |
Spr | -1.394 |
saddle | -1.393 |
Token | x |
Token ID | 87 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
Alam | +1.051 |
Antar | +0.934 |
Aman | +0.880 |
Negro | +0.863 |
Jama | +0.832 |
Neg logit contributions | |
ikes | -1.892 |
Stras | -1.760 |
hene | -1.732 |
saddle | -1.718 |
Spr | -1.711 |
Token | . |
Token ID | 13 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Alam | +0.564 |
Antar | +0.525 |
Aman | +0.504 |
Negro | +0.497 |
Jama | +0.489 |
Neg logit contributions | |
ikes | -0.537 |
Stras | -0.484 |
hene | -0.481 |
Spr | -0.471 |
saddle | -0.471 |
Token | 167 |
Token ID | 21940 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ikes | +0.227 |
Stras | +0.192 |
hene | +0.190 |
saddle | +0.182 |
Spr | +0.181 |
Neg logit contributions | |
Alam | -0.560 |
Antar | -0.538 |
Aman | -0.518 |
Negro | -0.517 |
Jama | -0.512 |
Token | 101 |
Token ID | 8949 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Alam | +1.033 |
Antar | +0.993 |
Aman | +0.918 |
Negro | +0.898 |
Jama | +0.893 |
Neg logit contributions | |
ikes | -1.027 |
hene | -0.923 |
Stras | -0.915 |
Spr | -0.906 |
saddle | -0.891 |
Token | 320 |
Token ID | 19504 |
Feature activation | -8.57e+00 |
Pos logit contributions | |
Alam | +0.245 |
Antar | +0.235 |
Aman | +0.219 |
Negro | +0.213 |
Jama | +0.211 |
Neg logit contributions | |
ikes | -0.246 |
hene | -0.221 |
Stras | -0.221 |
Spr | -0.217 |
saddle | -0.214 |
Token | 6 |
Token ID | 21 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
Alam | +6.758 |
Antar | +6.454 |
Aman | +6.105 |
Negro | +5.998 |
Deep | +5.953 |
Neg logit contributions | |
ikes | -6.616 |
hene | -6.149 |
EStreamFrame | -6.073 |
Stras | -5.890 |
saddle | -5.758 |
Token | x |
Token ID | 2124 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
Alam | +0.550 |
Antar | +0.517 |
Aman | +0.473 |
Negro | +0.461 |
Jama | +0.452 |
Neg logit contributions | |
ikes | -0.836 |
hene | -0.764 |
Stras | -0.762 |
Spr | -0.752 |
Stage | -0.743 |
Token | . |
Token ID | 13 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
Alam | +4.500 |
Aman | +3.920 |
Negro | +3.881 |
Antar | +3.793 |
Jama | +3.785 |
Neg logit contributions | |
ikes | -5.326 |
hene | -4.804 |
Stras | -4.774 |
saddle | -4.725 |
EStreamFrame | -4.662 |
Token | x |
Token ID | 87 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
Alam | +2.582 |
Aman | +2.101 |
Antar | +2.083 |
Negro | +2.079 |
Deep | +1.964 |
Neg logit contributions | |
ikes | -5.311 |
Stras | -4.979 |
saddle | -4.875 |
hene | -4.866 |
SPR | -4.782 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Alam | +2.395 |
Antar | +2.160 |
Aman | +2.125 |
Negro | +2.093 |
Jama | +2.049 |
Neg logit contributions | |
ikes | -2.455 |
Stras | -2.211 |
hene | -2.205 |
saddle | -2.164 |
Spr | -2.151 |
Token | > |
Token ID | 1875 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
Alam | +2.117 |
Antar | +2.042 |
Aman | +1.894 |
Negro | +1.854 |
Jama | +1.830 |
Neg logit contributions | |
ikes | -1.797 |
Stras | -1.603 |
hene | -1.601 |
Spr | -1.576 |
Stage | -1.540 |
Token | { |
Token ID | 1391 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
Alam | +1.945 |
Antar | +1.848 |
Aman | +1.643 |
Negro | +1.604 |
Jama | +1.572 |
Neg logit contributions | |
ikes | -3.300 |
Stras | -3.052 |
hene | -3.046 |
Spr | -3.008 |
Stage | -2.960 |
Token | pub |
Token ID | 2240 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
Alam | +3.587 |
Antar | +3.443 |
Aman | +3.178 |
Negro | +3.114 |
Jama | +3.057 |
Neg logit contributions | |
ikes | -3.567 |
Stras | -3.222 |
hene | -3.205 |
Spr | -3.157 |
Stage | -3.101 |
Token | fn |
Token ID | 24714 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Alam | +3.503 |
Antar | +3.337 |
Aman | +3.052 |
Negro | +2.979 |
Jama | +2.930 |
Neg logit contributions | |
ikes | -4.264 |
hene | -3.888 |
Stras | -3.885 |
Spr | -3.817 |
Stage | -3.754 |
Token | load |
Token ID | 3440 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Alam | +1.774 |
Antar | +1.709 |
Aman | +1.575 |
Negro | +1.545 |
Jama | +1.527 |
Neg logit contributions | |
ikes | -1.711 |
Stras | -1.539 |
hene | -1.534 |
Spr | -1.516 |
Stage | -1.482 |
Token | < |
Token ID | 1279 |
Feature activation | -8.48e+00 |
Pos logit contributions | |
Alam | +1.760 |
Antar | +1.698 |
Aman | +1.568 |
Negro | +1.539 |
Jama | +1.520 |
Neg logit contributions | |
ikes | -1.598 |
Stras | -1.438 |
hene | -1.427 |
Spr | -1.389 |
saddle | -1.375 |
Token | ' |
Token ID | 705 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
Alam | +5.615 |
Antar | +5.323 |
Aman | +4.844 |
Negro | +4.774 |
negro | +4.685 |
Neg logit contributions | |
ikes | -7.722 |
Stras | -7.097 |
hene | -7.082 |
Spr | -6.942 |
EStreamFrame | -6.858 |
Token | a |
Token ID | 64 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
Alam | +5.293 |
Antar | +5.031 |
Aman | +4.758 |
Negro | +4.617 |
negro | +4.547 |
Neg logit contributions | |
ikes | -4.168 |
Stras | -3.729 |
hene | -3.667 |
Spr | -3.619 |
EStreamFrame | -3.564 |
Token | > |
Token ID | 1875 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
Alam | +2.784 |
Antar | +2.671 |
Aman | +2.436 |
Negro | +2.373 |
Jama | +2.330 |
Neg logit contributions | |
ikes | -3.457 |
Stras | -3.151 |
hene | -3.132 |
Spr | -3.090 |
Stage | -3.045 |
Token | ( |
Token ID | 357 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
Alam | +2.562 |
Antar | +2.455 |
Aman | +2.258 |
Negro | +2.204 |
Jama | +2.171 |
Neg logit contributions | |
ikes | -2.821 |
hene | -2.567 |
Stras | -2.563 |
Spr | -2.509 |
Stage | -2.464 |
Token | & |
Token ID | 1222 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
Alam | +5.075 |
Antar | +4.781 |
Aman | +4.380 |
Negro | +4.271 |
negro | +4.230 |
Neg logit contributions | |
ikes | -6.306 |
Stras | -5.806 |
hene | -5.750 |
Spr | -5.657 |
Stage | -5.529 |
Token | a |
Token ID | 64 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Alam | +2.207 |
Antar | +2.136 |
Aman | +1.994 |
Negro | +1.957 |
Jama | +1.936 |
Neg logit contributions | |
ikes | -1.515 |
Stras | -1.339 |
hene | -1.326 |
Spr | -1.303 |
saddle | -1.273 |
Token | Guard |
Token ID | 4932 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ikes | +0.137 |
Stras | +0.125 |
hene | +0.124 |
Spr | +0.124 |
Stage | +0.121 |
Neg logit contributions | |
Alam | -0.107 |
Antar | -0.104 |
Aman | -0.094 |
Malays | -0.092 |
Jama | -0.091 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ikes | +2.130 |
Spr | +1.919 |
hene | +1.911 |
Stras | +1.896 |
Stage | +1.881 |
Neg logit contributions | |
Alam | -2.112 |
Antar | -2.077 |
Aman | -1.895 |
Negro | -1.857 |
Jama | -1.847 |
Token | -> |
Token ID | 4613 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Alam | +1.426 |
Antar | +1.370 |
Aman | +1.249 |
Negro | +1.222 |
Jama | +1.204 |
Neg logit contributions | |
ikes | -1.735 |
Stras | -1.580 |
hene | -1.577 |
Spr | -1.557 |
Stage | -1.530 |
Token | Option |
Token ID | 16018 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
Alam | +1.295 |
Antar | +1.256 |
Aman | +1.142 |
Negro | +1.114 |
Malays | +1.102 |
Neg logit contributions | |
ikes | -1.551 |
Stras | -1.409 |
hene | -1.403 |
Spr | -1.390 |
Stage | -1.367 |
Token | < |
Token ID | 1279 |
Feature activation | -8.44e+00 |
Pos logit contributions | |
Alam | +3.404 |
Antar | +3.154 |
Aman | +2.748 |
Negro | +2.669 |
Jama | +2.614 |
Neg logit contributions | |
ikes | -7.177 |
hene | -6.702 |
Stras | -6.695 |
Spr | -6.539 |
EStreamFrame | -6.520 |
Token | Shared |
Token ID | 39403 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Alam | +5.613 |
Antar | +5.304 |
Aman | +4.795 |
Negro | +4.697 |
Jama | +4.546 |
Neg logit contributions | |
ikes | -7.898 |
hene | -7.242 |
Stras | -7.242 |
Spr | -7.069 |
saddle | -7.004 |
Token | < |
Token ID | 1279 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
Alam | +1.110 |
Antar | +1.067 |
Aman | +0.965 |
Negro | +0.941 |
Jama | +0.928 |
Neg logit contributions | |
ikes | -1.487 |
Stras | -1.359 |
hene | -1.355 |
Spr | -1.338 |
Stage | -1.317 |
Token | ' |
Token ID | 705 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
Alam | +1.875 |
Antar | +1.796 |
Aman | +1.605 |
Negro | +1.559 |
Jama | +1.533 |
Neg logit contributions | |
ikes | -2.996 |
Stras | -2.751 |
hene | -2.744 |
Spr | -2.718 |
Stage | -2.674 |
Token | a |
Token ID | 64 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
Alam | +3.029 |
Antar | +2.856 |
Aman | +2.726 |
Negro | +2.659 |
Jama | +2.625 |
Neg logit contributions | |
ikes | -2.209 |
Stras | -1.964 |
hene | -1.934 |
Spr | -1.908 |
saddle | -1.878 |
Token | , |
Token ID | 837 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Alam | +3.195 |
Antar | +3.058 |
Aman | +2.814 |
Negro | +2.740 |
Jama | +2.694 |
Neg logit contributions | |
ikes | -3.475 |
Stras | -3.134 |
hene | -3.118 |
Spr | -3.080 |
saddle | -3.036 |
Token | > |
Token ID | 1875 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
Alam | +2.973 |
Antar | +2.865 |
Aman | +2.659 |
Negro | +2.593 |
Jama | +2.552 |
Neg logit contributions | |
ikes | -2.706 |
Stras | -2.436 |
hene | -2.427 |
Spr | -2.393 |
saddle | -2.337 |
Token | { |
Token ID | 1391 |
Feature activation | -6.63e+00 |
Pos logit contributions | |
Alam | +2.151 |
Antar | +2.073 |
Aman | +1.870 |
Negro | +1.823 |
Jama | +1.799 |
Neg logit contributions | |
ikes | -2.952 |
Stras | -2.695 |
hene | -2.688 |
Spr | -2.662 |
Stage | -2.618 |
Token | pub |
Token ID | 2240 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
Alam | +4.844 |
Antar | +4.617 |
Aman | +4.255 |
Negro | +4.129 |
Jama | +4.056 |
Neg logit contributions | |
ikes | -5.813 |
Stras | -5.303 |
hene | -5.271 |
Spr | -5.211 |
Stage | -5.125 |
Token | fn |
Token ID | 24714 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Alam | +2.718 |
Antar | +2.620 |
Aman | +2.393 |
Negro | +2.337 |
Jama | +2.308 |
Neg logit contributions | |
ikes | -3.170 |
Stras | -2.876 |
hene | -2.872 |
Spr | -2.836 |
Stage | -2.786 |
Token | new |
Token ID | 649 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Alam | +2.995 |
Antar | +2.885 |
Aman | +2.677 |
Negro | +2.605 |
Jama | +2.576 |
Neg logit contributions | |
ikes | -3.009 |
hene | -2.720 |
Stras | -2.712 |
Spr | -2.693 |
Stage | -2.626 |
Token | ( |
Token ID | 357 |
Feature activation | -8.32e+00 |
Pos logit contributions | |
Alam | +1.610 |
Antar | +1.559 |
Aman | +1.437 |
Negro | +1.407 |
Jama | +1.390 |
Neg logit contributions | |
ikes | -1.546 |
Stras | -1.396 |
hene | -1.389 |
Spr | -1.364 |
saddle | -1.336 |
Token | t |
Token ID | 256 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Alam | +5.548 |
Antar | +5.235 |
Aman | +4.783 |
Negro | +4.624 |
negro | +4.548 |
Neg logit contributions | |
ikes | -7.599 |
Stras | -7.094 |
hene | -6.991 |
Spr | -6.868 |
Jesus | -6.739 |
Token | : |
Token ID | 1058 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Alam | +1.366 |
Antar | +1.308 |
Aman | +1.187 |
Negro | +1.161 |
Jama | +1.145 |
Neg logit contributions | |
ikes | -1.811 |
Stras | -1.663 |
hene | -1.658 |
Spr | -1.636 |
Stage | -1.610 |
Token | T |
Token ID | 309 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Alam | +0.125 |
Antar | +0.122 |
Aman | +0.109 |
Negro | +0.105 |
Malays | +0.105 |
Neg logit contributions | |
ikes | -0.186 |
Stras | -0.171 |
hene | -0.169 |
Spr | -0.168 |
saddle | -0.166 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Alam | +1.163 |
Antar | +1.127 |
Aman | +1.038 |
Negro | +1.018 |
Jama | +1.006 |
Neg logit contributions | |
ikes | -1.084 |
Stras | -0.973 |
hene | -0.970 |
Spr | -0.957 |
Stage | -0.937 |
Token | -> |
Token ID | 4613 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Alam | +2.453 |
Antar | +2.330 |
Aman | +2.143 |
Negro | +2.100 |
Jama | +2.060 |
Neg logit contributions | |
ikes | -3.080 |
hene | -2.826 |
Stras | -2.816 |
Spr | -2.773 |
Stage | -2.732 |
Token | -> |
Token ID | 4613 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
Alam | +0.714 |
Antar | +0.691 |
Aman | +0.637 |
Negro | +0.623 |
Jama | +0.617 |
Neg logit contributions | |
ikes | -0.686 |
Stras | -0.616 |
hene | -0.614 |
Spr | -0.606 |
Stage | -0.594 |
Token | Add |
Token ID | 3060 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Alam | +2.424 |
Antar | +2.342 |
Aman | +2.162 |
Negro | +2.119 |
Jama | +2.094 |
Neg logit contributions | |
ikes | -2.356 |
hene | -2.127 |
Stras | -2.116 |
Spr | -2.090 |
Stage | -2.037 |
Token | ons |
Token ID | 684 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
Alam | +1.914 |
Antar | +1.850 |
Aman | +1.715 |
Negro | +1.689 |
Jama | +1.667 |
Neg logit contributions | |
ikes | -1.604 |
hene | -1.434 |
Stras | -1.433 |
Spr | -1.408 |
Stage | -1.371 |
Token | . |
Token ID | 13 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
Alam | +0.819 |
Antar | +0.794 |
Aman | +0.730 |
Negro | +0.715 |
Jama | +0.707 |
Neg logit contributions | |
ikes | -0.802 |
Stras | -0.721 |
hene | -0.719 |
Spr | -0.710 |
Stage | -0.696 |
Token | Make |
Token ID | 6889 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
Alam | +3.063 |
Antar | +2.929 |
Aman | +2.704 |
Negro | +2.645 |
Jama | +2.613 |
Neg logit contributions | |
ikes | -3.068 |
hene | -2.744 |
Stras | -2.743 |
Spr | -2.713 |
saddle | -2.668 |
Token | sure |
Token ID | 1654 |
Feature activation | -8.27e+00 |
Pos logit contributions | |
Alam | +2.588 |
Antar | +2.479 |
Aman | +2.276 |
Negro | +2.244 |
Malays | +2.199 |
Neg logit contributions | |
ikes | -2.863 |
Stras | -2.590 |
hene | -2.590 |
Spr | -2.563 |
Stage | -2.501 |
Token | to |
Token ID | 284 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
Alam | +5.801 |
Antar | +5.512 |
Aman | +5.055 |
Negro | +4.967 |
Jama | +4.904 |
Neg logit contributions | |
ikes | -7.287 |
hene | -6.769 |
Stras | -6.622 |
Spr | -6.595 |
EStreamFrame | -6.323 |
Token | turn |
Token ID | 1210 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
Alam | +3.140 |
Antar | +3.009 |
Aman | +2.767 |
Negro | +2.714 |
Jama | +2.674 |
Neg logit contributions | |
ikes | -3.434 |
hene | -3.121 |
Stras | -3.095 |
Spr | -3.067 |
Stage | -3.005 |
Token | on |
Token ID | 319 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ikes | +0.543 |
Stras | +0.486 |
hene | +0.482 |
Spr | +0.478 |
Stage | +0.469 |
Neg logit contributions | |
Alam | -0.602 |
Antar | -0.586 |
Aman | -0.540 |
Negro | -0.527 |
Jama | -0.523 |
Token | � |
Token ID | 564 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Alam | +1.416 |
Antar | +1.369 |
Aman | +1.255 |
Negro | +1.228 |
Jama | +1.215 |
Neg logit contributions | |
ikes | -1.507 |
Stras | -1.361 |
hene | -1.360 |
Spr | -1.342 |
Stage | -1.315 |
Token | � |
Token ID | 246 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
ikes | +2.156 |
hene | +1.971 |
Stras | +1.968 |
Spr | +1.957 |
Stage | +1.922 |
Neg logit contributions | |
Alam | -1.416 |
Antar | -1.362 |
Aman | -1.218 |
Negro | -1.188 |
Malays | -1.166 |
Token | � |
Token ID | 447 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Alam | +1.958 |
Antar | +1.885 |
Aman | +1.722 |
Negro | +1.692 |
Jama | +1.676 |
Neg logit contributions | |
ikes | -2.076 |
Stras | -1.868 |
hene | -1.859 |
Spr | -1.841 |
Stage | -1.818 |
Token | � |
Token ID | 247 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Alam | +1.526 |
Antar | +1.450 |
Aman | +1.318 |
Negro | +1.285 |
Malays | +1.269 |
Neg logit contributions | |
ikes | -2.191 |
Stras | -2.010 |
hene | -1.997 |
Spr | -1.972 |
Stage | -1.953 |
Token | t |
Token ID | 83 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
Alam | +0.899 |
Antar | +0.862 |
Aman | +0.783 |
Negro | +0.762 |
Jama | +0.752 |
Neg logit contributions | |
ikes | -1.172 |
Stras | -1.072 |
hene | -1.066 |
Spr | -1.055 |
Stage | -1.039 |
Token | ... |
Token ID | 986 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Alam | +2.195 |
Antar | +2.125 |
Aman | +1.941 |
Negro | +1.911 |
Jama | +1.898 |
Neg logit contributions | |
ikes | -2.229 |
Stras | -1.992 |
hene | -1.990 |
Spr | -1.973 |
Stage | -1.942 |
Token | 15 |
Token ID | 1315 |
Feature activation | -8.96e+00 |
Pos logit contributions | |
Alam | +0.893 |
Antar | +0.862 |
Aman | +0.795 |
Negro | +0.777 |
Jama | +0.770 |
Neg logit contributions | |
ikes | -0.884 |
Stras | -0.798 |
hene | -0.794 |
Spr | -0.781 |
Stage | -0.773 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
Alam | +6.363 |
Antar | +6.031 |
Aman | +5.654 |
Jama | +5.616 |
Deep | +5.488 |
Neg logit contributions | |
ikes | -7.547 |
Stras | -7.082 |
hene | -6.979 |
EStreamFrame | -6.947 |
Stage | -6.815 |
Token | of |
Token ID | 286 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
Alam | +4.993 |
Antar | +4.566 |
Jama | +4.528 |
Deep | +4.394 |
Aman | +4.384 |
Neg logit contributions | |
Stras | -7.284 |
ikes | -7.279 |
hene | -7.026 |
EStreamFrame | -6.863 |
Stage | -6.729 |
Token | 15 |
Token ID | 1315 |
Feature activation | -9.25e+00 |
Pos logit contributions | |
Alam | +4.239 |
Antar | +4.022 |
Aman | +3.809 |
Negro | +3.709 |
Jama | +3.656 |
Neg logit contributions | |
ikes | -4.412 |
hene | -4.034 |
Stras | -3.990 |
Spr | -3.892 |
EStreamFrame | -3.874 |
Token | Photo |
Token ID | 5555 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Alam | +6.841 |
Antar | +6.419 |
Aman | +6.182 |
Jama | +6.082 |
negro | +5.978 |
Neg logit contributions | |
ikes | -7.588 |
hene | -7.044 |
Stras | -7.014 |
EStreamFrame | -6.832 |
Spr | -6.828 |
Token | : |
Token ID | 25 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Alam | +1.330 |
Antar | +1.273 |
Aman | +1.196 |
Negro | +1.170 |
Jama | +1.154 |
Neg logit contributions | |
ikes | -1.135 |
hene | -1.023 |
Stras | -1.023 |
Spr | -0.996 |
EStreamFrame | -0.977 |
Token | Le |
Token ID | 1004 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Alam | +1.199 |
Antar | +1.161 |
Aman | +1.075 |
Negro | +1.048 |
Jama | +1.042 |
Neg logit contributions | |
ikes | -1.134 |
hene | -1.012 |
Stras | -1.005 |
Spr | -0.997 |
Stage | -0.977 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Alam | +2.366 |
Antar | +2.145 |
Aman | +2.098 |
Negro | +2.070 |
Jama | +2.028 |
Neg logit contributions | |
ikes | -2.400 |
Stras | -2.157 |
hene | -2.152 |
saddle | -2.107 |
Spr | -2.102 |
Token | x |
Token ID | 87 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Alam | +1.107 |
Antar | +0.991 |
Aman | +0.928 |
Negro | +0.913 |
Jama | +0.883 |
Neg logit contributions | |
ikes | -1.989 |
Stras | -1.848 |
hene | -1.820 |
saddle | -1.803 |
Spr | -1.801 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
Alam | +0.982 |
Antar | +0.915 |
Aman | +0.875 |
Negro | +0.862 |
Jama | +0.850 |
Neg logit contributions | |
ikes | -0.930 |
Stras | -0.833 |
hene | -0.830 |
Spr | -0.815 |
saddle | -0.807 |
Token | 130 |
Token ID | 12952 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Alam | +0.010 |
Antar | +0.009 |
Aman | +0.009 |
Negro | +0.009 |
Jama | +0.009 |
Neg logit contributions | |
ikes | -0.009 |
Stras | -0.008 |
hene | -0.008 |
Spr | -0.008 |
saddle | -0.008 |
Token | 120 |
Token ID | 7982 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Alam | +1.418 |
Antar | +1.370 |
Aman | +1.270 |
Negro | +1.244 |
Jama | +1.235 |
Neg logit contributions | |
ikes | -1.310 |
hene | -1.174 |
Stras | -1.156 |
Spr | -1.146 |
saddle | -1.129 |
Token | 45 |
Token ID | 2231 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
Alam | +1.837 |
Antar | +1.736 |
Aman | +1.634 |
Negro | +1.581 |
Jama | +1.560 |
Neg logit contributions | |
ikes | -2.092 |
hene | -1.910 |
Stras | -1.896 |
Spr | -1.852 |
saddle | -1.851 |
Token | 25 |
Token ID | 1495 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
Alam | +5.364 |
Antar | +4.711 |
Aman | +4.701 |
Negro | +4.517 |
Deep | +4.405 |
Neg logit contributions | |
ikes | -7.484 |
hene | -6.921 |
EStreamFrame | -6.798 |
Stras | -6.795 |
saddle | -6.695 |
Token | x |
Token ID | 2124 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
Alam | +1.787 |
Antar | +1.641 |
Aman | +1.521 |
Negro | +1.487 |
Jama | +1.453 |
Neg logit contributions | |
ikes | -2.871 |
hene | -2.632 |
Stras | -2.605 |
Spr | -2.582 |
Stage | -2.554 |
Token | . |
Token ID | 13 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
Alam | +4.118 |
Aman | +3.608 |
Negro | +3.566 |
Antar | +3.536 |
Jama | +3.470 |
Neg logit contributions | |
ikes | -4.708 |
hene | -4.246 |
Stras | -4.234 |
saddle | -4.171 |
EStreamFrame | -4.094 |
Token | x |
Token ID | 87 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
Alam | +2.649 |
Aman | +2.148 |
Antar | +2.148 |
Negro | +2.141 |
Deep | +2.020 |
Neg logit contributions | |
ikes | -5.569 |
Stras | -5.234 |
saddle | -5.114 |
hene | -5.096 |
SPR | -5.028 |
Token | . |
Token ID | 13 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Alam | +2.441 |
Antar | +2.203 |
Aman | +2.162 |
Negro | +2.135 |
Jama | +2.086 |
Neg logit contributions | |
ikes | -2.487 |
Stras | -2.235 |
hene | -2.229 |
saddle | -2.181 |
Spr | -2.179 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Alam | +1.622 |
Antar | +1.490 |
Aman | +1.442 |
Negro | +1.418 |
Jama | +1.394 |
Neg logit contributions | |
ikes | -1.585 |
Stras | -1.421 |
hene | -1.421 |
Spr | -1.387 |
saddle | -1.385 |
Token | x |
Token ID | 87 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Alam | +0.663 |
Antar | +0.598 |
Aman | +0.559 |
Negro | +0.546 |
Jama | +0.529 |
Neg logit contributions | |
ikes | -1.156 |
Stras | -1.073 |
hene | -1.059 |
saddle | -1.045 |
Spr | -1.045 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ikes | +0.360 |
Stras | +0.322 |
hene | +0.321 |
Spr | +0.315 |
saddle | +0.310 |
Neg logit contributions | |
Alam | -0.405 |
Antar | -0.387 |
Aman | -0.362 |
Negro | -0.356 |
Jama | -0.352 |
Token | 160 |
Token ID | 14198 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
ikes | +1.238 |
Stras | +1.080 |
hene | +1.079 |
Spr | +1.067 |
Stage | +1.040 |
Neg logit contributions | |
Alam | -1.863 |
Antar | -1.824 |
Aman | -1.697 |
Negro | -1.663 |
Jama | -1.653 |
Token | 100 |
Token ID | 1802 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Alam | +2.659 |
Antar | +2.541 |
Aman | +2.367 |
Negro | +2.315 |
Jama | +2.306 |
Neg logit contributions | |
ikes | -2.646 |
hene | -2.386 |
Stras | -2.322 |
Spr | -2.319 |
EStreamFrame | -2.297 |
Token | 10 |
Token ID | 940 |
Feature activation | -8.09e+00 |
Pos logit contributions | |
Alam | +1.184 |
Antar | +1.129 |
Aman | +1.060 |
Negro | +1.032 |
Jama | +1.020 |
Neg logit contributions | |
ikes | -1.142 |
hene | -1.030 |
Stras | -1.026 |
Spr | -1.006 |
saddle | -1.001 |
Token | 94 |
Token ID | 5824 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Alam | +5.441 |
Antar | +4.912 |
Aman | +4.756 |
Negro | +4.585 |
Jama | +4.487 |
Neg logit contributions | |
ikes | -7.427 |
hene | -6.797 |
Stras | -6.721 |
EStreamFrame | -6.709 |
saddle | -6.619 |
Token | x |
Token ID | 2124 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
Alam | +1.086 |
Antar | +1.009 |
Aman | +0.929 |
Negro | +0.911 |
Jama | +0.888 |
Neg logit contributions | |
ikes | -1.729 |
hene | -1.582 |
Stras | -1.571 |
Spr | -1.553 |
Stage | -1.534 |
Token | . |
Token ID | 13 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
Alam | +3.813 |
Aman | +3.339 |
Negro | +3.298 |
Antar | +3.291 |
Jama | +3.220 |
Neg logit contributions | |
ikes | -4.268 |
hene | -3.846 |
Stras | -3.835 |
saddle | -3.771 |
EStreamFrame | -3.710 |
Token | x |
Token ID | 87 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Alam | +2.345 |
Antar | +1.930 |
Aman | +1.915 |
Negro | +1.898 |
Jama | +1.794 |
Neg logit contributions | |
ikes | -4.677 |
Stras | -4.369 |
hene | -4.283 |
saddle | -4.281 |
SPR | -4.201 |
Token | . |
Token ID | 13 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
Alam | +1.484 |
Antar | +1.366 |
Aman | +1.321 |
Negro | +1.298 |
Jama | +1.276 |
Neg logit contributions | |
ikes | -1.442 |
Stras | -1.293 |
hene | -1.292 |
Spr | -1.261 |
saddle | -1.258 |
Token | > |
Token ID | 1875 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
Alam | +2.221 |
Antar | +2.134 |
Aman | +1.976 |
Negro | +1.932 |
Jama | +1.904 |
Neg logit contributions | |
ikes | -2.136 |
Stras | -1.931 |
hene | -1.922 |
Spr | -1.896 |
Stage | -1.857 |
Token | { |
Token ID | 1391 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
Alam | +1.943 |
Antar | +1.849 |
Aman | +1.648 |
Negro | +1.603 |
Jama | +1.569 |
Neg logit contributions | |
ikes | -3.435 |
Stras | -3.178 |
hene | -3.168 |
Spr | -3.132 |
Stage | -3.088 |
Token | ... |
Token ID | 2644 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Alam | +4.019 |
Antar | +3.837 |
Aman | +3.538 |
Negro | +3.456 |
Jama | +3.384 |
Neg logit contributions | |
ikes | -4.680 |
Stras | -4.281 |
hene | -4.244 |
Spr | -4.183 |
Stage | -4.116 |
Token | } |
Token ID | 1782 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Alam | +0.350 |
Antar | +0.341 |
Aman | +0.309 |
Negro | +0.303 |
Jama | +0.300 |
Neg logit contributions | |
ikes | -0.397 |
Stras | -0.359 |
hene | -0.358 |
Spr | -0.354 |
Stage | -0.348 |
Token | impl |
Token ID | 4114 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
Alam | +1.765 |
Antar | +1.703 |
Aman | +1.566 |
Negro | +1.534 |
Jama | +1.514 |
Neg logit contributions | |
ikes | -1.825 |
Stras | -1.644 |
hene | -1.641 |
Spr | -1.622 |
Stage | -1.592 |
Token | < |
Token ID | 1279 |
Feature activation | -8.08e+00 |
Pos logit contributions | |
Alam | +2.549 |
Antar | +2.458 |
Aman | +2.238 |
Negro | +2.185 |
Jama | +2.157 |
Neg logit contributions | |
ikes | -3.106 |
Stras | -2.824 |
hene | -2.818 |
Spr | -2.788 |
Stage | -2.737 |
Token | T |
Token ID | 309 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
Alam | +5.193 |
Antar | +4.945 |
Aman | +4.527 |
Negro | +4.409 |
negro | +4.251 |
Neg logit contributions | |
ikes | -7.690 |
Stras | -7.085 |
hene | -7.032 |
Spr | -6.868 |
saddle | -6.811 |
Token | > |
Token ID | 1875 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
Alam | +3.915 |
Antar | +3.749 |
Aman | +3.480 |
Negro | +3.392 |
Jama | +3.333 |
Neg logit contributions | |
ikes | -3.790 |
Stras | -3.426 |
hene | -3.411 |
Spr | -3.374 |
EStreamFrame | -3.304 |
Token | Own |
Token ID | 11744 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Alam | +2.324 |
Antar | +2.230 |
Aman | +2.026 |
Negro | +1.974 |
Jama | +1.940 |
Neg logit contributions | |
ikes | -3.208 |
Stras | -2.939 |
hene | -2.936 |
Spr | -2.900 |
Stage | -2.854 |
Token | ed |
Token ID | 276 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
Alam | +0.174 |
Antar | +0.170 |
Aman | +0.155 |
Negro | +0.152 |
Malays | +0.151 |
Neg logit contributions | |
ikes | -0.167 |
hene | -0.149 |
Stras | -0.149 |
Spr | -0.148 |
Stage | -0.145 |
Token | < |
Token ID | 1279 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
ikes | +0.780 |
Spr | +0.708 |
hene | +0.706 |
Stras | +0.704 |
Stage | +0.699 |
Neg logit contributions | |
Alam | -0.528 |
Antar | -0.511 |
Aman | -0.455 |
Negro | -0.446 |
Malays | -0.444 |
Token | can |
Token ID | 460 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ikes | +1.583 |
hene | +1.391 |
Stras | +1.390 |
Spr | +1.366 |
Stage | +1.342 |
Neg logit contributions | |
Alam | -1.956 |
Antar | -1.915 |
Aman | -1.771 |
Negro | -1.724 |
Jama | -1.710 |
Token | trust |
Token ID | 3774 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ikes | +0.818 |
Stras | +0.733 |
hene | +0.728 |
Spr | +0.721 |
Stage | +0.707 |
Neg logit contributions | |
Alam | -0.841 |
Antar | -0.817 |
Aman | -0.749 |
Negro | -0.730 |
Jama | -0.724 |
Token | ? |
Token ID | 30 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ikes | +1.076 |
Stras | +0.940 |
hene | +0.936 |
Spr | +0.921 |
Stage | +0.898 |
Neg logit contributions | |
Alam | -1.646 |
Antar | -1.604 |
Aman | -1.496 |
Negro | -1.472 |
Jama | -1.459 |
Token |
|
Token ID | 198 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Alam | +1.453 |
Antar | +1.372 |
Aman | +1.310 |
Negro | +1.291 |
Jama | +1.279 |
Neg logit contributions | |
ikes | -1.158 |
Stras | -1.029 |
hene | -1.024 |
saddle | -1.000 |
Spr | -0.994 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Alam | +2.149 |
Antar | +1.957 |
Aman | +1.926 |
Negro | +1.908 |
Jama | +1.873 |
Neg logit contributions | |
ikes | -1.859 |
hene | -1.651 |
Stras | -1.643 |
saddle | -1.609 |
Spr | -1.589 |
Token | Subscribe |
Token ID | 27125 |
Feature activation | -8.01e+00 |
Pos logit contributions | |
Alam | +1.079 |
Antar | +1.007 |
Aman | +0.944 |
Negro | +0.930 |
Jama | +0.914 |
Neg logit contributions | |
ikes | -1.396 |
Stras | -1.279 |
hene | -1.269 |
saddle | -1.241 |
Spr | -1.228 |
Token | to |
Token ID | 284 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
Alam | +5.184 |
Antar | +4.783 |
Aman | +4.720 |
Negro | +4.550 |
Jama | +4.529 |
Neg logit contributions | |
ikes | -7.406 |
hene | -6.827 |
Stras | -6.690 |
Spr | -6.609 |
EStreamFrame | -6.569 |
Token | our |
Token ID | 674 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
Alam | +2.088 |
Antar | +1.967 |
Aman | +1.814 |
Negro | +1.766 |
Jama | +1.749 |
Neg logit contributions | |
ikes | -3.087 |
hene | -2.791 |
Stras | -2.766 |
Spr | -2.747 |
saddle | -2.701 |
Token | free |
Token ID | 1479 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
Alam | +3.142 |
Antar | +2.994 |
Aman | +2.857 |
Negro | +2.849 |
Jama | +2.780 |
Neg logit contributions | |
ikes | -2.581 |
hene | -2.267 |
Stras | -2.253 |
Spr | -2.218 |
EStreamFrame | -2.190 |
Token | newsletters |
Token ID | 16983 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Alam | +3.524 |
Antar | +3.408 |
Aman | +3.192 |
Negro | +3.192 |
Jama | +3.110 |
Neg logit contributions | |
ikes | -3.992 |
hene | -3.553 |
Stras | -3.536 |
Spr | -3.514 |
EStreamFrame | -3.505 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ikes | +1.159 |
Stras | +1.033 |
hene | +1.029 |
Spr | +1.016 |
Stage | +0.994 |
Neg logit contributions | |
Alam | -1.375 |
Antar | -1.335 |
Aman | -1.235 |
Negro | -1.212 |
Jama | -1.200 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Alam | +2.306 |
Antar | +2.085 |
Aman | +2.041 |
Negro | +2.014 |
Jama | +1.971 |
Neg logit contributions | |
ikes | -2.335 |
Stras | -2.100 |
hene | -2.094 |
saddle | -2.052 |
Spr | -2.046 |
Token | x |
Token ID | 87 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
Alam | +1.081 |
Antar | +0.963 |
Aman | +0.904 |
Negro | +0.889 |
Jama | +0.857 |
Neg logit contributions | |
ikes | -1.945 |
Stras | -1.806 |
hene | -1.782 |
saddle | -1.764 |
Spr | -1.759 |
Token | . |
Token ID | 13 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Alam | +0.664 |
Antar | +0.620 |
Aman | +0.590 |
Negro | +0.583 |
Jama | +0.574 |
Neg logit contributions | |
ikes | -0.627 |
Stras | -0.561 |
hene | -0.558 |
Spr | -0.548 |
saddle | -0.544 |
Token | 126 |
Token ID | 19420 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Alam | +0.306 |
Antar | +0.290 |
Aman | +0.273 |
Negro | +0.272 |
Jama | +0.269 |
Neg logit contributions | |
ikes | -0.242 |
Stras | -0.214 |
hene | -0.211 |
Spr | -0.208 |
Stage | -0.204 |
Token | 11 |
Token ID | 1367 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Alam | +1.879 |
Antar | +1.799 |
Aman | +1.663 |
Negro | +1.624 |
Jama | +1.616 |
Neg logit contributions | |
ikes | -1.946 |
hene | -1.753 |
Stras | -1.727 |
Spr | -1.717 |
saddle | -1.694 |
Token | 458 |
Token ID | 29334 |
Feature activation | -7.96e+00 |
Pos logit contributions | |
Alam | +0.281 |
Antar | +0.270 |
Aman | +0.251 |
Negro | +0.244 |
Jama | +0.242 |
Neg logit contributions | |
ikes | -0.266 |
Stras | -0.238 |
hene | -0.238 |
Spr | -0.234 |
saddle | -0.230 |
Token | 72 |
Token ID | 4761 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Alam | +5.300 |
Aman | +4.681 |
Antar | +4.657 |
Negro | +4.473 |
Deep | +4.398 |
Neg logit contributions | |
ikes | -7.290 |
hene | -6.748 |
Stras | -6.636 |
EStreamFrame | -6.615 |
saddle | -6.543 |
Token | x |
Token ID | 2124 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
Alam | +1.005 |
Antar | +0.936 |
Aman | +0.861 |
Negro | +0.841 |
Jama | +0.822 |
Neg logit contributions | |
ikes | -1.565 |
hene | -1.433 |
Stras | -1.423 |
Spr | -1.406 |
Stage | -1.388 |
Token | . |
Token ID | 13 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Alam | +4.638 |
Aman | +4.049 |
Negro | +4.018 |
Antar | +3.929 |
Jama | +3.907 |
Neg logit contributions | |
ikes | -5.468 |
hene | -4.931 |
Stras | -4.906 |
saddle | -4.843 |
EStreamFrame | -4.758 |
Token | x |
Token ID | 87 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
Alam | +2.264 |
Antar | +1.885 |
Aman | +1.855 |
Negro | +1.838 |
Jama | +1.734 |
Neg logit contributions | |
ikes | -4.588 |
Stras | -4.299 |
hene | -4.209 |
saddle | -4.203 |
Spr | -4.140 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Alam | +2.909 |
Antar | +2.605 |
Aman | +2.569 |
Negro | +2.542 |
Jama | +2.482 |
Neg logit contributions | |
ikes | -3.029 |
Stras | -2.724 |
hene | -2.720 |
saddle | -2.671 |
Spr | -2.657 |
Token | 79 |
Token ID | 3720 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ikes | +2.017 |
hene | +1.774 |
Stras | +1.766 |
Spr | +1.751 |
Stage | +1.712 |
Neg logit contributions | |
Alam | -2.468 |
Antar | -2.430 |
Aman | -2.203 |
Negro | -2.202 |
Jama | -2.175 |
Token | 23 |
Token ID | 1954 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
ikes | +0.305 |
Stras | +0.273 |
hene | +0.272 |
Spr | +0.268 |
Stage | +0.263 |
Neg logit contributions | |
Alam | -0.345 |
Antar | -0.334 |
Aman | -0.309 |
Negro | -0.303 |
Jama | -0.299 |
Token | 12 |
Token ID | 1065 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Alam | +1.722 |
Antar | +1.627 |
Aman | +1.520 |
Negro | +1.477 |
Jama | +1.460 |
Neg logit contributions | |
ikes | -1.953 |
Stras | -1.784 |
hene | -1.771 |
Spr | -1.740 |
saddle | -1.722 |
Token | . |
Token ID | 13 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
Alam | +1.544 |
Antar | +1.441 |
Aman | +1.379 |
Negro | +1.350 |
Jama | +1.336 |
Neg logit contributions | |
ikes | -1.501 |
hene | -1.348 |
Stras | -1.345 |
Spr | -1.322 |
saddle | -1.309 |
Token | e |
Token ID | 68 |
Feature activation | -7.73e+00 |
Pos logit contributions | |
Alam | +3.982 |
Antar | +3.670 |
Aman | +3.441 |
Jama | +3.377 |
Malays | +3.337 |
Neg logit contributions | |
ikes | -4.726 |
Stras | -4.348 |
hene | -4.257 |
SPR | -4.250 |
Spr | -4.238 |
Token | ce |
Token ID | 344 |
Feature activation | -7.91e+00 |
Pos logit contributions | |
Alam | +4.299 |
Aman | +3.633 |
Antar | +3.625 |
Deep | +3.499 |
adem | +3.406 |
Neg logit contributions | |
ikes | -7.390 |
Stras | -7.317 |
EStreamFrame | -7.257 |
SPR | -7.150 |
eneg | -7.112 |
Token | / |
Token ID | 14 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
Alam | +6.170 |
Antar | +5.905 |
Aman | +5.566 |
Jama | +5.419 |
Deep | +5.384 |
Neg logit contributions | |
ikes | -6.310 |
hene | -5.745 |
Stras | -5.573 |
eneg | -5.534 |
SPR | -5.521 |
Token | edd |
Token ID | 6048 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
Alam | +3.955 |
Antar | +3.746 |
Aman | +3.521 |
Negro | +3.412 |
Jama | +3.379 |
Neg logit contributions | |
ikes | -3.645 |
Stras | -3.412 |
hene | -3.307 |
Spr | -3.273 |
SPR | -3.216 |
Token | 75 |
Token ID | 2425 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
Alam | +2.362 |
Antar | +2.251 |
Aman | +2.118 |
Negro | +2.055 |
Jama | +2.034 |
Neg logit contributions | |
ikes | -2.123 |
Stras | -1.967 |
hene | -1.906 |
Spr | -1.889 |
EStreamFrame | -1.852 |
Token | / |
Token ID | 14 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
Alam | +4.547 |
Antar | +4.274 |
Aman | +4.052 |
Negro | +3.948 |
Jama | +3.921 |
Neg logit contributions | |
ikes | -4.190 |
Stras | -3.903 |
hene | -3.776 |
Spr | -3.746 |
SPR | -3.688 |
Token | AUT |
Token ID | 39371 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
Alam | +0.687 |
Antar | +0.667 |
Aman | +0.618 |
Negro | +0.606 |
Jama | +0.601 |
Neg logit contributions | |
ikes | -0.555 |
Stras | -0.495 |
hene | -0.493 |
Spr | -0.482 |
saddle | -0.474 |
Token | System |
Token ID | 11964 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
Alam | +2.141 |
Antar | +2.082 |
Aman | +1.933 |
Negro | +1.894 |
Jama | +1.883 |
Neg logit contributions | |
ikes | -1.604 |
Stras | -1.421 |
hene | -1.406 |
Spr | -1.360 |
saddle | -1.356 |
Token | . |
Token ID | 13 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
Alam | +2.638 |
Antar | +2.549 |
Aman | +2.360 |
Negro | +2.319 |
Malays | +2.283 |
Neg logit contributions | |
ikes | -2.527 |
hene | -2.275 |
Stras | -2.259 |
saddle | -2.184 |
Spr | -2.174 |
Token | Draw |
Token ID | 25302 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
Alam | +3.993 |
Antar | +3.795 |
Aman | +3.566 |
Negro | +3.464 |
Jama | +3.403 |
Neg logit contributions | |
ikes | -4.195 |
Stras | -3.800 |
hene | -3.716 |
saddle | -3.657 |
EStreamFrame | -3.535 |
Token | ing |
Token ID | 278 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
Alam | +4.292 |
Antar | +4.034 |
Aman | +3.806 |
Negro | +3.730 |
Jama | +3.657 |
Neg logit contributions | |
ikes | -4.153 |
Stras | -3.718 |
hene | -3.660 |
EStreamFrame | -3.521 |
saddle | -3.518 |
Token | . |
Token ID | 13 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
Alam | +2.616 |
Antar | +2.523 |
Aman | +2.344 |
Negro | +2.293 |
Jama | +2.280 |
Neg logit contributions | |
ikes | -2.458 |
Stras | -2.198 |
hene | -2.186 |
saddle | -2.128 |
Spr | -2.092 |
Token | Graphics |
Token ID | 18172 |
Feature activation | -7.88e+00 |
Pos logit contributions | |
Alam | +4.406 |
Antar | +4.202 |
Aman | +3.931 |
Negro | +3.880 |
Jama | +3.820 |
Neg logit contributions | |
ikes | -3.799 |
Stras | -3.478 |
hene | -3.367 |
saddle | -3.340 |
EStreamFrame | -3.164 |
Token | ] |
Token ID | 60 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Alam | +6.131 |
Antar | +5.765 |
Aman | +5.392 |
Negro | +5.372 |
Jama | +5.274 |
Neg logit contributions | |
ikes | -6.293 |
Stras | -5.679 |
hene | -5.545 |
saddle | -5.465 |
EStreamFrame | -5.342 |
Token | :: |
Token ID | 3712 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
ikes | +1.397 |
Spr | +1.253 |
Stras | +1.247 |
hene | +1.246 |
Stage | +1.222 |
Neg logit contributions | |
Alam | -1.519 |
Antar | -1.481 |
Aman | -1.360 |
Negro | -1.334 |
Jama | -1.323 |
Token | From |
Token ID | 4863 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
Alam | +3.764 |
Antar | +3.573 |
Aman | +3.378 |
Negro | +3.339 |
Jama | +3.269 |
Neg logit contributions | |
ikes | -2.777 |
Stras | -2.521 |
hene | -2.439 |
saddle | -2.394 |
SPR | -2.300 |
Token | Image |
Token ID | 5159 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
Alam | +5.288 |
Antar | +5.053 |
Aman | +4.758 |
Negro | +4.684 |
Jama | +4.606 |
Neg logit contributions | |
ikes | -4.338 |
Stras | -3.770 |
hene | -3.703 |
saddle | -3.666 |
EStreamFrame | -3.584 |
Token | ($ |
Token ID | 16763 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Alam | +2.932 |
Antar | +2.822 |
Aman | +2.602 |
Negro | +2.540 |
Jama | +2.512 |
Neg logit contributions | |
ikes | -3.142 |
Stras | -2.829 |
hene | -2.821 |
saddle | -2.731 |
Spr | -2.702 |
Token | , |
Token ID | 11 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Alam | +0.837 |
Antar | +0.809 |
Aman | +0.746 |
Negro | +0.730 |
Jama | +0.722 |
Neg logit contributions | |
ikes | -0.813 |
hene | -0.728 |
Stras | -0.726 |
Spr | -0.718 |
Stage | -0.702 |
Token | " |
Token ID | 366 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
Alam | +2.099 |
Antar | +2.029 |
Aman | +1.873 |
Negro | +1.829 |
Jama | +1.809 |
Neg logit contributions | |
ikes | -2.083 |
hene | -1.871 |
Stras | -1.869 |
Spr | -1.842 |
Stage | -1.799 |
Token | My |
Token ID | 3666 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Alam | +0.467 |
Antar | +0.453 |
Aman | +0.422 |
Negro | +0.414 |
Jama | +0.410 |
Neg logit contributions | |
ikes | -0.355 |
Stras | -0.315 |
hene | -0.313 |
Spr | -0.307 |
saddle | -0.301 |
Token | what |
Token ID | 644 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Alam | +1.201 |
Antar | +1.164 |
Aman | +1.076 |
Negro | +1.055 |
Jama | +1.043 |
Neg logit contributions | |
ikes | -1.106 |
hene | -0.993 |
Stras | -0.992 |
Spr | -0.978 |
Stage | -0.960 |
Token | is |
Token ID | 318 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
ikes | +2.161 |
hene | +1.883 |
Stras | +1.880 |
Spr | +1.859 |
saddle | +1.825 |
Neg logit contributions | |
Alam | -2.801 |
Antar | -2.757 |
Aman | -2.532 |
Negro | -2.484 |
Malays | -2.468 |
Token | what |
Token ID | 644 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
Alam | +1.941 |
Antar | +1.866 |
Aman | +1.717 |
Negro | +1.678 |
Jama | +1.656 |
Neg logit contributions | |
ikes | -2.273 |
hene | -2.056 |
Stras | -2.053 |
Spr | -2.032 |
Stage | -1.989 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
ikes | +3.837 |
Stras | +3.441 |
hene | +3.390 |
Spr | +3.364 |
saddle | +3.339 |
Neg logit contributions | |
Alam | -4.203 |
Antar | -4.132 |
Aman | -3.762 |
Negro | -3.665 |
Malays | -3.659 |
Token | There |
Token ID | 1318 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ikes | +0.050 |
Stras | +0.045 |
hene | +0.045 |
Spr | +0.045 |
Stage | +0.044 |
Neg logit contributions | |
Alam | -0.053 |
Antar | -0.052 |
Aman | -0.048 |
Negro | -0.047 |
Jama | -0.046 |
Token | went |
Token ID | 1816 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ikes | +0.162 |
Stras | +0.145 |
hene | +0.145 |
Spr | +0.143 |
Stage | +0.140 |
Neg logit contributions | |
Alam | -0.163 |
Antar | -0.158 |
Aman | -0.145 |
Negro | -0.142 |
Jama | -0.140 |
Token | cool |
Token ID | 3608 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Alam | +0.871 |
Antar | +0.843 |
Aman | +0.771 |
Negro | +0.755 |
Jama | +0.746 |
Neg logit contributions | |
ikes | -0.953 |
Stras | -0.860 |
hene | -0.859 |
Spr | -0.849 |
Stage | -0.834 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ikes | +0.360 |
Stras | +0.324 |
hene | +0.323 |
Spr | +0.320 |
Stage | +0.313 |
Neg logit contributions | |
Alam | -0.357 |
Antar | -0.346 |
Aman | -0.317 |
Negro | -0.310 |
Jama | -0.306 |
Token | 16 |
Token ID | 1467 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ikes | +0.805 |
Stras | +0.716 |
hene | +0.715 |
Spr | +0.705 |
Stage | +0.690 |
Neg logit contributions | |
Alam | -0.951 |
Antar | -0.922 |
Aman | -0.854 |
Negro | -0.838 |
Jama | -0.829 |
Token | 27 |
Token ID | 1983 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
Alam | +1.520 |
Antar | +1.430 |
Aman | +1.366 |
Negro | +1.344 |
Jama | +1.324 |
Neg logit contributions | |
ikes | -1.396 |
Stras | -1.238 |
hene | -1.236 |
Spr | -1.215 |
saddle | -1.206 |
Token | 145 |
Token ID | 18781 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ikes | +0.026 |
hene | +0.023 |
Stras | +0.023 |
Spr | +0.022 |
saddle | +0.022 |
Neg logit contributions | |
Alam | -0.038 |
Antar | -0.037 |
Aman | -0.035 |
Negro | -0.034 |
Malays | -0.033 |
Token | Flat |
Token ID | 21939 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ikes | +1.218 |
Stras | +1.077 |
hene | +1.074 |
Spr | +1.059 |
Stage | +1.036 |
Neg logit contributions | |
Alam | -1.602 |
Antar | -1.563 |
Aman | -1.451 |
Negro | -1.422 |
Jama | -1.409 |
Token | buff |
Token ID | 36873 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
ikes | +1.145 |
hene | +1.024 |
Stras | +1.020 |
Spr | +1.011 |
Stage | +0.992 |
Neg logit contributions | |
Alam | -1.210 |
Antar | -1.181 |
Aman | -1.081 |
Negro | -1.058 |
Jama | -1.049 |
Token | ers |
Token ID | 364 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
ikes | +0.701 |
Stras | +0.626 |
hene | +0.624 |
Spr | +0.616 |
Stage | +0.603 |
Neg logit contributions | |
Alam | -0.819 |
Antar | -0.794 |
Aman | -0.735 |
Negro | -0.721 |
Jama | -0.713 |
Token | Reading |
Token ID | 36120 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ikes | +2.936 |
Spr | +2.565 |
Stage | +2.464 |
hene | +2.433 |
Stras | +2.392 |
Neg logit contributions | |
Alam | -6.529 |
Antar | -6.490 |
Aman | -6.046 |
negro | -5.920 |
Malays | -5.899 |
Token | 69 |
Token ID | 8644 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ikes | +2.203 |
Stras | +1.978 |
hene | +1.953 |
Spr | +1.941 |
Stage | +1.893 |
Neg logit contributions | |
Alam | -2.674 |
Antar | -2.623 |
Aman | -2.401 |
Negro | -2.360 |
Malays | -2.351 |
Token | 30 |
Token ID | 1270 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ikes | +1.304 |
Stras | +1.167 |
hene | +1.163 |
Spr | +1.151 |
Stage | +1.128 |
Neg logit contributions | |
Alam | -1.392 |
Antar | -1.355 |
Aman | -1.243 |
Negro | -1.221 |
Jama | -1.207 |
Token | 696 |
Token ID | 38205 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Alam | +1.914 |
Antar | +1.847 |
Aman | +1.720 |
Negro | +1.679 |
Jama | +1.663 |
Neg logit contributions | |
ikes | -1.628 |
Stras | -1.462 |
hene | -1.458 |
Spr | -1.430 |
saddle | -1.401 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ikes | +0.365 |
Stras | +0.326 |
hene | +0.325 |
Spr | +0.321 |
Stage | +0.315 |
Neg logit contributions | |
Alam | -0.406 |
Antar | -0.395 |
Aman | -0.364 |
Negro | -0.357 |
Jama | -0.353 |
Token | 's |
Token ID | 338 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ikes | +0.797 |
Stras | +0.711 |
hene | +0.708 |
Spr | +0.699 |
saddle | +0.684 |
Neg logit contributions | |
Alam | -0.901 |
Antar | -0.877 |
Aman | -0.807 |
Negro | -0.792 |
Jama | -0.783 |
Token | so |
Token ID | 523 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ikes | +1.671 |
Stras | +1.512 |
hene | +1.492 |
Spr | +1.473 |
saddle | +1.451 |
Neg logit contributions | |
Alam | -1.787 |
Antar | -1.744 |
Aman | -1.593 |
Negro | -1.566 |
Malays | -1.550 |
Token | new |
Token ID | 649 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
ikes | +2.158 |
Stras | +1.965 |
hene | +1.939 |
Spr | +1.913 |
saddle | +1.891 |
Neg logit contributions | |
Alam | -2.221 |
Antar | -2.163 |
Aman | -1.979 |
Negro | -1.932 |
Malays | -1.923 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ikes | +2.090 |
Stras | +1.869 |
hene | +1.847 |
Spr | +1.830 |
saddle | +1.799 |
Neg logit contributions | |
Alam | -2.446 |
Antar | -2.395 |
Aman | -2.198 |
Negro | -2.153 |
Jama | -2.130 |
Token | it |
Token ID | 340 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
ikes | +1.795 |
Stras | +1.634 |
hene | +1.594 |
Spr | +1.586 |
saddle | +1.561 |
Neg logit contributions | |
Alam | -1.850 |
Antar | -1.813 |
Aman | -1.651 |
Negro | -1.624 |
Malays | -1.608 |
Token | 's |
Token ID | 338 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
ikes | +3.750 |
Stras | +3.355 |
hene | +3.296 |
Spr | +3.255 |
saddle | +3.251 |
Neg logit contributions | |
Alam | -4.690 |
Antar | -4.595 |
Aman | -4.199 |
Negro | -4.127 |
Malays | -4.103 |
Token | too |
Token ID | 1165 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ikes | +3.747 |
Stras | +3.444 |
hene | +3.351 |
Spr | +3.309 |
saddle | +3.303 |
Neg logit contributions | |
Alam | -4.383 |
Antar | -4.291 |
Aman | -3.912 |
Malays | -3.864 |
Negro | -3.856 |
Token | early |
Token ID | 1903 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
ikes | +1.152 |
Stras | +1.045 |
hene | +1.039 |
Spr | +1.026 |
saddle | +1.009 |
Neg logit contributions | |
Alam | -1.164 |
Antar | -1.129 |
Aman | -1.036 |
Negro | -1.009 |
Malays | -1.002 |
Token | to |
Token ID | 284 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ikes | +0.161 |
Stras | +0.145 |
hene | +0.144 |
Spr | +0.142 |
Stage | +0.140 |
Neg logit contributions | |
Alam | -0.171 |
Antar | -0.166 |
Aman | -0.153 |
Negro | -0.150 |
Jama | -0.148 |
Token | ask |
Token ID | 1265 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ikes | +0.167 |
Stras | +0.151 |
hene | +0.150 |
Spr | +0.149 |
saddle | +0.146 |
Neg logit contributions | |
Alam | -0.158 |
Antar | -0.153 |
Aman | -0.140 |
Negro | -0.137 |
Jama | -0.135 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Alam | +0.915 |
Antar | +0.882 |
Aman | +0.812 |
Negro | +0.795 |
Jama | +0.786 |
Neg logit contributions | |
ikes | -0.960 |
hene | -0.865 |
Stras | -0.862 |
Spr | -0.854 |
Stage | -0.838 |
Token | hood |
Token ID | 14263 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
Alam | +1.144 |
Antar | +1.104 |
Aman | +1.006 |
Negro | +0.985 |
Jama | +0.975 |
Neg logit contributions | |
ikes | -1.413 |
hene | -1.282 |
Stras | -1.280 |
Spr | -1.265 |
Stage | -1.244 |
Token | ed |
Token ID | 276 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Alam | +0.367 |
Antar | +0.358 |
Aman | +0.334 |
Negro | +0.329 |
Jama | +0.326 |
Neg logit contributions | |
ikes | -0.239 |
Stras | -0.210 |
hene | -0.209 |
Spr | -0.205 |
Stage | -0.201 |
Token | sweats |
Token ID | 39387 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Alam | +1.359 |
Antar | +1.311 |
Aman | +1.194 |
Negro | +1.170 |
Jama | +1.159 |
Neg logit contributions | |
ikes | -1.682 |
hene | -1.532 |
Stras | -1.529 |
Spr | -1.507 |
Stage | -1.485 |
Token | hirt |
Token ID | 49756 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Alam | +1.405 |
Antar | +1.344 |
Aman | +1.203 |
Negro | +1.172 |
Jama | +1.152 |
Neg logit contributions | |
ikes | -2.305 |
Stras | -2.139 |
hene | -2.117 |
Spr | -2.098 |
Stage | -2.076 |
Token | , |
Token ID | 11 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Alam | +1.155 |
Antar | +1.123 |
Aman | +1.035 |
Negro | +1.014 |
Jama | +1.006 |
Neg logit contributions | |
ikes | -1.086 |
Stras | -0.975 |
hene | -0.974 |
Spr | -0.959 |
Stage | -0.942 |
Token | looking |
Token ID | 2045 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
ikes | +0.525 |
Stras | +0.472 |
hene | +0.470 |
Spr | +0.466 |
saddle | +0.456 |
Neg logit contributions | |
Alam | -0.520 |
Antar | -0.504 |
Aman | -0.462 |
Negro | -0.453 |
Jama | -0.447 |
Token | more |
Token ID | 517 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ikes | +4.171 |
Stras | +3.767 |
saddle | +3.687 |
hene | +3.683 |
Spr | +3.652 |
Neg logit contributions | |
Alam | -4.156 |
Antar | -4.000 |
Aman | -3.636 |
Negro | -3.565 |
Malays | -3.541 |
Token | like |
Token ID | 588 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Alam | +0.443 |
Antar | +0.430 |
Aman | +0.396 |
Negro | +0.387 |
Jama | +0.384 |
Neg logit contributions | |
ikes | -0.446 |
Stras | -0.400 |
hene | -0.400 |
Spr | -0.396 |
Stage | -0.388 |
Token | a |
Token ID | 257 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
ikes | +0.506 |
Stras | +0.457 |
hene | +0.455 |
Spr | +0.450 |
Stage | +0.442 |
Neg logit contributions | |
Alam | -0.472 |
Antar | -0.457 |
Aman | -0.418 |
Negro | -0.409 |
Jama | -0.404 |
Token | rock |
Token ID | 3881 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Alam | +0.286 |
Antar | +0.278 |
Aman | +0.255 |
Negro | +0.250 |
Jama | +0.248 |
Neg logit contributions | |
ikes | -0.292 |
hene | -0.262 |
Stras | -0.261 |
Spr | -0.258 |
Stage | -0.253 |
Token | musician |
Token ID | 21623 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ikes | +0.917 |
Stras | +0.832 |
hene | +0.829 |
Spr | +0.821 |
Stage | +0.806 |
Neg logit contributions | |
Alam | -0.873 |
Antar | -0.844 |
Aman | -0.771 |
Negro | -0.758 |
Malays | -0.751 |
Token | ; |
Token ID | 26 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
Alam | +1.348 |
Antar | +1.311 |
Aman | +1.208 |
Negro | +1.184 |
Jama | +1.171 |
Neg logit contributions | |
ikes | -1.266 |
Stras | -1.135 |
hene | -1.129 |
Spr | -1.124 |
Stage | -1.096 |
Token | these |
Token ID | 777 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Alam | +0.427 |
Antar | +0.413 |
Aman | +0.379 |
Negro | +0.371 |
Jama | +0.367 |
Neg logit contributions | |
ikes | -0.446 |
Stras | -0.401 |
hene | -0.401 |
Spr | -0.397 |
Stage | -0.389 |
Token | disagreements |
Token ID | 37990 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Alam | +0.237 |
Antar | +0.228 |
Aman | +0.207 |
Negro | +0.202 |
Jama | +0.199 |
Neg logit contributions | |
ikes | -0.309 |
Stras | -0.282 |
hene | -0.281 |
Spr | -0.279 |
Stage | -0.274 |
Token | may |
Token ID | 743 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
Alam | +1.365 |
Antar | +1.322 |
Aman | +1.216 |
Negro | +1.195 |
Jama | +1.178 |
Neg logit contributions | |
ikes | -1.415 |
Stras | -1.273 |
hene | -1.266 |
Spr | -1.261 |
Stage | -1.237 |
Token | or |
Token ID | 393 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
ikes | +0.506 |
Stras | +0.455 |
hene | +0.454 |
Spr | +0.448 |
Stage | +0.439 |
Neg logit contributions | |
Alam | -0.521 |
Antar | -0.505 |
Aman | -0.464 |
Negro | -0.454 |
Jama | -0.449 |
Token | may |
Token ID | 743 |
Feature activation | +5.78e+00 |
Pos logit contributions | |
Alam | +3.122 |
Antar | +2.963 |
Aman | +2.738 |
Negro | +2.724 |
Malays | +2.720 |
Neg logit contributions | |
ikes | -3.249 |
Stras | -2.931 |
Spr | -2.920 |
hene | -2.909 |
Stage | -2.823 |
Token | not |
Token ID | 407 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
ikes | +3.686 |
hene | +3.206 |
saddle | +3.166 |
Stras | +3.164 |
Spr | +3.126 |
Neg logit contributions | |
Alam | -5.570 |
Antar | -5.553 |
Aman | -5.042 |
Negro | -4.920 |
negro | -4.906 |
Token | reflect |
Token ID | 4079 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ikes | +0.783 |
Stras | +0.703 |
hene | +0.701 |
Spr | +0.690 |
saddle | +0.679 |
Neg logit contributions | |
Alam | -0.815 |
Antar | -0.790 |
Aman | -0.726 |
Negro | -0.711 |
Jama | -0.704 |
Token | substantive |
Token ID | 28580 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Alam | +0.270 |
Antar | +0.261 |
Aman | +0.240 |
Negro | +0.235 |
Jama | +0.232 |
Neg logit contributions | |
ikes | -0.286 |
Stras | -0.258 |
hene | -0.258 |
Spr | -0.255 |
Stage | -0.250 |
Token | differences |
Token ID | 5400 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Alam | +1.610 |
Antar | +1.546 |
Aman | +1.413 |
Negro | +1.385 |
Jama | +1.362 |
Neg logit contributions | |
ikes | -2.196 |
hene | -1.995 |
Spr | -1.992 |
Stras | -1.991 |
Stage | -1.954 |
Token | in |
Token ID | 287 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Alam | +1.258 |
Antar | +1.212 |
Aman | +1.115 |
Negro | +1.093 |
Jama | +1.079 |
Neg logit contributions | |
ikes | -1.323 |
Stras | -1.197 |
hene | -1.193 |
Spr | -1.188 |
Stage | -1.162 |
Token | of |
Token ID | 286 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
ikes | +0.743 |
Stras | +0.667 |
hene | +0.664 |
Spr | +0.656 |
Stage | +0.643 |
Neg logit contributions | |
Alam | -0.800 |
Antar | -0.776 |
Aman | -0.714 |
Negro | -0.700 |
Jama | -0.693 |
Token | remote |
Token ID | 6569 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ikes | +0.303 |
hene | +0.273 |
Stras | +0.273 |
Spr | +0.269 |
Stage | +0.264 |
Neg logit contributions | |
Alam | -0.291 |
Antar | -0.282 |
Aman | -0.258 |
Negro | -0.253 |
Jama | -0.251 |
Token | control |
Token ID | 1630 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ikes | +1.053 |
Stras | +0.950 |
hene | +0.948 |
Spr | +0.937 |
Stage | +0.918 |
Neg logit contributions | |
Alam | -1.015 |
Antar | -0.982 |
Aman | -0.901 |
Negro | -0.882 |
Jama | -0.872 |
Token | cars |
Token ID | 5006 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
ikes | +1.427 |
Stras | +1.285 |
hene | +1.270 |
Spr | +1.257 |
Stage | +1.237 |
Neg logit contributions | |
Alam | -1.490 |
Antar | -1.450 |
Aman | -1.329 |
Negro | -1.303 |
Jama | -1.286 |
Token | 1993 |
Token ID | 9656 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
ikes | +2.388 |
Stras | +2.161 |
hene | +2.128 |
Spr | +2.106 |
Stage | +2.078 |
Neg logit contributions | |
Alam | -2.482 |
Antar | -2.421 |
Aman | -2.202 |
Negro | -2.168 |
negro | -2.149 |
Token | : |
Token ID | 25 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ikes | +0.327 |
Stras | +0.289 |
hene | +0.289 |
Spr | +0.285 |
Stage | +0.278 |
Neg logit contributions | |
Alam | -0.416 |
Antar | -0.404 |
Aman | -0.375 |
Negro | -0.368 |
Jama | -0.364 |
Token | Father |
Token ID | 9190 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ikes | +0.851 |
Stras | +0.766 |
hene | +0.764 |
Spr | +0.755 |
Stage | +0.741 |
Neg logit contributions | |
Alam | -0.841 |
Antar | -0.814 |
Aman | -0.747 |
Negro | -0.732 |
Jama | -0.724 |
Token | buys |
Token ID | 24779 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
Alam | +0.843 |
Antar | +0.812 |
Aman | +0.752 |
Negro | +0.737 |
Jama | +0.733 |
Neg logit contributions | |
ikes | -0.814 |
hene | -0.732 |
Stras | -0.729 |
Spr | -0.724 |
Stage | -0.707 |
Token | him |
Token ID | 683 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Alam | +1.633 |
Antar | +1.567 |
Aman | +1.453 |
Negro | +1.428 |
Jama | +1.417 |
Neg logit contributions | |
ikes | -1.619 |
hene | -1.461 |
Stras | -1.446 |
Spr | -1.439 |
Stage | -1.412 |
Token | a |
Token ID | 257 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Alam | +1.069 |
Antar | +1.026 |
Aman | +0.950 |
Negro | +0.928 |
Jama | +0.922 |
Neg logit contributions | |
ikes | -1.162 |
hene | -1.052 |
Stras | -1.049 |
Spr | -1.039 |
Stage | -1.020 |
Token | £ |
Token ID | 4248 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
ikes | +0.358 |
Stras | +0.322 |
hene | +0.321 |
Spr | +0.317 |
Stage | +0.311 |
Neg logit contributions | |
Alam | -0.371 |
Antar | -0.360 |
Aman | -0.331 |
Negro | -0.324 |
Jama | -0.320 |
Token | the |
Token ID | 262 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Alam | +0.238 |
Antar | +0.231 |
Aman | +0.213 |
Negro | +0.208 |
Jama | +0.206 |
Neg logit contributions | |
ikes | -0.230 |
Stras | -0.206 |
hene | -0.206 |
Spr | -0.204 |
Stage | -0.199 |
Token | Palestinians |
Token ID | 12890 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ikes | +1.312 |
Stras | +1.192 |
hene | +1.175 |
Spr | +1.163 |
saddle | +1.144 |
Neg logit contributions | |
Alam | -1.389 |
Antar | -1.343 |
Aman | -1.229 |
Negro | -1.205 |
Malays | -1.196 |
Token | have |
Token ID | 423 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ikes | +1.127 |
Stras | +1.023 |
hene | +1.012 |
Spr | +0.997 |
saddle | +0.994 |
Neg logit contributions | |
Alam | -1.106 |
Antar | -1.072 |
Aman | -0.980 |
Negro | -0.961 |
Jama | -0.948 |
Token | is |
Token ID | 318 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
ikes | +0.146 |
Stras | +0.131 |
hene | +0.130 |
Spr | +0.128 |
Stage | +0.126 |
Neg logit contributions | |
Alam | -0.160 |
Antar | -0.156 |
Aman | -0.143 |
Negro | -0.140 |
Jama | -0.139 |
Token | to |
Token ID | 284 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
Alam | +0.341 |
Antar | +0.330 |
Aman | +0.303 |
Negro | +0.297 |
Jama | +0.293 |
Neg logit contributions | |
ikes | -0.354 |
Stras | -0.318 |
hene | -0.318 |
Spr | -0.314 |
Stage | -0.308 |
Token | accept |
Token ID | 2453 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Alam | +0.074 |
Antar | +0.071 |
Aman | +0.065 |
Negro | +0.064 |
Jama | +0.063 |
Neg logit contributions | |
ikes | -0.081 |
Stras | -0.073 |
hene | -0.073 |
Spr | -0.072 |
Stage | -0.071 |
Token | the |
Token ID | 262 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
ikes | +0.203 |
Stras | +0.183 |
hene | +0.182 |
Spr | +0.180 |
Stage | +0.177 |
Neg logit contributions | |
Alam | -0.193 |
Antar | -0.187 |
Aman | -0.171 |
Negro | -0.168 |
Jama | -0.166 |
Token | outcome |
Token ID | 8055 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
ikes | +0.028 |
Stras | +0.025 |
hene | +0.025 |
Spr | +0.025 |
Stage | +0.024 |
Neg logit contributions | |
Alam | -0.028 |
Antar | -0.027 |
Aman | -0.025 |
Negro | -0.024 |
Jama | -0.024 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Alam | +2.050 |
Antar | +1.986 |
Aman | +1.832 |
Negro | +1.792 |
Jama | +1.774 |
Neg logit contributions | |
ikes | -2.034 |
hene | -1.817 |
Stras | -1.804 |
Spr | -1.801 |
Stage | -1.751 |
Token | by |
Token ID | 416 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ikes | +1.758 |
Stras | +1.587 |
hene | +1.575 |
Spr | +1.552 |
saddle | +1.525 |
Neg logit contributions | |
Alam | -2.011 |
Antar | -1.951 |
Aman | -1.797 |
Negro | -1.764 |
Jama | -1.747 |
Token | Zionist |
Token ID | 29390 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Alam | +1.489 |
Antar | +1.444 |
Aman | +1.336 |
Negro | +1.300 |
Jama | +1.290 |
Neg logit contributions | |
ikes | -1.500 |
hene | -1.351 |
Stras | -1.323 |
Spr | -1.323 |
Stage | -1.290 |
Token | an |
Token ID | 281 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ikes | +0.604 |
Stras | +0.545 |
hene | +0.543 |
Spr | +0.537 |
Stage | +0.526 |
Neg logit contributions | |
Alam | -0.583 |
Antar | -0.564 |
Aman | -0.516 |
Negro | -0.504 |
Jama | -0.499 |
Token | oxy |
Token ID | 10661 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Alam | +1.868 |
Antar | +1.801 |
Aman | +1.676 |
Negro | +1.641 |
Jama | +1.618 |
Neg logit contributions | |
ikes | -1.836 |
Stras | -1.652 |
hene | -1.648 |
Spr | -1.635 |
Stage | -1.612 |
Token | mor |
Token ID | 4491 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Alam | +2.590 |
Antar | +2.507 |
Aman | +2.318 |
Negro | +2.273 |
Jama | +2.244 |
Neg logit contributions | |
ikes | -2.391 |
Stras | -2.142 |
hene | -2.128 |
Spr | -2.106 |
Stage | -2.064 |
Token | on |
Token ID | 261 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
Alam | +0.296 |
Antar | +0.287 |
Aman | +0.263 |
Negro | +0.258 |
Jama | +0.255 |
Neg logit contributions | |
ikes | -0.292 |
Stras | -0.263 |
hene | -0.262 |
Spr | -0.259 |
Stage | -0.254 |
Token | ). |
Token ID | 737 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
Alam | +1.764 |
Antar | +1.703 |
Aman | +1.577 |
Negro | +1.550 |
Jama | +1.527 |
Neg logit contributions | |
ikes | -1.749 |
hene | -1.578 |
Stras | -1.573 |
Spr | -1.553 |
Stage | -1.526 |
Token | The |
Token ID | 383 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Alam | +0.660 |
Antar | +0.640 |
Aman | +0.591 |
Negro | +0.580 |
Jama | +0.573 |
Neg logit contributions | |
ikes | -0.628 |
hene | -0.562 |
Stras | -0.561 |
Spr | -0.553 |
saddle | -0.543 |
Token | much |
Token ID | 881 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Alam | +0.258 |
Antar | +0.250 |
Aman | +0.229 |
Negro | +0.225 |
Jama | +0.222 |
Neg logit contributions | |
ikes | -0.269 |
Stras | -0.242 |
hene | -0.242 |
Spr | -0.239 |
Stage | -0.234 |
Token | v |
Token ID | 410 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Alam | +1.775 |
Antar | +1.717 |
Aman | +1.581 |
Negro | +1.557 |
Jama | +1.536 |
Neg logit contributions | |
ikes | -1.839 |
Stras | -1.659 |
hene | -1.657 |
Spr | -1.640 |
Stage | -1.604 |
Token | aunted |
Token ID | 20227 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
Alam | +2.013 |
Antar | +1.941 |
Aman | +1.804 |
Negro | +1.773 |
Jama | +1.741 |
Neg logit contributions | |
ikes | -1.916 |
Stras | -1.749 |
hene | -1.726 |
Spr | -1.710 |
Stage | -1.671 |
Token | " |
Token ID | 366 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Alam | +2.055 |
Antar | +1.983 |
Aman | +1.841 |
Negro | +1.817 |
Jama | +1.790 |
Neg logit contributions | |
ikes | -2.087 |
hene | -1.876 |
Stras | -1.864 |
Spr | -1.849 |
Stage | -1.818 |
Token | cons |
Token ID | 5936 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ikes | +0.983 |
Stras | +0.874 |
hene | +0.872 |
Spr | +0.861 |
Stage | +0.843 |
Neg logit contributions | |
Alam | -1.180 |
Antar | -1.147 |
Aman | -1.061 |
Negro | -1.040 |
Jama | -1.031 |
Token | Stephen |
Token ID | 7970 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Alam | +0.226 |
Antar | +0.219 |
Aman | +0.200 |
Negro | +0.196 |
Jama | +0.193 |
Neg logit contributions | |
ikes | -0.252 |
Stras | -0.227 |
hene | -0.227 |
Spr | -0.224 |
Stage | -0.220 |
Token | and |
Token ID | 290 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ikes | +1.901 |
Stras | +1.738 |
hene | +1.709 |
Spr | +1.700 |
Stage | +1.666 |
Neg logit contributions | |
Alam | -1.741 |
Antar | -1.690 |
Aman | -1.541 |
Negro | -1.506 |
Malays | -1.500 |
Token | Mary |
Token ID | 5335 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Alam | +0.375 |
Antar | +0.363 |
Aman | +0.335 |
Negro | +0.328 |
Jama | +0.324 |
Neg logit contributions | |
ikes | -0.367 |
hene | -0.328 |
Stras | -0.327 |
Spr | -0.324 |
Stage | -0.317 |
Token | Birch |
Token ID | 47631 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
ikes | +1.025 |
Stras | +0.935 |
hene | +0.924 |
Spr | +0.916 |
Stage | +0.901 |
Neg logit contributions | |
Alam | -0.917 |
Antar | -0.888 |
Aman | -0.808 |
Negro | -0.791 |
Malays | -0.785 |
Token | Texas |
Token ID | 3936 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Alam | +0.286 |
Antar | +0.277 |
Aman | +0.255 |
Negro | +0.249 |
Jama | +0.247 |
Neg logit contributions | |
ikes | -0.279 |
Stras | -0.250 |
hene | -0.250 |
Spr | -0.247 |
Stage | -0.242 |
Token | Theater |
Token ID | 22207 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
ikes | +0.989 |
Stras | +0.886 |
hene | +0.879 |
Spr | +0.870 |
Stage | +0.854 |
Neg logit contributions | |
Alam | -1.157 |
Antar | -1.124 |
Aman | -1.040 |
Negro | -1.018 |
Jama | -1.010 |
Token | , |
Token ID | 11 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
ikes | +0.037 |
Stras | +0.033 |
hene | +0.033 |
Spr | +0.032 |
Stage | +0.032 |
Neg logit contributions | |
Alam | -0.042 |
Antar | -0.041 |
Aman | -0.037 |
Negro | -0.037 |
Jama | -0.036 |
Token | for |
Token ID | 329 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
Alam | +0.615 |
Antar | +0.597 |
Aman | +0.551 |
Negro | +0.540 |
Jama | +0.535 |
Neg logit contributions | |
ikes | -0.550 |
Stras | -0.491 |
hene | -0.490 |
Spr | -0.483 |
Stage | -0.474 |
Token | over |
Token ID | 625 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
ikes | +0.555 |
Stras | +0.502 |
hene | +0.499 |
Spr | +0.494 |
Stage | +0.485 |
Neg logit contributions | |
Alam | -0.527 |
Antar | -0.512 |
Aman | -0.468 |
Negro | -0.457 |
Jama | -0.452 |
Token | 60 |
Token ID | 3126 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Alam | +0.661 |
Antar | +0.640 |
Aman | +0.586 |
Negro | +0.574 |
Jama | +0.567 |
Neg logit contributions | |
ikes | -0.696 |
Stras | -0.629 |
hene | -0.627 |
Spr | -0.620 |
Stage | -0.608 |
Token | years |
Token ID | 812 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ikes | +0.278 |
Stras | +0.253 |
hene | +0.252 |
Spr | +0.249 |
Stage | +0.244 |
Neg logit contributions | |
Alam | -0.244 |
Antar | -0.236 |
Aman | -0.215 |
Negro | -0.211 |
Jama | -0.208 |
Token | � |
Token ID | 447 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Alam | +0.337 |
Antar | +0.327 |
Aman | +0.302 |
Negro | +0.297 |
Jama | +0.294 |
Neg logit contributions | |
ikes | -0.287 |
Stras | -0.256 |
hene | -0.255 |
Spr | -0.251 |
Stage | -0.246 |
Token | � |
Token ID | 251 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
Alam | +0.924 |
Antar | +0.884 |
Aman | +0.788 |
Negro | +0.766 |
Jama | +0.753 |
Neg logit contributions | |
ikes | -1.527 |
Stras | -1.408 |
hene | -1.404 |
Spr | -1.389 |
Stage | -1.370 |
Token | the |
Token ID | 262 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
ikes | +0.642 |
Stras | +0.580 |
hene | +0.574 |
Spr | +0.570 |
Stage | +0.557 |
Neg logit contributions | |
Alam | -0.679 |
Antar | -0.662 |
Aman | -0.608 |
Negro | -0.593 |
Malays | -0.588 |
Token | writer |
Token ID | 6260 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ikes | +0.220 |
Stras | +0.199 |
hene | +0.198 |
Spr | +0.196 |
Stage | +0.193 |
Neg logit contributions | |
Alam | -0.204 |
Antar | -0.198 |
Aman | -0.181 |
Negro | -0.177 |
Jama | -0.174 |
Token | , |
Token ID | 11 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ikes | +0.859 |
Stras | +0.775 |
hene | +0.770 |
Spr | +0.762 |
Stage | +0.746 |
Neg logit contributions | |
Alam | -0.876 |
Antar | -0.852 |
Aman | -0.780 |
Negro | -0.766 |
Malays | -0.756 |
Token | Jim |
Token ID | 5395 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Alam | +1.632 |
Antar | +1.581 |
Aman | +1.460 |
Negro | +1.430 |
Jama | +1.422 |
Neg logit contributions | |
ikes | -1.522 |
hene | -1.353 |
Stras | -1.352 |
Spr | -1.334 |
Stage | -1.310 |
Token | Quinn |
Token ID | 16109 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
ikes | +1.274 |
Stras | +1.160 |
hene | +1.149 |
Spr | +1.134 |
Stage | +1.115 |
Neg logit contributions | |
Alam | -1.146 |
Antar | -1.108 |
Aman | -1.012 |
Negro | -0.990 |
Malays | -0.981 |
Token | , |
Token ID | 11 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
ikes | +0.232 |
Stras | +0.208 |
hene | +0.207 |
Spr | +0.205 |
Stage | +0.200 |
Neg logit contributions | |
Alam | -0.255 |
Antar | -0.248 |
Aman | -0.228 |
Negro | -0.224 |
Jama | -0.221 |
Token | continued |
Token ID | 3767 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Alam | +0.434 |
Antar | +0.420 |
Aman | +0.386 |
Negro | +0.378 |
Jama | +0.374 |
Neg logit contributions | |
ikes | -0.428 |
Stras | -0.385 |
hene | -0.384 |
Spr | -0.379 |
Stage | -0.372 |
Token | . |
Token ID | 13 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
Alam | +1.702 |
Antar | +1.650 |
Aman | +1.520 |
Negro | +1.487 |
Jama | +1.479 |
Neg logit contributions | |
ikes | -1.568 |
hene | -1.402 |
Stras | -1.397 |
Spr | -1.377 |
Stage | -1.350 |
Token | � |
Token ID | 564 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Alam | +0.841 |
Antar | +0.816 |
Aman | +0.757 |
Negro | +0.744 |
Jama | +0.737 |
Neg logit contributions | |
ikes | -0.673 |
hene | -0.595 |
Stras | -0.595 |
Spr | -0.585 |
Stage | -0.573 |
Token | � |
Token ID | 250 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
ikes | +0.138 |
Stras | +0.124 |
hene | +0.124 |
Spr | +0.122 |
Stage | +0.120 |
Neg logit contributions | |
Alam | -0.130 |
Antar | -0.126 |
Aman | -0.115 |
Negro | -0.113 |
Jama | -0.112 |
Token | The |
Token ID | 464 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Alam | +0.895 |
Antar | +0.866 |
Aman | +0.811 |
Negro | +0.797 |
Jama | +0.787 |
Neg logit contributions | |
ikes | -0.670 |
Stras | -0.595 |
hene | -0.591 |
Spr | -0.573 |
saddle | -0.568 |
Token | Planes |
Token ID | 42788 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
Alam | +1.547 |
Antar | +1.495 |
Aman | +1.367 |
Negro | +1.347 |
Jama | +1.325 |
Neg logit contributions | |
ikes | -1.654 |
Stras | -1.494 |
hene | -1.494 |
Spr | -1.472 |
Stage | -1.443 |
Token | that |
Token ID | 326 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
ikes | +0.717 |
Stras | +0.642 |
hene | +0.640 |
Spr | +0.632 |
Stage | +0.619 |
Neg logit contributions | |
Alam | -0.790 |
Antar | -0.767 |
Aman | -0.707 |
Negro | -0.693 |
Jama | -0.686 |
Token | Ye |
Token ID | 11609 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Alam | +0.381 |
Antar | +0.369 |
Aman | +0.341 |
Negro | +0.335 |
Jama | +0.330 |
Neg logit contributions | |
ikes | -0.344 |
Stras | -0.307 |
hene | -0.307 |
Spr | -0.303 |
Stage | -0.297 |
Token | ager |
Token ID | 3536 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Alam | +1.873 |
Antar | +1.796 |
Aman | +1.687 |
Negro | +1.649 |
Jama | +1.623 |
Neg logit contributions | |
ikes | -1.505 |
Stras | -1.354 |
hene | -1.341 |
Spr | -1.332 |
EStreamFrame | -1.296 |
Token | Fle |
Token ID | 12005 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
Alam | +1.884 |
Antar | +1.813 |
Aman | +1.680 |
Negro | +1.642 |
Jama | +1.624 |
Neg logit contributions | |
ikes | -1.796 |
hene | -1.619 |
Stras | -1.612 |
Spr | -1.598 |
Stage | -1.571 |
Token | w |
Token ID | 86 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ikes | +0.489 |
hene | +0.420 |
Stras | +0.418 |
Spr | +0.408 |
Stage | +0.396 |
Neg logit contributions | |
Alam | -0.894 |
Antar | -0.875 |
Aman | -0.816 |
Negro | -0.805 |
Jama | -0.799 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ikes | +0.166 |
Stras | +0.149 |
hene | +0.148 |
Spr | +0.146 |
Stage | +0.144 |
Neg logit contributions | |
Alam | -0.172 |
Antar | -0.167 |
Aman | -0.153 |
Negro | -0.150 |
Jama | -0.149 |
Token | � |
Token ID | 447 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Alam | +0.161 |
Antar | +0.156 |
Aman | +0.145 |
Negro | +0.142 |
Jama | +0.141 |
Neg logit contributions | |
ikes | -0.130 |
Stras | -0.116 |
hene | -0.116 |
Spr | -0.114 |
Stage | -0.111 |
Token | � |
Token ID | 251 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ikes | +2.519 |
Stras | +2.315 |
hene | +2.309 |
Spr | +2.294 |
Stage | +2.262 |
Neg logit contributions | |
Alam | -1.422 |
Antar | -1.365 |
Aman | -1.205 |
Negro | -1.171 |
Jama | -1.152 |
Token | with |
Token ID | 351 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Alam | +1.397 |
Antar | +1.351 |
Aman | +1.252 |
Negro | +1.221 |
Jama | +1.219 |
Neg logit contributions | |
ikes | -1.405 |
hene | -1.258 |
Stras | -1.250 |
Spr | -1.249 |
Stage | -1.219 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ikes | +0.451 |
Stras | +0.406 |
hene | +0.406 |
Spr | +0.401 |
Stage | +0.394 |
Neg logit contributions | |
Alam | -0.432 |
Antar | -0.418 |
Aman | -0.383 |
Negro | -0.375 |
Jama | -0.371 |
Token | chance |
Token ID | 2863 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Alam | +0.099 |
Antar | +0.096 |
Aman | +0.088 |
Negro | +0.086 |
Jama | +0.085 |
Neg logit contributions | |
ikes | -0.103 |
Stras | -0.093 |
hene | -0.093 |
Spr | -0.092 |
Stage | -0.090 |
Token | for |
Token ID | 329 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ikes | +1.435 |
Stras | +1.295 |
hene | +1.283 |
Spr | +1.267 |
Stage | +1.243 |
Neg logit contributions | |
Alam | -1.536 |
Antar | -1.488 |
Aman | -1.370 |
Negro | -1.346 |
Malays | -1.332 |
Token | 30 |
Token ID | 1542 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
ikes | +1.700 |
Stras | +1.544 |
hene | +1.525 |
Spr | +1.508 |
Stage | +1.481 |
Neg logit contributions | |
Alam | -1.666 |
Antar | -1.616 |
Aman | -1.477 |
Negro | -1.452 |
negro | -1.433 |
Token | - |
Token ID | 12 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ikes | +0.411 |
Stras | +0.370 |
hene | +0.369 |
Spr | +0.365 |
Stage | +0.358 |
Neg logit contributions | |
Alam | -0.406 |
Antar | -0.393 |
Aman | -0.361 |
Negro | -0.353 |
Jama | -0.349 |
Token | plus |
Token ID | 9541 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Alam | +1.761 |
Antar | +1.710 |
Aman | +1.607 |
Negro | +1.580 |
Jama | +1.566 |
Neg logit contributions | |
ikes | -1.212 |
Stras | -1.076 |
hene | -1.049 |
Spr | -1.030 |
saddle | -1.016 |
Token | points |
Token ID | 2173 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Alam | +0.800 |
Antar | +0.772 |
Aman | +0.709 |
Negro | +0.692 |
Jama | +0.686 |
Neg logit contributions | |
ikes | -0.924 |
Stras | -0.837 |
hene | -0.835 |
Spr | -0.831 |
Stage | -0.812 |
Token | like |
Token ID | 588 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Alam | +0.907 |
Antar | +0.877 |
Aman | +0.811 |
Negro | +0.791 |
Jama | +0.789 |
Neg logit contributions | |
ikes | -0.889 |
hene | -0.795 |
Stras | -0.792 |
Spr | -0.789 |
Stage | -0.771 |
Token | we |
Token ID | 356 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
Alam | +0.793 |
Antar | +0.767 |
Aman | +0.706 |
Jama | +0.687 |
Negro | +0.685 |
Neg logit contributions | |
ikes | -0.857 |
hene | -0.772 |
Stras | -0.767 |
Spr | -0.765 |
Stage | -0.751 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Alam | +2.189 |
Antar | +2.127 |
Aman | +1.969 |
Negro | +1.915 |
Jama | +1.909 |
Neg logit contributions | |
ikes | -2.197 |
Stras | -2.013 |
Spr | -1.991 |
hene | -1.981 |
Stage | -1.937 |
Token | Phant |
Token ID | 38699 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
ikes | +1.415 |
Stras | +1.262 |
hene | +1.254 |
Spr | +1.245 |
Stage | +1.224 |
Neg logit contributions | |
Alam | -1.502 |
Antar | -1.458 |
Aman | -1.336 |
Negro | -1.315 |
Jama | -1.303 |
Token | oms |
Token ID | 3150 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
Alam | +0.367 |
Antar | +0.354 |
Aman | +0.326 |
Negro | +0.318 |
Jama | +0.315 |
Neg logit contributions | |
ikes | -0.384 |
Stras | -0.348 |
hene | -0.348 |
Spr | -0.343 |
Stage | -0.337 |
Token | more |
Token ID | 517 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Alam | +0.503 |
Antar | +0.487 |
Aman | +0.448 |
Negro | +0.437 |
Jama | +0.433 |
Neg logit contributions | |
ikes | -0.520 |
Stras | -0.469 |
hene | -0.469 |
Spr | -0.464 |
Stage | -0.454 |
Token | bass |
Token ID | 12702 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Alam | +0.327 |
Antar | +0.316 |
Aman | +0.290 |
Negro | +0.283 |
Jama | +0.280 |
Neg logit contributions | |
ikes | -0.350 |
Stras | -0.316 |
hene | -0.315 |
Spr | -0.312 |
Stage | -0.306 |
Token | slam |
Token ID | 21158 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Alam | +1.493 |
Antar | +1.446 |
Aman | +1.342 |
Negro | +1.308 |
Jama | +1.300 |
Neg logit contributions | |
ikes | -1.451 |
Stras | -1.313 |
hene | -1.306 |
Spr | -1.291 |
Stage | -1.253 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Alam | +2.460 |
Antar | +2.376 |
Aman | +2.218 |
Jama | +2.144 |
Negro | +2.140 |
Neg logit contributions | |
ikes | -2.474 |
Stras | -2.263 |
hene | -2.237 |
Spr | -2.224 |
Stage | -2.159 |
Token | better |
Token ID | 1365 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Alam | +1.020 |
Antar | +0.987 |
Aman | +0.911 |
Negro | +0.887 |
Jama | +0.881 |
Neg logit contributions | |
ikes | -1.074 |
hene | -0.969 |
Stras | -0.965 |
Spr | -0.957 |
Stage | -0.936 |
Token | imaging |
Token ID | 19560 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
ikes | +0.101 |
Stras | +0.092 |
hene | +0.091 |
Spr | +0.090 |
Stage | +0.089 |
Neg logit contributions | |
Alam | -0.094 |
Antar | -0.091 |
Aman | -0.083 |
Negro | -0.081 |
Jama | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Alam | +0.751 |
Antar | +0.725 |
Aman | +0.673 |
Negro | +0.655 |
Jama | +0.648 |
Neg logit contributions | |
ikes | -0.737 |
hene | -0.663 |
Stras | -0.661 |
Spr | -0.653 |
Stage | -0.638 |
Token | But |
Token ID | 887 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Alam | +1.102 |
Antar | +1.068 |
Aman | +0.989 |
Negro | +0.966 |
Jama | +0.957 |
Neg logit contributions | |
ikes | -1.014 |
hene | -0.906 |
Stras | -0.903 |
Spr | -0.889 |
saddle | -0.872 |
Token | in |
Token ID | 287 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
Alam | +0.909 |
Antar | +0.879 |
Aman | +0.807 |
Negro | +0.787 |
Jama | +0.779 |
Neg logit contributions | |
ikes | -0.987 |
hene | -0.891 |
Stras | -0.890 |
Spr | -0.881 |
Stage | -0.863 |
Token | np |
Token ID | 37659 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Alam | +2.978 |
Antar | +2.891 |
Aman | +2.724 |
Negro | +2.674 |
Jama | +2.666 |
Neg logit contributions | |
ikes | -1.661 |
Stras | -1.431 |
hene | -1.411 |
Spr | -1.373 |
saddle | -1.355 |
Token | - |
Token ID | 12 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
ikes | +1.569 |
Stras | +1.402 |
hene | +1.401 |
Spr | +1.376 |
Stage | +1.349 |
Neg logit contributions | |
Alam | -1.794 |
Antar | -1.736 |
Aman | -1.609 |
Negro | -1.578 |
Jama | -1.561 |
Token | related |
Token ID | 5363 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
Alam | +0.056 |
Antar | +0.054 |
Aman | +0.050 |
Negro | +0.049 |
Jama | +0.049 |
Neg logit contributions | |
ikes | -0.043 |
Stras | -0.038 |
hene | -0.038 |
Spr | -0.038 |
Stage | -0.037 |
Token | ] |
Token ID | 60 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Alam | +0.599 |
Antar | +0.580 |
Aman | +0.528 |
Negro | +0.515 |
Jama | +0.509 |
Neg logit contributions | |
ikes | -0.782 |
hene | -0.712 |
Stras | -0.710 |
Spr | -0.705 |
Stage | -0.691 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
ikes | +2.019 |
Stras | +1.778 |
hene | +1.766 |
Spr | +1.745 |
Stage | +1.701 |
Neg logit contributions | |
Alam | -2.886 |
Antar | -2.817 |
Aman | -2.615 |
Negro | -2.572 |
Jama | -2.546 |
Token | The |
Token ID | 464 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ikes | +0.080 |
Stras | +0.071 |
hene | +0.071 |
Spr | +0.069 |
saddle | +0.068 |
Neg logit contributions | |
Alam | -0.103 |
Antar | -0.100 |
Aman | -0.093 |
Negro | -0.091 |
Jama | -0.090 |
Token | Chicago |
Token ID | 4842 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Alam | +0.816 |
Antar | +0.789 |
Aman | +0.724 |
Negro | +0.710 |
Jama | +0.703 |
Neg logit contributions | |
ikes | -0.842 |
hene | -0.758 |
Stras | -0.756 |
Spr | -0.749 |
Stage | -0.736 |
Token | Bears |
Token ID | 15682 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Alam | +1.252 |
Antar | +1.211 |
Aman | +1.103 |
Negro | +1.090 |
Jama | +1.070 |
Neg logit contributions | |
ikes | -1.436 |
Stras | -1.296 |
hene | -1.293 |
Spr | -1.282 |
Stage | -1.259 |
Token | have |
Token ID | 423 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Alam | +0.323 |
Antar | +0.312 |
Aman | +0.286 |
Negro | +0.280 |
Jama | +0.278 |
Neg logit contributions | |
ikes | -0.349 |
Stras | -0.315 |
hene | -0.314 |
Spr | -0.311 |
Stage | -0.306 |
Token | blocked |
Token ID | 10226 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
ikes | +1.180 |
Stras | +1.074 |
hene | +1.065 |
Spr | +1.049 |
saddle | +1.032 |
Neg logit contributions | |
Alam | -1.127 |
Antar | -1.092 |
Aman | -0.997 |
Negro | -0.973 |
Malays | -0.964 |
Token | outside |
Token ID | 2354 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Alam | +0.497 |
Antar | +0.479 |
Aman | +0.441 |
Negro | +0.432 |
Jama | +0.431 |
Neg logit contributions | |
ikes | -0.532 |
hene | -0.482 |
Stras | -0.477 |
Spr | -0.475 |
Stage | -0.468 |
Token | her |
Token ID | 607 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Alam | +1.148 |
Antar | +1.099 |
Aman | +1.008 |
Negro | +0.981 |
Jama | +0.968 |
Neg logit contributions | |
ikes | -1.557 |
hene | -1.426 |
Stras | -1.405 |
Spr | -1.404 |
Stage | -1.378 |
Token | movie |
Token ID | 3807 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
Alam | +2.232 |
Antar | +2.141 |
Aman | +2.007 |
Negro | +1.971 |
Jama | +1.955 |
Neg logit contributions | |
ikes | -2.295 |
hene | -2.073 |
Stras | -2.048 |
Spr | -2.047 |
Stage | -2.017 |
Token | star |
Token ID | 3491 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Alam | +0.476 |
Antar | +0.460 |
Aman | +0.426 |
Negro | +0.419 |
Jama | +0.412 |
Neg logit contributions | |
ikes | -0.469 |
hene | -0.421 |
Stras | -0.421 |
Spr | -0.416 |
Stage | -0.407 |
Token | looks |
Token ID | 3073 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Alam | +0.221 |
Antar | +0.214 |
Aman | +0.197 |
Negro | +0.193 |
Jama | +0.191 |
Neg logit contributions | |
ikes | -0.219 |
Stras | -0.197 |
hene | -0.197 |
Spr | -0.195 |
Stage | -0.191 |
Token | in |
Token ID | 287 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Alam | +1.638 |
Antar | +1.580 |
Aman | +1.468 |
Negro | +1.440 |
Jama | +1.426 |
Neg logit contributions | |
ikes | -1.516 |
Stras | -1.355 |
hene | -1.351 |
Spr | -1.343 |
Stage | -1.315 |
Token | the |
Token ID | 262 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Alam | +1.471 |
Antar | +1.419 |
Aman | +1.306 |
Negro | +1.275 |
Jama | +1.262 |
Neg logit contributions | |
ikes | -1.636 |
hene | -1.486 |
Stras | -1.468 |
Spr | -1.458 |
Stage | -1.433 |
Token | process |
Token ID | 1429 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Alam | +0.495 |
Antar | +0.481 |
Aman | +0.446 |
Negro | +0.439 |
Jama | +0.435 |
Neg logit contributions | |
ikes | -0.415 |
hene | -0.370 |
Stras | -0.367 |
Spr | -0.363 |
Stage | -0.355 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ikes | +1.073 |
Stras | +0.956 |
hene | +0.951 |
Spr | +0.938 |
Stage | +0.919 |
Neg logit contributions | |
Alam | -1.310 |
Antar | -1.273 |
Aman | -1.177 |
Negro | -1.156 |
Malays | -1.146 |
Token | She |
Token ID | 1375 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Alam | +0.903 |
Antar | +0.868 |
Aman | +0.808 |
Negro | +0.792 |
Jama | +0.782 |
Neg logit contributions | |
ikes | -0.845 |
hene | -0.755 |
Stras | -0.743 |
Spr | -0.739 |
saddle | -0.733 |
Token | was |
Token ID | 373 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
Alam | +0.916 |
Antar | +0.882 |
Aman | +0.809 |
Negro | +0.791 |
Jama | +0.780 |
Neg logit contributions | |
ikes | -1.076 |
hene | -0.974 |
Stras | -0.972 |
Spr | -0.969 |
Stage | -0.948 |
Token | also |
Token ID | 635 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
ikes | +0.810 |
Stras | +0.732 |
hene | +0.729 |
Spr | +0.720 |
Stage | +0.707 |
Neg logit contributions | |
Alam | -0.775 |
Antar | -0.751 |
Aman | -0.687 |
Negro | -0.673 |
Jama | -0.665 |
Token | . |
Token ID | 13 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
Alam | +0.406 |
Antar | +0.380 |
Aman | +0.363 |
Negro | +0.358 |
Jama | +0.352 |
Neg logit contributions | |
ikes | -0.385 |
Stras | -0.348 |
hene | -0.345 |
Spr | -0.338 |
saddle | -0.338 |
Token | 169 |
Token ID | 22172 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ikes | +0.421 |
Stras | +0.372 |
hene | +0.365 |
Spr | +0.353 |
saddle | +0.353 |
Neg logit contributions | |
Alam | -0.733 |
Antar | -0.702 |
Aman | -0.669 |
Negro | -0.666 |
Jama | -0.658 |
Token | 11 |
Token ID | 1367 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
Alam | +1.976 |
Antar | +1.885 |
Aman | +1.756 |
Negro | +1.709 |
Jama | +1.708 |
Neg logit contributions | |
ikes | -1.999 |
hene | -1.799 |
Stras | -1.770 |
Spr | -1.758 |
saddle | -1.743 |
Token | 66 |
Token ID | 2791 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
ikes | +0.195 |
Stras | +0.175 |
hene | +0.175 |
Spr | +0.172 |
saddle | +0.169 |
Neg logit contributions | |
Alam | -0.204 |
Antar | -0.197 |
Aman | -0.182 |
Negro | -0.178 |
Jama | -0.176 |
Token | 589 |
Token ID | 44169 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Alam | +2.936 |
Antar | +2.812 |
Aman | +2.653 |
Negro | +2.573 |
Jama | +2.542 |
Neg logit contributions | |
ikes | -2.373 |
Stras | -2.132 |
hene | -2.125 |
Spr | -2.074 |
saddle | -2.052 |
Token | x |
Token ID | 2124 |
Feature activation | -6.39e+00 |
Pos logit contributions | |
Alam | +1.683 |
Antar | +1.535 |
Aman | +1.431 |
Negro | +1.390 |
Jama | +1.359 |
Neg logit contributions | |
ikes | -2.762 |
hene | -2.528 |
Stras | -2.506 |
Spr | -2.480 |
Stage | -2.455 |
Token | . |
Token ID | 13 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
Alam | +4.677 |
Aman | +4.075 |
Negro | +4.035 |
Jama | +3.937 |
Antar | +3.929 |
Neg logit contributions | |
ikes | -5.580 |
hene | -5.031 |
Stras | -5.000 |
saddle | -4.942 |
EStreamFrame | -4.879 |
Token | x |
Token ID | 87 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Alam | +2.145 |
Antar | +1.792 |
Aman | +1.767 |
Negro | +1.740 |
Jama | +1.649 |
Neg logit contributions | |
ikes | -4.233 |
Stras | -3.952 |
hene | -3.878 |
saddle | -3.868 |
Spr | -3.807 |
Token | . |
Token ID | 13 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
Alam | +2.193 |
Antar | +1.992 |
Aman | +1.947 |
Negro | +1.917 |
Jama | +1.881 |
Neg logit contributions | |
ikes | -2.215 |
Stras | -1.991 |
hene | -1.988 |
saddle | -1.947 |
Spr | -1.940 |
Token | x |
Token ID | 87 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
Alam | +0.394 |
Antar | +0.359 |
Aman | +0.333 |
Negro | +0.327 |
Jama | +0.318 |
Neg logit contributions | |
ikes | -0.680 |
Stras | -0.632 |
hene | -0.624 |
Spr | -0.616 |
saddle | -0.616 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Alam | +0.059 |
Antar | +0.056 |
Aman | +0.053 |
Negro | +0.052 |
Jama | +0.051 |
Neg logit contributions | |
ikes | -0.055 |
Stras | -0.050 |
hene | -0.049 |
Spr | -0.048 |
saddle | -0.048 |
Token | fn |
Token ID | 24714 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
Alam | +3.259 |
Antar | +3.128 |
Aman | +2.854 |
Negro | +2.787 |
Jama | +2.745 |
Neg logit contributions | |
ikes | -3.911 |
Stras | -3.552 |
hene | -3.548 |
Spr | -3.499 |
Stage | -3.437 |
Token | null |
Token ID | 9242 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Alam | +4.733 |
Antar | +4.515 |
Aman | +4.188 |
Negro | +4.057 |
negro | +4.025 |
Neg logit contributions | |
ikes | -4.934 |
Stras | -4.453 |
hene | -4.422 |
Spr | -4.409 |
Stage | -4.294 |
Token | () |
Token ID | 7499 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
Alam | +1.364 |
Antar | +1.323 |
Aman | +1.230 |
Negro | +1.205 |
Jama | +1.190 |
Neg logit contributions | |
ikes | -1.031 |
Stras | -0.918 |
hene | -0.913 |
Spr | -0.894 |
saddle | -0.873 |
Token | -> |
Token ID | 4613 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Alam | +3.599 |
Antar | +3.343 |
Aman | +3.092 |
Negro | +3.014 |
negro | +2.958 |
Neg logit contributions | |
ikes | -4.803 |
hene | -4.423 |
Stras | -4.420 |
Spr | -4.318 |
Stage | -4.264 |
Token | Atomic |
Token ID | 28976 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Alam | +1.483 |
Antar | +1.433 |
Aman | +1.290 |
Negro | +1.258 |
Jama | +1.242 |
Neg logit contributions | |
ikes | -2.075 |
Stras | -1.896 |
hene | -1.891 |
Spr | -1.873 |
Stage | -1.842 |
Token | < |
Token ID | 1279 |
Feature activation | -9.12e+00 |
Pos logit contributions | |
Alam | +2.481 |
Antar | +2.349 |
Aman | +2.084 |
Negro | +2.022 |
Jama | +1.968 |
Neg logit contributions | |
ikes | -4.453 |
Stras | -4.152 |
hene | -4.119 |
Spr | -4.042 |
saddle | -4.017 |
Token | T |
Token ID | 309 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
Alam | +5.430 |
Antar | +5.108 |
Aman | +4.565 |
Negro | +4.413 |
negro | +4.270 |
Neg logit contributions | |
ikes | -9.083 |
Stras | -8.390 |
hene | -8.372 |
Spr | -8.199 |
saddle | -8.128 |
Token | > |
Token ID | 1875 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
Alam | +3.788 |
Antar | +3.613 |
Aman | +3.370 |
Negro | +3.278 |
negro | +3.233 |
Neg logit contributions | |
ikes | -3.385 |
Stras | -3.068 |
hene | -3.048 |
Spr | -3.005 |
saddle | -2.940 |
Token | ; |
Token ID | 2162 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
Alam | +2.971 |
Antar | +2.786 |
Aman | +2.476 |
Negro | +2.404 |
negro | +2.349 |
Neg logit contributions | |
ikes | -5.515 |
Stras | -5.155 |
hene | -5.108 |
Spr | -5.056 |
Stage | -4.982 |
Token | } |
Token ID | 1782 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Alam | +4.913 |
Antar | +4.670 |
Aman | +4.332 |
Negro | +4.251 |
negro | +4.166 |
Neg logit contributions | |
ikes | -4.734 |
Stras | -4.244 |
hene | -4.217 |
Spr | -4.190 |
Stage | -4.104 |
Token |
|
Token ID | 198 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
Alam | +1.134 |
Antar | +1.097 |
Aman | +0.993 |
Negro | +0.970 |
Jama | +0.959 |
Neg logit contributions | |
ikes | -1.452 |
Stras | -1.323 |
hene | -1.320 |
Spr | -1.305 |
Stage | -1.283 |
Token | your |
Token ID | 534 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ikes | +0.175 |
hene | +0.157 |
Stras | +0.157 |
Spr | +0.156 |
Stage | +0.152 |
Neg logit contributions | |
Alam | -0.173 |
Antar | -0.168 |
Aman | -0.154 |
Negro | -0.151 |
Jama | -0.150 |
Token | point |
Token ID | 966 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Alam | +0.982 |
Antar | +0.949 |
Aman | +0.874 |
Negro | +0.863 |
Jama | +0.849 |
Neg logit contributions | |
ikes | -1.018 |
hene | -0.916 |
Stras | -0.916 |
Spr | -0.905 |
Stage | -0.884 |
Token | ? |
Token ID | 30 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Alam | +0.299 |
Antar | +0.290 |
Aman | +0.270 |
Negro | +0.265 |
Jama | +0.263 |
Neg logit contributions | |
ikes | -0.241 |
Stras | -0.214 |
hene | -0.213 |
Spr | -0.211 |
Stage | -0.206 |
Token | And |
Token ID | 843 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
Alam | +1.754 |
Antar | +1.693 |
Aman | +1.571 |
Negro | +1.541 |
Jama | +1.519 |
Neg logit contributions | |
ikes | -1.717 |
hene | -1.539 |
Stras | -1.530 |
Spr | -1.514 |
saddle | -1.477 |
Token | why |
Token ID | 1521 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
ikes | +0.390 |
Stras | +0.352 |
hene | +0.351 |
Spr | +0.347 |
Stage | +0.340 |
Neg logit contributions | |
Alam | -0.386 |
Antar | -0.374 |
Aman | -0.344 |
Negro | -0.337 |
Jama | -0.333 |
Token | are |
Token ID | 389 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
Alam | +2.249 |
Antar | +2.159 |
Aman | +1.988 |
Negro | +1.956 |
Jama | +1.935 |
Neg logit contributions | |
ikes | -2.507 |
hene | -2.274 |
Stras | -2.250 |
Spr | -2.241 |
EStreamFrame | -2.197 |
Token | you |
Token ID | 345 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Alam | +4.197 |
Antar | +4.006 |
Negro | +3.684 |
Aman | +3.666 |
negro | +3.621 |
Neg logit contributions | |
ikes | -5.295 |
hene | -4.889 |
Stras | -4.833 |
Spr | -4.825 |
Stage | -4.726 |
Token | here |
Token ID | 994 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Alam | +0.808 |
Antar | +0.782 |
Aman | +0.721 |
Negro | +0.707 |
Jama | +0.700 |
Neg logit contributions | |
ikes | -0.838 |
hene | -0.756 |
Stras | -0.754 |
Spr | -0.746 |
Stage | -0.732 |
Token | ? |
Token ID | 30 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
Alam | +1.519 |
Antar | +1.474 |
Aman | +1.372 |
Negro | +1.349 |
Jama | +1.336 |
Neg logit contributions | |
ikes | -1.183 |
hene | -1.051 |
Stras | -1.050 |
Spr | -1.033 |
Stage | -1.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Alam | +3.069 |
Antar | +2.952 |
Aman | +2.754 |
Negro | +2.696 |
Jama | +2.654 |
Neg logit contributions | |
ikes | -3.053 |
hene | -2.739 |
Stras | -2.708 |
Spr | -2.684 |
EStreamFrame | -2.648 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Alam | +1.709 |
Antar | +1.570 |
Aman | +1.537 |
Negro | +1.513 |
Jama | +1.488 |
Neg logit contributions | |
ikes | -1.453 |
hene | -1.295 |
Stras | -1.285 |
saddle | -1.250 |
Spr | -1.246 |
Token | is |
Token ID | 318 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Alam | +0.385 |
Antar | +0.373 |
Aman | +0.344 |
Negro | +0.337 |
Jama | +0.333 |
Neg logit contributions | |
ikes | -0.363 |
Stras | -0.325 |
hene | -0.324 |
Spr | -0.319 |
Stage | -0.313 |
Token | it |
Token ID | 340 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Alam | +2.354 |
Antar | +2.275 |
Aman | +2.083 |
Negro | +2.055 |
Jama | +2.019 |
Neg logit contributions | |
ikes | -2.650 |
Stras | -2.397 |
hene | -2.396 |
Spr | -2.349 |
saddle | -2.302 |
Token | ? |
Token ID | 30 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
ikes | +1.088 |
Stras | +0.969 |
hene | +0.964 |
Spr | +0.957 |
Stage | +0.935 |
Neg logit contributions | |
Alam | -1.297 |
Antar | -1.261 |
Aman | -1.166 |
Negro | -1.144 |
Jama | -1.133 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Alam | +2.574 |
Antar | +2.479 |
Aman | +2.281 |
Negro | +2.240 |
Jama | +2.204 |
Neg logit contributions | |
ikes | -2.658 |
hene | -2.392 |
Stras | -2.382 |
Spr | -2.334 |
Stage | -2.285 |
Token | : |
Token ID | 1058 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ikes | +1.568 |
Stras | +1.419 |
hene | +1.419 |
Spr | +1.414 |
Stage | +1.390 |
Neg logit contributions | |
Alam | -1.249 |
Antar | -1.206 |
Aman | -1.092 |
Negro | -1.063 |
Jama | -1.054 |
Token | [ |
Token ID | 685 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
Alam | +1.409 |
Antar | +1.365 |
Aman | +1.250 |
Negro | +1.223 |
Jama | +1.208 |
Neg logit contributions | |
ikes | -1.498 |
Stras | -1.353 |
hene | -1.351 |
Spr | -1.333 |
Stage | -1.309 |
Token | Option |
Token ID | 16018 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
Alam | +5.276 |
Antar | +5.114 |
Aman | +4.701 |
Negro | +4.590 |
Jama | +4.497 |
Neg logit contributions | |
ikes | -5.293 |
Stras | -4.777 |
hene | -4.769 |
Spr | -4.570 |
saddle | -4.568 |
Token | < |
Token ID | 1279 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
Alam | +3.027 |
Antar | +2.862 |
Aman | +2.608 |
Negro | +2.529 |
Jama | +2.494 |
Neg logit contributions | |
ikes | -4.344 |
hene | -4.005 |
Stras | -3.977 |
Spr | -3.881 |
saddle | -3.860 |
Token | Piece |
Token ID | 27053 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Alam | +2.705 |
Antar | +2.621 |
Aman | +2.418 |
Negro | +2.381 |
Jama | +2.335 |
Neg logit contributions | |
ikes | -2.572 |
hene | -2.305 |
Stras | -2.297 |
Spr | -2.243 |
saddle | -2.221 |
Token | > |
Token ID | 1875 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
ikes | +0.232 |
Stras | +0.207 |
hene | +0.206 |
Spr | +0.203 |
saddle | +0.198 |
Neg logit contributions | |
Alam | -0.264 |
Antar | -0.256 |
Aman | -0.237 |
Negro | -0.232 |
Jama | -0.229 |
Token | ; |
Token ID | 2162 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
Alam | +2.301 |
Antar | +2.188 |
Aman | +2.034 |
Negro | +1.979 |
Malays | +1.949 |
Neg logit contributions | |
ikes | -2.570 |
hene | -2.349 |
Stras | -2.336 |
Spr | -2.283 |
saddle | -2.250 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Alam | +0.321 |
Antar | +0.314 |
Aman | +0.292 |
Negro | +0.287 |
Jama | +0.284 |
Neg logit contributions | |
ikes | -0.227 |
Stras | -0.199 |
hene | -0.199 |
Spr | -0.196 |
Stage | -0.191 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Alam | +0.177 |
Antar | +0.167 |
Aman | +0.160 |
Negro | +0.157 |
Jama | +0.155 |
Neg logit contributions | |
ikes | -0.138 |
Stras | -0.122 |
hene | -0.122 |
Spr | -0.119 |
saddle | -0.117 |
Token | pub |
Token ID | 12984 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
Alam | +1.238 |
Antar | +1.190 |
Aman | +1.082 |
Negro | +1.055 |
Jama | +1.040 |
Neg logit contributions | |
ikes | -1.576 |
Stras | -1.441 |
hene | -1.432 |
Spr | -1.414 |
saddle | -1.391 |
Token | struct |
Token ID | 2878 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
Alam | +2.390 |
Antar | +2.295 |
Aman | +2.088 |
Negro | +2.039 |
Jama | +2.014 |
Neg logit contributions | |
ikes | -2.978 |
Stras | -2.712 |
hene | -2.706 |
Spr | -2.674 |
Stage | -2.628 |
Token | Atomic |
Token ID | 28976 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ikes | +0.561 |
Stras | +0.513 |
hene | +0.511 |
Spr | +0.505 |
Stage | +0.498 |
Neg logit contributions | |
Alam | -0.418 |
Antar | -0.410 |
Aman | -0.368 |
Negro | -0.360 |
Malays | -0.360 |
Token | < |
Token ID | 1279 |
Feature activation | -8.69e+00 |
Pos logit contributions | |
Alam | +0.265 |
Antar | +0.256 |
Aman | +0.227 |
Negro | +0.220 |
Malays | +0.218 |
Neg logit contributions | |
ikes | -0.445 |
hene | -0.406 |
Stras | -0.406 |
Spr | -0.406 |
Stage | -0.399 |
Token | T |
Token ID | 309 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Alam | +5.597 |
Antar | +5.303 |
Aman | +4.821 |
Negro | +4.678 |
negro | +4.523 |
Neg logit contributions | |
ikes | -8.255 |
Stras | -7.574 |
hene | -7.552 |
Spr | -7.477 |
Stage | -7.356 |
Token | > |
Token ID | 1875 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
Alam | +3.152 |
Antar | +3.014 |
Aman | +2.803 |
Negro | +2.735 |
Jama | +2.691 |
Neg logit contributions | |
ikes | -2.837 |
Stras | -2.558 |
hene | -2.549 |
Spr | -2.509 |
saddle | -2.457 |
Token | { |
Token ID | 1391 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
Alam | +2.706 |
Antar | +2.527 |
Aman | +2.239 |
Negro | +2.167 |
Jama | +2.108 |
Neg logit contributions | |
ikes | -5.338 |
Stras | -4.978 |
hene | -4.967 |
Spr | -4.897 |
Stage | -4.827 |
Token | ... |
Token ID | 2644 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Alam | +3.933 |
Antar | +3.713 |
Aman | +3.364 |
Negro | +3.263 |
negro | +3.179 |
Neg logit contributions | |
ikes | -5.891 |
Stras | -5.444 |
hene | -5.414 |
Spr | -5.345 |
Stage | -5.261 |
Token | } |
Token ID | 1782 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
Alam | +1.553 |
Antar | +1.505 |
Aman | +1.368 |
Negro | +1.339 |
Jama | +1.324 |
Neg logit contributions | |
ikes | -1.821 |
Stras | -1.651 |
hene | -1.647 |
Spr | -1.628 |
Stage | -1.601 |