Token | big |
Token ID | 1263 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
counters | +0.016 |
nam | +0.015 |
forward | +0.015 |
pans | +0.015 |
spec | +0.015 |
Neg logit contributions | |
zag | -0.025 |
gy | -0.021 |
sometime | -0.021 |
seek | -0.021 |
now | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
nam | +0.113 |
pans | +0.113 |
ding | +0.113 |
counters | +0.110 |
forward | +0.108 |
Neg logit contributions | |
zag | -0.124 |
oot | -0.116 |
uzz | -0.112 |
seek | -0.109 |
sometime | -0.105 |
Token | round |
Token ID | 2835 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
zag | +0.031 |
seek | +0.030 |
now | +0.030 |
gy | +0.028 |
sometime | +0.028 |
Neg logit contributions | |
forward | -0.026 |
spec | -0.026 |
pared | -0.026 |
cient | -0.025 |
counters | -0.024 |
Token | cookie |
Token ID | 19751 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ding | +0.060 |
pans | +0.059 |
counters | +0.058 |
nam | +0.058 |
y | +0.057 |
Neg logit contributions | |
zag | -0.075 |
oot | -0.072 |
uzz | -0.070 |
seek | -0.069 |
sometime | -0.065 |
Token | with |
Token ID | 351 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
zag | +0.107 |
oot | +0.100 |
uzz | +0.096 |
seek | +0.093 |
sometime | +0.090 |
Neg logit contributions | |
nam | -0.108 |
pans | -0.108 |
ding | -0.107 |
counters | -0.105 |
forward | -0.103 |
Token | spec |
Token ID | 1020 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
uzz | +0.002 |
zag | +0.002 |
ad | +0.002 |
oot | +0.002 |
seek | +0.002 |
Neg logit contributions | |
forward | -0.002 |
counters | -0.002 |
stressed | -0.002 |
pans | -0.002 |
sc | -0.002 |
Token | ks |
Token ID | 591 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
nam | +0.466 |
forward | +0.462 |
ding | +0.459 |
pans | +0.450 |
spec | +0.440 |
Neg logit contributions | |
zag | -0.575 |
oot | -0.519 |
seek | -0.509 |
sometime | -0.489 |
gy | -0.483 |
Token | of |
Token ID | 286 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
zag | +0.019 |
oot | +0.018 |
uzz | +0.018 |
seek | +0.017 |
gy | +0.016 |
Neg logit contributions | |
nam | -0.021 |
pans | -0.020 |
counters | -0.019 |
ding | -0.019 |
spec | -0.019 |
Token | sugar |
Token ID | 7543 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
forward | +0.148 |
sc | +0.145 |
counters | +0.139 |
nam | +0.138 |
ding | +0.138 |
Neg logit contributions | |
zag | -0.166 |
uzz | -0.162 |
oot | -0.160 |
seek | -0.153 |
sometime | -0.151 |
Token | on |
Token ID | 319 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
nam | +0.211 |
ding | +0.208 |
pans | +0.206 |
counters | +0.201 |
forward | +0.200 |
Neg logit contributions | |
zag | -0.191 |
oot | -0.175 |
uzz | -0.164 |
seek | -0.163 |
gy | -0.159 |
Token | the |
Token ID | 262 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
zag | +0.023 |
oot | +0.021 |
uzz | +0.020 |
seek | +0.019 |
gy | +0.019 |
Neg logit contributions | |
nam | -0.023 |
pans | -0.023 |
ding | -0.023 |
counters | -0.022 |
forward | -0.022 |
Token | high |
Token ID | 1029 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
counters | +0.023 |
nam | +0.022 |
sc | +0.022 |
pans | +0.021 |
forward | +0.021 |
Neg logit contributions | |
zag | -0.046 |
uzz | -0.044 |
oot | -0.044 |
sometime | -0.041 |
seek | -0.040 |
Token | they |
Token ID | 484 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ding | +0.066 |
pans | +0.065 |
forward | +0.063 |
counters | +0.063 |
nam | +0.063 |
Neg logit contributions | |
zag | -0.081 |
oot | -0.076 |
uzz | -0.076 |
seek | -0.072 |
sometime | -0.069 |
Token | were |
Token ID | 547 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
counters | +0.046 |
pans | +0.046 |
ding | +0.044 |
nam | +0.044 |
forward | +0.041 |
Neg logit contributions | |
zag | -0.066 |
oot | -0.062 |
uzz | -0.060 |
gy | -0.057 |
seek | -0.057 |
Token | just |
Token ID | 655 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
nam | +0.055 |
pans | +0.055 |
ding | +0.055 |
counters | +0.053 |
forward | +0.052 |
Neg logit contributions | |
zag | -0.078 |
oot | -0.073 |
uzz | -0.071 |
seek | -0.070 |
sometime | -0.067 |
Token | tiny |
Token ID | 7009 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
zag | +0.038 |
uzz | +0.036 |
oot | +0.036 |
sometime | +0.033 |
gy | +0.033 |
Neg logit contributions | |
pans | -0.038 |
counters | -0.038 |
nam | -0.037 |
sc | -0.036 |
ding | -0.036 |
Token | spec |
Token ID | 1020 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
nam | +0.121 |
ding | +0.120 |
pans | +0.120 |
counters | +0.118 |
forward | +0.115 |
Neg logit contributions | |
zag | -0.107 |
oot | -0.099 |
uzz | -0.095 |
seek | -0.093 |
sometime | -0.089 |
Token | ks |
Token ID | 591 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
nam | +0.482 |
ding | +0.481 |
pans | +0.478 |
forward | +0.473 |
counters | +0.464 |
Neg logit contributions | |
zag | -0.542 |
oot | -0.503 |
seek | -0.482 |
uzz | -0.466 |
sometime | -0.461 |
Token | in |
Token ID | 287 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
zag | +0.021 |
oot | +0.020 |
uzz | +0.019 |
seek | +0.018 |
sometime | +0.017 |
Neg logit contributions | |
nam | -0.027 |
pans | -0.026 |
counters | -0.025 |
ding | -0.025 |
ju | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
nam | +0.031 |
pans | +0.031 |
ding | +0.030 |
counters | +0.030 |
forward | +0.029 |
Neg logit contributions | |
zag | -0.039 |
oot | -0.037 |
uzz | -0.036 |
seek | -0.035 |
sometime | -0.033 |
Token | sky |
Token ID | 6766 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
nam | +0.013 |
stressed | +0.011 |
pans | +0.011 |
ults | +0.011 |
counters | +0.011 |
Neg logit contributions | |
zag | -0.014 |
istle | -0.012 |
gy | -0.012 |
seek | -0.012 |
ad | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
nam | +0.095 |
pans | +0.093 |
counters | +0.091 |
ding | +0.091 |
forward | +0.087 |
Neg logit contributions | |
zag | -0.078 |
oot | -0.070 |
uzz | -0.067 |
seek | -0.065 |
gy | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
zag | +0.031 |
oot | +0.029 |
uzz | +0.028 |
seek | +0.027 |
sometime | +0.027 |
Neg logit contributions | |
nam | -0.031 |
pans | -0.030 |
ding | -0.030 |
counters | -0.030 |
forward | -0.028 |
Token | leaf |
Token ID | 12835 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
nam | +0.007 |
pans | +0.007 |
ding | +0.007 |
counters | +0.007 |
forward | +0.006 |
Neg logit contributions | |
zag | -0.009 |
oot | -0.008 |
uzz | -0.008 |
seek | -0.008 |
sometime | -0.008 |
Token | there |
Token ID | 612 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
zag | +0.043 |
oot | +0.041 |
uzz | +0.039 |
seek | +0.038 |
sometime | +0.036 |
Neg logit contributions | |
pans | -0.043 |
nam | -0.043 |
ding | -0.043 |
counters | -0.042 |
forward | -0.041 |
Token | were |
Token ID | 547 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
zag | +0.004 |
oot | +0.004 |
uzz | +0.004 |
seek | +0.004 |
sometime | +0.004 |
Neg logit contributions | |
pans | -0.003 |
nam | -0.003 |
ding | -0.003 |
counters | -0.003 |
forward | -0.003 |
Token | little |
Token ID | 1310 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
pans | +0.047 |
nam | +0.047 |
ding | +0.047 |
counters | +0.046 |
forward | +0.046 |
Neg logit contributions | |
zag | -0.066 |
oot | -0.062 |
uzz | -0.061 |
seek | -0.059 |
sometime | -0.058 |
Token | spec |
Token ID | 1020 |
Feature activation | +9.73e+00 |
Pos logit contributions | |
nam | +0.146 |
ding | +0.145 |
pans | +0.144 |
forward | +0.142 |
counters | +0.141 |
Neg logit contributions | |
zag | -0.177 |
oot | -0.168 |
uzz | -0.163 |
seek | -0.158 |
sometime | -0.155 |
Token | ks |
Token ID | 591 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
nam | +0.465 |
forward | +0.455 |
ding | +0.454 |
pans | +0.445 |
spec | +0.444 |
Neg logit contributions | |
zag | -0.545 |
oot | -0.501 |
seek | -0.480 |
sometime | -0.460 |
gy | -0.452 |
Token | of |
Token ID | 286 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
zag | +0.030 |
oot | +0.028 |
uzz | +0.027 |
seek | +0.026 |
sometime | +0.025 |
Neg logit contributions | |
nam | -0.031 |
pans | -0.030 |
ding | -0.029 |
counters | -0.029 |
ju | -0.028 |
Token | gold |
Token ID | 3869 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
pans | +0.129 |
nam | +0.129 |
ding | +0.128 |
counters | +0.125 |
forward | +0.123 |
Neg logit contributions | |
zag | -0.183 |
oot | -0.174 |
uzz | -0.171 |
seek | -0.164 |
sometime | -0.160 |
Token | ! |
Token ID | 0 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
nam | +0.022 |
pans | +0.022 |
ding | +0.022 |
counters | +0.021 |
forward | +0.021 |
Neg logit contributions | |
zag | -0.020 |
oot | -0.019 |
uzz | -0.018 |
seek | -0.017 |
sometime | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
uzz | +0.061 |
zag | +0.060 |
seek | +0.056 |
oot | +0.056 |
sometime | +0.053 |
Neg logit contributions | |
pans | -0.083 |
ding | -0.079 |
nam | -0.078 |
forward | -0.076 |
brightest | -0.074 |
Token | spoon |
Token ID | 24556 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
nam | +0.119 |
pans | +0.113 |
forward | +0.112 |
ding | +0.112 |
counters | +0.112 |
Neg logit contributions | |
zag | -0.174 |
oot | -0.160 |
uzz | -0.159 |
gy | -0.152 |
sometime | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
pans | +0.096 |
ding | +0.096 |
forward | +0.093 |
counters | +0.093 |
y | +0.091 |
Neg logit contributions | |
zag | -0.124 |
oot | -0.117 |
seek | -0.114 |
uzz | -0.111 |
sometime | -0.111 |
Token | He |
Token ID | 679 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
nam | +0.016 |
pans | +0.016 |
ding | +0.015 |
counters | +0.015 |
forward | +0.015 |
Neg logit contributions | |
zag | -0.017 |
oot | -0.016 |
uzz | -0.016 |
seek | -0.015 |
sometime | -0.015 |
Token | puts |
Token ID | 7584 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
zag | +0.002 |
oot | +0.002 |
uzz | +0.002 |
seek | +0.002 |
sometime | +0.002 |
Neg logit contributions | |
pans | -0.001 |
nam | -0.001 |
ding | -0.001 |
counters | -0.001 |
forward | -0.001 |
Token | some |
Token ID | 617 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
zag | +0.025 |
uzz | +0.024 |
gy | +0.022 |
oot | +0.022 |
sometime | +0.022 |
Neg logit contributions | |
counters | -0.035 |
nam | -0.035 |
ding | -0.035 |
spec | -0.034 |
stressed | -0.034 |
Token | flour |
Token ID | 10601 |
Feature activation | +8.43e+00 |
Pos logit contributions | |
zag | +0.081 |
uzz | +0.078 |
sometime | +0.075 |
oot | +0.074 |
now | +0.072 |
Neg logit contributions | |
nam | -0.083 |
ding | -0.079 |
pared | -0.076 |
forward | -0.076 |
stressed | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
nam | +0.479 |
ding | +0.461 |
pans | +0.458 |
counters | +0.457 |
spec | +0.440 |
Neg logit contributions | |
zag | -0.410 |
oot | -0.377 |
uzz | -0.367 |
gy | -0.348 |
seek | -0.339 |
Token | some |
Token ID | 617 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
forward | +0.007 |
nam | +0.007 |
ding | +0.007 |
spec | +0.007 |
sc | +0.007 |
Neg logit contributions | |
zag | -0.009 |
sometime | -0.009 |
oot | -0.008 |
uzz | -0.008 |
gy | -0.008 |
Token | sugar |
Token ID | 7543 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
zag | +0.085 |
sometime | +0.084 |
uzz | +0.080 |
now | +0.079 |
oot | +0.078 |
Neg logit contributions | |
nam | -0.081 |
ding | -0.074 |
forward | -0.074 |
pared | -0.069 |
stressed | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
nam | +0.236 |
pans | +0.235 |
ding | +0.234 |
counters | +0.230 |
forward | +0.225 |
Neg logit contributions | |
zag | -0.213 |
oot | -0.198 |
uzz | -0.191 |
seek | -0.185 |
sometime | -0.177 |
Token | some |
Token ID | 617 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
nam | +0.012 |
forward | +0.012 |
ding | +0.012 |
counters | +0.011 |
spec | +0.011 |
Neg logit contributions | |
zag | -0.008 |
sometime | -0.007 |
uzz | -0.007 |
oot | -0.007 |
gy | -0.007 |
Token | is |
Token ID | 318 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
pans | +0.012 |
ding | +0.012 |
nam | +0.012 |
counters | +0.012 |
forward | +0.012 |
Neg logit contributions | |
zag | -0.017 |
oot | -0.016 |
uzz | -0.015 |
seek | -0.015 |
gy | -0.015 |
Token | cheaper |
Token ID | 11721 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
counters | +0.035 |
pans | +0.034 |
nam | +0.033 |
ding | +0.033 |
forward | +0.032 |
Neg logit contributions | |
zag | -0.041 |
uzz | -0.038 |
oot | -0.037 |
sometime | -0.036 |
seek | -0.035 |
Token | than |
Token ID | 621 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
zag | +0.095 |
oot | +0.089 |
uzz | +0.085 |
seek | +0.085 |
ogo | +0.079 |
Neg logit contributions | |
pans | -0.079 |
nam | -0.079 |
ding | -0.076 |
forward | -0.076 |
counters | -0.076 |
Token | sugar |
Token ID | 7543 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
pans | +0.045 |
ding | +0.045 |
counters | +0.045 |
nam | +0.044 |
forward | +0.043 |
Neg logit contributions | |
zag | -0.042 |
oot | -0.040 |
uzz | -0.039 |
seek | -0.037 |
sometime | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
nam | +0.235 |
pans | +0.233 |
ding | +0.233 |
counters | +0.228 |
forward | +0.222 |
Neg logit contributions | |
zag | -0.216 |
oot | -0.199 |
uzz | -0.191 |
seek | -0.186 |
sometime | -0.181 |
Token | flour |
Token ID | 10601 |
Feature activation | +8.42e+00 |
Pos logit contributions | |
forward | +0.021 |
ding | +0.020 |
counters | +0.020 |
nam | +0.020 |
pans | +0.019 |
Neg logit contributions | |
zag | -0.028 |
oot | -0.026 |
sometime | -0.026 |
uzz | -0.026 |
seek | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
nam | +0.476 |
pans | +0.464 |
ding | +0.461 |
counters | +0.457 |
forward | +0.439 |
Neg logit contributions | |
zag | -0.407 |
oot | -0.376 |
uzz | -0.361 |
seek | -0.344 |
sometime | -0.341 |
Token | We |
Token ID | 775 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
pans | +0.013 |
nam | +0.013 |
ding | +0.013 |
counters | +0.013 |
forward | +0.012 |
Neg logit contributions | |
zag | -0.017 |
uzz | -0.016 |
oot | -0.016 |
sometime | -0.015 |
seek | -0.015 |
Token | are |
Token ID | 389 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
nam | +0.126 |
ding | +0.125 |
pans | +0.124 |
forward | +0.121 |
y | +0.120 |
Neg logit contributions | |
zag | -0.190 |
oot | -0.179 |
seek | -0.172 |
uzz | -0.171 |
ippy | -0.161 |
Token | not |
Token ID | 407 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
sc | +0.056 |
spec | +0.054 |
counters | +0.053 |
pans | +0.053 |
ding | +0.050 |
Neg logit contributions | |
zag | -0.076 |
uzz | -0.076 |
sometime | -0.073 |
oot | -0.072 |
now | -0.070 |
Token | very |
Token ID | 845 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
zag | +0.094 |
oot | +0.092 |
uzz | +0.091 |
sometime | +0.087 |
gy | +0.084 |
Neg logit contributions | |
counters | -0.073 |
sc | -0.073 |
spec | -0.072 |
ding | -0.071 |
pans | -0.071 |
Token | sorry |
Token ID | 7926 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
brightest | +0.034 |
ju | +0.034 |
sc | +0.032 |
pans | +0.031 |
counters | +0.031 |
Neg logit contributions | |
now | -0.027 |
uzz | -0.027 |
oot | -0.027 |
zag | -0.025 |
drowned | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
ding | +0.168 |
forward | +0.163 |
pans | +0.163 |
y | +0.161 |
counters | +0.157 |
Neg logit contributions | |
zag | -0.226 |
oot | -0.207 |
seek | -0.204 |
uzz | -0.200 |
gy | -0.194 |
Token | They |
Token ID | 1119 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
nam | +0.029 |
pans | +0.029 |
ding | +0.029 |
counters | +0.028 |
forward | +0.028 |
Neg logit contributions | |
zag | -0.044 |
oot | -0.041 |
uzz | -0.040 |
seek | -0.039 |
sometime | -0.038 |
Token | heard |
Token ID | 2982 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
pans | +0.032 |
ding | +0.031 |
nam | +0.030 |
counters | +0.030 |
forward | +0.030 |
Neg logit contributions | |
zag | -0.033 |
oot | -0.032 |
uzz | -0.031 |
seek | -0.029 |
gy | -0.029 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ding | +0.068 |
nam | +0.066 |
pans | +0.065 |
counters | +0.064 |
y | +0.063 |
Neg logit contributions | |
zag | -0.099 |
oot | -0.092 |
seek | -0.089 |
uzz | -0.088 |
sometime | -0.085 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.40e+00 |
Pos logit contributions | |
nam | +0.129 |
ju | +0.124 |
brightest | +0.119 |
redd | +0.115 |
pans | +0.110 |
Neg logit contributions | |
zag | -0.112 |
oot | -0.106 |
gy | -0.105 |
uzz | -0.099 |
ad | -0.099 |
Token | back |
Token ID | 736 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
nam | +0.450 |
pans | +0.448 |
ding | +0.446 |
counters | +0.437 |
forward | +0.429 |
Neg logit contributions | |
zag | -0.429 |
oot | -0.399 |
uzz | -0.385 |
seek | -0.373 |
sometime | -0.359 |
Token | and |
Token ID | 290 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
zag | +0.084 |
oot | +0.079 |
seek | +0.075 |
uzz | +0.074 |
ogo | +0.071 |
Neg logit contributions | |
pans | -0.066 |
forward | -0.064 |
ding | -0.063 |
nam | -0.063 |
counters | -0.062 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
brightest | +0.053 |
ju | +0.052 |
sc | +0.050 |
redd | +0.049 |
ifying | +0.049 |
Neg logit contributions | |
gy | -0.030 |
again | -0.030 |
now | -0.030 |
uzz | -0.029 |
oot | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
nam | +0.094 |
pans | +0.094 |
ding | +0.093 |
counters | +0.091 |
forward | +0.089 |
Neg logit contributions | |
zag | -0.074 |
oot | -0.068 |
uzz | -0.066 |
seek | -0.064 |
sometime | -0.061 |
Token | hide |
Token ID | 7808 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
zag | +0.033 |
oot | +0.031 |
seek | +0.029 |
uzz | +0.029 |
ogo | +0.028 |
Neg logit contributions | |
nam | -0.020 |
pans | -0.020 |
ding | -0.020 |
forward | -0.019 |
counters | -0.019 |
Token | dish |
Token ID | 9433 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
nam | +0.168 |
stressed | +0.145 |
forward | +0.144 |
pans | +0.137 |
ults | +0.137 |
Neg logit contributions | |
zag | -0.161 |
oot | -0.136 |
seek | -0.133 |
ippy | -0.131 |
ad | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
nam | +0.017 |
pans | +0.015 |
ding | +0.015 |
spec | +0.015 |
counters | +0.015 |
Neg logit contributions | |
zag | -0.011 |
oot | -0.010 |
uzz | -0.009 |
seek | -0.009 |
sometime | -0.009 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
pans | +0.023 |
nam | +0.023 |
ding | +0.023 |
counters | +0.022 |
forward | +0.022 |
Neg logit contributions | |
zag | -0.029 |
oot | -0.028 |
uzz | -0.027 |
seek | -0.026 |
sometime | -0.025 |
Token | puts |
Token ID | 7584 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
nam | +0.005 |
pans | +0.005 |
ding | +0.005 |
forward | +0.005 |
counters | +0.005 |
Neg logit contributions | |
zag | -0.006 |
oot | -0.005 |
uzz | -0.005 |
seek | -0.005 |
sometime | -0.005 |
Token | some |
Token ID | 617 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
zag | +0.027 |
uzz | +0.027 |
sometime | +0.024 |
again | +0.024 |
gy | +0.024 |
Neg logit contributions | |
counters | -0.048 |
nam | -0.047 |
ding | -0.045 |
spec | -0.045 |
pans | -0.045 |
Token | flour |
Token ID | 10601 |
Feature activation | +8.39e+00 |
Pos logit contributions | |
zag | +0.074 |
sometime | +0.074 |
again | +0.071 |
oot | +0.069 |
ad | +0.068 |
Neg logit contributions | |
nam | -0.081 |
ding | -0.076 |
forward | -0.073 |
counters | -0.072 |
cient | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
nam | +0.432 |
ding | +0.414 |
counters | +0.412 |
pans | +0.411 |
spec | +0.389 |
Neg logit contributions | |
zag | -0.450 |
oot | -0.419 |
uzz | -0.411 |
gy | -0.385 |
sometime | -0.383 |
Token | water |
Token ID | 1660 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
forward | +0.046 |
nam | +0.045 |
ding | +0.043 |
counters | +0.041 |
sc | +0.040 |
Neg logit contributions | |
zag | -0.057 |
sometime | -0.055 |
uzz | -0.052 |
oot | -0.051 |
seek | -0.051 |
Token | in |
Token ID | 287 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
nam | +0.153 |
counters | +0.143 |
ding | +0.142 |
pans | +0.142 |
brightest | +0.137 |
Neg logit contributions | |
zag | -0.162 |
uzz | -0.150 |
oot | -0.149 |
seek | -0.140 |
gy | -0.137 |
Token | another |
Token ID | 1194 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
nam | +0.066 |
ding | +0.066 |
pans | +0.066 |
counters | +0.065 |
forward | +0.063 |
Neg logit contributions | |
zag | -0.067 |
oot | -0.062 |
uzz | -0.061 |
seek | -0.058 |
sometime | -0.057 |
Token | bowl |
Token ID | 9396 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
zag | +0.172 |
sometime | +0.170 |
again | +0.163 |
gy | +0.153 |
now | +0.142 |
Neg logit contributions | |
nam | -0.245 |
ding | -0.229 |
spec | -0.210 |
Hungry | -0.209 |
capt | -0.209 |
Token | with |
Token ID | 351 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
nam | +0.045 |
pans | +0.045 |
ding | +0.044 |
counters | +0.044 |
spec | +0.041 |
Neg logit contributions | |
zag | -0.044 |
oot | -0.041 |
uzz | -0.040 |
seek | -0.038 |
sometime | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
sc | +0.028 |
forward | +0.027 |
counters | +0.027 |
ding | +0.027 |
stressed | +0.026 |
Neg logit contributions | |
uzz | -0.021 |
ad | -0.020 |
zag | -0.019 |
oot | -0.019 |
sometime | -0.018 |
Token | messy |
Token ID | 24097 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
nam | +0.044 |
forward | +0.041 |
counters | +0.041 |
sc | +0.040 |
stressed | +0.039 |
Neg logit contributions | |
zag | -0.052 |
onna | -0.044 |
uzz | -0.042 |
ah | -0.042 |
sometime | -0.041 |
Token | pile |
Token ID | 14540 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
zag | +0.042 |
oot | +0.039 |
uzz | +0.038 |
seek | +0.037 |
gy | +0.037 |
Neg logit contributions | |
nam | -0.026 |
ding | -0.025 |
pans | -0.025 |
forward | -0.025 |
counters | -0.024 |
Token | of |
Token ID | 286 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
nam | +0.055 |
pans | +0.054 |
ding | +0.054 |
counters | +0.052 |
forward | +0.050 |
Neg logit contributions | |
zag | -0.059 |
oot | -0.056 |
uzz | -0.055 |
seek | -0.051 |
gy | -0.050 |
Token | flour |
Token ID | 10601 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
forward | +0.205 |
sc | +0.193 |
pared | +0.185 |
nam | +0.176 |
ults | +0.171 |
Neg logit contributions | |
ad | -0.149 |
uzz | -0.145 |
now | -0.145 |
sometime | -0.144 |
zag | -0.138 |
Token | and |
Token ID | 290 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
nam | +0.484 |
pans | +0.464 |
ding | +0.463 |
counters | +0.457 |
forward | +0.444 |
Neg logit contributions | |
zag | -0.401 |
oot | -0.368 |
uzz | -0.351 |
gy | -0.333 |
seek | -0.330 |
Token | sugar |
Token ID | 7543 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
forward | +0.020 |
ding | +0.017 |
nam | +0.017 |
stressed | +0.016 |
sc | +0.016 |
Neg logit contributions | |
zag | -0.023 |
sometime | -0.023 |
uzz | -0.022 |
seek | -0.021 |
gy | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
nam | +0.211 |
ding | +0.205 |
pans | +0.204 |
counters | +0.200 |
forward | +0.197 |
Neg logit contributions | |
zag | -0.236 |
oot | -0.219 |
uzz | -0.211 |
seek | -0.204 |
gy | -0.200 |
Token | " |
Token ID | 366 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
nam | +0.005 |
pans | +0.005 |
ding | +0.004 |
counters | +0.004 |
forward | +0.004 |
Neg logit contributions | |
zag | -0.005 |
uzz | -0.005 |
oot | -0.005 |
sometime | -0.004 |
seek | -0.004 |
Token | Do |
Token ID | 5211 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
counters | +0.121 |
nam | +0.121 |
forward | +0.121 |
pans | +0.118 |
ding | +0.117 |
Neg logit contributions | |
zag | -0.144 |
uzz | -0.138 |
seek | -0.134 |
sometime | -0.133 |
oot | -0.132 |
Token |
|
Token ID | 198 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
nam | +0.031 |
pans | +0.030 |
ding | +0.030 |
counters | +0.030 |
forward | +0.029 |
Neg logit contributions | |
zag | -0.027 |
oot | -0.025 |
uzz | -0.025 |
seek | -0.024 |
sometime | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
ding | +0.024 |
pans | +0.023 |
counters | +0.023 |
nam | +0.022 |
y | +0.022 |
Neg logit contributions | |
zag | -0.037 |
oot | -0.035 |
uzz | -0.034 |
seek | -0.034 |
gy | -0.033 |
Token | They |
Token ID | 2990 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
nam | +0.037 |
pans | +0.036 |
ding | +0.036 |
counters | +0.036 |
forward | +0.035 |
Neg logit contributions | |
zag | -0.030 |
oot | -0.028 |
uzz | -0.027 |
seek | -0.026 |
sometime | -0.025 |
Token | measured |
Token ID | 8630 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
pans | +0.030 |
nam | +0.030 |
ding | +0.030 |
counters | +0.029 |
forward | +0.029 |
Neg logit contributions | |
zag | -0.041 |
oot | -0.038 |
uzz | -0.037 |
seek | -0.036 |
sometime | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
nam | +0.036 |
counters | +0.036 |
pans | +0.036 |
stressed | +0.035 |
sc | +0.035 |
Neg logit contributions | |
zag | -0.025 |
uzz | -0.023 |
sometime | -0.023 |
gy | -0.022 |
oot | -0.021 |
Token | flour |
Token ID | 10601 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
nam | +0.041 |
forward | +0.039 |
ding | +0.037 |
sc | +0.036 |
pans | +0.035 |
Neg logit contributions | |
zag | -0.055 |
sometime | -0.048 |
uzz | -0.048 |
gy | -0.047 |
oot | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
nam | +0.553 |
pans | +0.526 |
counters | +0.516 |
ding | +0.516 |
brightest | +0.497 |
Neg logit contributions | |
zag | -0.343 |
oot | -0.303 |
uzz | -0.290 |
sometime | -0.275 |
gy | -0.275 |
Token | the |
Token ID | 262 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
forward | +0.018 |
sc | +0.017 |
ding | +0.017 |
pared | +0.017 |
nam | +0.016 |
Neg logit contributions | |
sometime | -0.011 |
zag | -0.010 |
uzz | -0.010 |
again | -0.010 |
gy | -0.010 |
Token | sugar |
Token ID | 7543 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
forward | +0.041 |
nam | +0.040 |
sc | +0.040 |
ding | +0.037 |
pared | +0.036 |
Neg logit contributions | |
zag | -0.053 |
uzz | -0.048 |
sometime | -0.047 |
fault | -0.047 |
gy | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
nam | +0.277 |
ding | +0.263 |
pans | +0.262 |
forward | +0.258 |
counters | +0.256 |
Neg logit contributions | |
zag | -0.185 |
oot | -0.161 |
uzz | -0.152 |
gy | -0.149 |
sometime | -0.146 |
Token | and |
Token ID | 290 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
nam | +0.021 |
sc | +0.020 |
forward | +0.020 |
counters | +0.020 |
spec | +0.020 |
Neg logit contributions | |
zag | -0.010 |
sometime | -0.010 |
uzz | -0.009 |
again | -0.009 |
gy | -0.009 |
Token | They |
Token ID | 2990 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
nam | +0.019 |
ding | +0.018 |
spec | +0.018 |
counters | +0.018 |
forward | +0.018 |
Neg logit contributions | |
zag | -0.014 |
oot | -0.013 |
uzz | -0.012 |
seek | -0.012 |
sometime | -0.012 |
Token | did |
Token ID | 750 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
ding | +0.021 |
forward | +0.021 |
pans | +0.020 |
nam | +0.020 |
counters | +0.020 |
Neg logit contributions | |
zag | -0.020 |
uzz | -0.019 |
oot | -0.019 |
sometime | -0.018 |
gy | -0.018 |
Token | not |
Token ID | 407 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
zag | +0.042 |
oot | +0.041 |
uzz | +0.037 |
seek | +0.036 |
ippy | +0.035 |
Neg logit contributions | |
ding | -0.051 |
y | -0.050 |
nam | -0.049 |
counters | -0.049 |
pans | -0.049 |
Token | hear |
Token ID | 3285 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
zag | +0.100 |
oot | +0.092 |
uzz | +0.088 |
seek | +0.087 |
ippy | +0.085 |
Neg logit contributions | |
pans | -0.066 |
ding | -0.065 |
nam | -0.065 |
counters | -0.063 |
forward | -0.062 |
Token | Mom |
Token ID | 11254 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
zag | +0.055 |
oot | +0.051 |
seek | +0.049 |
uzz | +0.048 |
ippy | +0.047 |
Neg logit contributions | |
ding | -0.034 |
nam | -0.032 |
y | -0.032 |
pans | -0.032 |
counters | -0.032 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
nam | +0.219 |
ju | +0.204 |
brightest | +0.202 |
pans | +0.197 |
redd | +0.188 |
Neg logit contributions | |
zag | -0.243 |
oot | -0.221 |
gy | -0.220 |
uzz | -0.214 |
seek | -0.213 |
Token | home |
Token ID | 1363 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
nam | +0.455 |
ding | +0.443 |
pans | +0.442 |
counters | +0.434 |
ju | +0.426 |
Neg logit contributions | |
zag | -0.423 |
oot | -0.396 |
uzz | -0.388 |
seek | -0.365 |
gy | -0.361 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
zag | +0.283 |
oot | +0.264 |
uzz | +0.254 |
seek | +0.247 |
sometime | +0.237 |
Neg logit contributions | |
nam | -0.282 |
pans | -0.282 |
ding | -0.280 |
counters | -0.275 |
forward | -0.270 |
Token | They |
Token ID | 1119 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
nam | +0.028 |
ding | +0.027 |
pans | +0.027 |
forward | +0.026 |
brightest | +0.026 |
Neg logit contributions | |
uzz | -0.025 |
zag | -0.024 |
sometime | -0.022 |
oot | -0.022 |
seek | -0.021 |
Token | did |
Token ID | 750 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
pans | +0.020 |
nam | +0.020 |
ding | +0.020 |
counters | +0.020 |
forward | +0.019 |
Neg logit contributions | |
zag | -0.024 |
oot | -0.022 |
uzz | -0.022 |
seek | -0.021 |
gy | -0.020 |
Token | not |
Token ID | 407 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
oot | +0.049 |
zag | +0.048 |
uzz | +0.043 |
ippy | +0.042 |
seek | +0.041 |
Neg logit contributions | |
y | -0.048 |
ding | -0.048 |
nam | -0.047 |
pans | -0.045 |
counters | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
zag | +0.036 |
oot | +0.034 |
uzz | +0.034 |
seek | +0.033 |
sometime | +0.031 |
Neg logit contributions | |
ding | -0.023 |
pans | -0.023 |
counters | -0.022 |
forward | -0.022 |
y | -0.021 |
Token | Mia |
Token ID | 32189 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
ding | +0.053 |
pans | +0.052 |
nam | +0.052 |
y | +0.050 |
forward | +0.050 |
Neg logit contributions | |
zag | -0.058 |
oot | -0.056 |
seek | -0.051 |
uzz | -0.050 |
gy | -0.049 |
Token | hear |
Token ID | 3285 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
zag | +0.028 |
oot | +0.026 |
uzz | +0.025 |
seek | +0.024 |
sometime | +0.024 |
Neg logit contributions | |
pans | -0.029 |
nam | -0.028 |
counters | -0.027 |
ding | -0.027 |
ju | -0.026 |
Token | their |
Token ID | 511 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
zag | +0.033 |
oot | +0.031 |
seek | +0.029 |
uzz | +0.028 |
gy | +0.028 |
Neg logit contributions | |
ding | -0.020 |
pans | -0.019 |
counters | -0.018 |
y | -0.018 |
forward | -0.017 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
pans | +0.050 |
ding | +0.050 |
nam | +0.049 |
counters | +0.049 |
y | +0.047 |
Neg logit contributions | |
zag | -0.054 |
oot | -0.051 |
uzz | -0.049 |
seek | -0.048 |
sometime | -0.047 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.37e+00 |
Pos logit contributions | |
nam | +0.136 |
ju | +0.131 |
brightest | +0.128 |
pans | +0.124 |
redd | +0.123 |
Neg logit contributions | |
zag | -0.101 |
oot | -0.096 |
uzz | -0.091 |
gy | -0.089 |
ad | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
nam | +0.460 |
ding | +0.449 |
pans | +0.446 |
counters | +0.437 |
ju | +0.433 |
Neg logit contributions | |
zag | -0.421 |
oot | -0.392 |
uzz | -0.385 |
seek | -0.363 |
gy | -0.358 |
Token | They |
Token ID | 1119 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
nam | +0.041 |
ju | +0.039 |
brightest | +0.038 |
forward | +0.038 |
pans | +0.038 |
Neg logit contributions | |
zag | -0.040 |
uzz | -0.038 |
gy | -0.035 |
oot | -0.035 |
seek | -0.034 |
Token | know |
Token ID | 760 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
pans | +0.044 |
nam | +0.044 |
counters | +0.042 |
ding | +0.042 |
ju | +0.041 |
Neg logit contributions | |
zag | -0.043 |
oot | -0.040 |
uzz | -0.039 |
gy | -0.037 |
seek | -0.036 |
Token | she |
Token ID | 673 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
zag | +0.145 |
oot | +0.135 |
uzz | +0.131 |
seek | +0.128 |
gy | +0.123 |
Neg logit contributions | |
nam | -0.112 |
pans | -0.112 |
ding | -0.111 |
counters | -0.109 |
forward | -0.106 |
Token | will |
Token ID | 481 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
counters | +0.079 |
pans | +0.079 |
ding | +0.078 |
y | +0.076 |
forward | +0.075 |
Neg logit contributions | |
zag | -0.143 |
oot | -0.139 |
uzz | -0.135 |
seek | -0.130 |
sometime | -0.127 |
Token | tells |
Token ID | 4952 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
pans | +0.023 |
ding | +0.023 |
nam | +0.022 |
counters | +0.022 |
y | +0.022 |
Neg logit contributions | |
zag | -0.043 |
oot | -0.041 |
uzz | -0.040 |
seek | -0.039 |
gy | -0.038 |
Token | Sara |
Token ID | 24799 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ding | +0.009 |
nam | +0.009 |
pans | +0.009 |
counters | +0.009 |
forward | +0.009 |
Neg logit contributions | |
zag | -0.010 |
oot | -0.009 |
uzz | -0.009 |
seek | -0.009 |
sometime | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
zag | +0.026 |
oot | +0.024 |
seek | +0.023 |
uzz | +0.023 |
sometime | +0.021 |
Neg logit contributions | |
pans | -0.024 |
nam | -0.023 |
counters | -0.023 |
y | -0.023 |
ding | -0.023 |
Token | mix |
Token ID | 5022 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
zag | +0.034 |
oot | +0.032 |
uzz | +0.031 |
seek | +0.030 |
sometime | +0.029 |
Neg logit contributions | |
ding | -0.027 |
pans | -0.027 |
nam | -0.027 |
counters | -0.027 |
y | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
nam | +0.038 |
ding | +0.037 |
counters | +0.037 |
spec | +0.036 |
pans | +0.036 |
Neg logit contributions | |
zag | -0.029 |
uzz | -0.028 |
sometime | -0.027 |
oot | -0.026 |
gy | -0.024 |
Token | flour |
Token ID | 10601 |
Feature activation | +8.37e+00 |
Pos logit contributions | |
nam | +0.039 |
forward | +0.037 |
ding | +0.036 |
pared | +0.034 |
sc | +0.033 |
Neg logit contributions | |
zag | -0.045 |
fault | -0.039 |
sometime | -0.039 |
uzz | -0.039 |
onna | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
nam | +0.483 |
pans | +0.472 |
ding | +0.469 |
counters | +0.465 |
forward | +0.448 |
Neg logit contributions | |
zag | -0.396 |
oot | -0.359 |
uzz | -0.349 |
sometime | -0.330 |
seek | -0.329 |
Token | the |
Token ID | 262 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
forward | +0.017 |
ding | +0.017 |
spec | +0.016 |
sc | +0.016 |
nam | +0.016 |
Neg logit contributions | |
zag | -0.014 |
sometime | -0.014 |
uzz | -0.013 |
oot | -0.013 |
gy | -0.013 |
Token | eggs |
Token ID | 9653 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
nam | +0.036 |
forward | +0.036 |
pared | +0.033 |
sc | +0.031 |
ding | +0.031 |
Neg logit contributions | |
zag | -0.050 |
fault | -0.044 |
onna | -0.043 |
sometime | -0.043 |
uzz | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
nam | +0.221 |
pans | +0.215 |
ding | +0.213 |
counters | +0.212 |
forward | +0.206 |
Neg logit contributions | |
zag | -0.169 |
oot | -0.150 |
uzz | -0.145 |
gy | -0.139 |
sometime | -0.138 |
Token | the |
Token ID | 262 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
forward | +0.043 |
sc | +0.040 |
spec | +0.040 |
ding | +0.040 |
counters | +0.039 |
Neg logit contributions | |
sometime | -0.033 |
zag | -0.032 |
uzz | -0.030 |
now | -0.029 |
gy | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
nam | +0.068 |
counters | +0.065 |
ju | +0.065 |
ding | +0.064 |
pans | +0.064 |
Neg logit contributions | |
uzz | -0.049 |
zag | -0.047 |
oot | -0.046 |
again | -0.045 |
sometime | -0.043 |
Token | They |
Token ID | 1119 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
nam | +0.030 |
pans | +0.029 |
ding | +0.029 |
forward | +0.028 |
counters | +0.028 |
Neg logit contributions | |
zag | -0.035 |
uzz | -0.033 |
oot | -0.032 |
seek | -0.031 |
sometime | -0.031 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
nam | +0.024 |
pans | +0.024 |
ding | +0.024 |
counters | +0.023 |
forward | +0.023 |
Neg logit contributions | |
zag | -0.035 |
oot | -0.033 |
uzz | -0.032 |
seek | -0.032 |
sometime | -0.031 |
Token | their |
Token ID | 511 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
nam | +0.091 |
pans | +0.090 |
counters | +0.088 |
forward | +0.088 |
ding | +0.087 |
Neg logit contributions | |
zag | -0.094 |
uzz | -0.089 |
oot | -0.087 |
seek | -0.082 |
gy | -0.080 |
Token | dad |
Token ID | 9955 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
pans | +0.050 |
ding | +0.050 |
nam | +0.050 |
counters | +0.049 |
forward | +0.047 |
Neg logit contributions | |
zag | -0.057 |
oot | -0.055 |
uzz | -0.052 |
seek | -0.051 |
sometime | -0.049 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
nam | +0.198 |
pans | +0.191 |
ju | +0.190 |
brightest | +0.185 |
ding | +0.181 |
Neg logit contributions | |
zag | -0.187 |
oot | -0.170 |
uzz | -0.167 |
gy | -0.162 |
sometime | -0.161 |
Token | home |
Token ID | 1363 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
nam | +0.396 |
pans | +0.393 |
ding | +0.391 |
counters | +0.383 |
forward | +0.372 |
Neg logit contributions | |
zag | -0.479 |
oot | -0.450 |
uzz | -0.438 |
seek | -0.424 |
sometime | -0.410 |
Token | from |
Token ID | 422 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
zag | +0.276 |
oot | +0.256 |
uzz | +0.247 |
seek | +0.240 |
sometime | +0.231 |
Neg logit contributions | |
nam | -0.288 |
pans | -0.286 |
ding | -0.284 |
counters | -0.279 |
forward | -0.274 |
Token | work |
Token ID | 670 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
pans | +0.073 |
nam | +0.070 |
ding | +0.069 |
counters | +0.067 |
forward | +0.066 |
Neg logit contributions | |
zag | -0.118 |
oot | -0.112 |
seek | -0.104 |
uzz | -0.103 |
ogo | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
zag | +0.132 |
oot | +0.120 |
uzz | +0.117 |
seek | +0.110 |
gy | +0.104 |
Neg logit contributions | |
nam | -0.189 |
ding | -0.182 |
pans | -0.182 |
ju | -0.181 |
brightest | -0.178 |
Token | He |
Token ID | 679 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
nam | +0.034 |
pans | +0.033 |
ding | +0.033 |
counters | +0.033 |
forward | +0.032 |
Neg logit contributions | |
zag | -0.034 |
uzz | -0.032 |
oot | -0.031 |
seek | -0.030 |
gy | -0.029 |
Token | oons |
Token ID | 13022 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
nam | +0.056 |
ding | +0.053 |
pans | +0.052 |
forward | +0.052 |
counters | +0.050 |
Neg logit contributions | |
zag | -0.072 |
oot | -0.068 |
uzz | -0.065 |
seek | -0.063 |
ippy | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
pans | +0.134 |
nam | +0.133 |
ding | +0.133 |
counters | +0.130 |
forward | +0.129 |
Neg logit contributions | |
zag | -0.122 |
oot | -0.114 |
uzz | -0.109 |
seek | -0.106 |
sometime | -0.101 |
Token | cups |
Token ID | 14180 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
zag | +0.003 |
sometime | +0.003 |
uzz | +0.003 |
gy | +0.003 |
oot | +0.003 |
Neg logit contributions | |
forward | -0.004 |
ding | -0.004 |
nam | -0.004 |
spec | -0.003 |
pared | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
nam | +0.290 |
ding | +0.284 |
pans | +0.278 |
counters | +0.272 |
forward | +0.271 |
Neg logit contributions | |
zag | -0.196 |
oot | -0.180 |
uzz | -0.172 |
seek | -0.164 |
sometime | -0.158 |
Token | some |
Token ID | 617 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
forward | +0.020 |
ding | +0.019 |
nam | +0.018 |
counters | +0.017 |
spec | +0.017 |
Neg logit contributions | |
zag | -0.025 |
uzz | -0.023 |
sometime | -0.023 |
seek | -0.022 |
oot | -0.022 |
Token | flour |
Token ID | 10601 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
sometime | +0.082 |
zag | +0.080 |
uzz | +0.079 |
ad | +0.074 |
now | +0.072 |
Neg logit contributions | |
ding | -0.089 |
nam | -0.087 |
forward | -0.086 |
pared | -0.084 |
stressed | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
nam | +0.503 |
ding | +0.491 |
pans | +0.484 |
counters | +0.480 |
forward | +0.469 |
Neg logit contributions | |
zag | -0.382 |
oot | -0.348 |
uzz | -0.336 |
seek | -0.317 |
gy | -0.316 |
Token |
|
Token ID | 198 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
nam | +0.017 |
ding | +0.017 |
pans | +0.017 |
counters | +0.016 |
forward | +0.016 |
Neg logit contributions | |
zag | -0.021 |
uzz | -0.020 |
oot | -0.020 |
sometime | -0.018 |
seek | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
pans | +0.012 |
ding | +0.012 |
counters | +0.011 |
forward | +0.011 |
y | +0.011 |
Neg logit contributions | |
zag | -0.022 |
oot | -0.021 |
seek | -0.020 |
gy | -0.019 |
uzz | -0.019 |
Token | " |
Token ID | 1 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
pans | +0.020 |
nam | +0.020 |
ding | +0.020 |
counters | +0.019 |
forward | +0.019 |
Neg logit contributions | |
zag | -0.023 |
oot | -0.022 |
uzz | -0.021 |
seek | -0.021 |
gy | -0.020 |
Token | Let |
Token ID | 5756 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
zag | +0.010 |
sometime | +0.009 |
uzz | +0.009 |
seek | +0.009 |
oot | +0.009 |
Neg logit contributions | |
nam | -0.008 |
forward | -0.008 |
counters | -0.008 |
ding | -0.007 |
stressed | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
pans | +0.019 |
ding | +0.019 |
counters | +0.018 |
y | +0.018 |
nam | +0.018 |
Neg logit contributions | |
zag | -0.037 |
oot | -0.034 |
seek | -0.033 |
gy | -0.032 |
uzz | -0.032 |
Token | They |
Token ID | 2990 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
pans | +0.028 |
ding | +0.027 |
nam | +0.027 |
counters | +0.026 |
forward | +0.026 |
Neg logit contributions | |
zag | -0.036 |
oot | -0.034 |
uzz | -0.032 |
seek | -0.032 |
gy | -0.031 |
Token | heard |
Token ID | 2982 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
pans | +0.023 |
ding | +0.023 |
nam | +0.023 |
counters | +0.023 |
forward | +0.022 |
Neg logit contributions | |
zag | -0.031 |
oot | -0.029 |
uzz | -0.028 |
seek | -0.027 |
sometime | -0.027 |
Token | their |
Token ID | 511 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
ding | +0.064 |
nam | +0.061 |
pans | +0.060 |
counters | +0.060 |
y | +0.060 |
Neg logit contributions | |
zag | -0.096 |
oot | -0.089 |
seek | -0.085 |
uzz | -0.082 |
sometime | -0.082 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
ding | +0.045 |
pans | +0.044 |
nam | +0.044 |
counters | +0.043 |
y | +0.042 |
Neg logit contributions | |
zag | -0.046 |
oot | -0.044 |
uzz | -0.042 |
seek | -0.041 |
sometime | -0.039 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
nam | +0.129 |
ju | +0.126 |
brightest | +0.119 |
redd | +0.118 |
pans | +0.116 |
Neg logit contributions | |
zag | -0.129 |
oot | -0.120 |
gy | -0.118 |
ad | -0.114 |
uzz | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
nam | +0.484 |
pans | +0.467 |
ju | +0.466 |
ding | +0.464 |
counters | +0.456 |
Neg logit contributions | |
zag | -0.398 |
oot | -0.371 |
uzz | -0.371 |
gy | -0.342 |
seek | -0.336 |
Token | She |
Token ID | 1375 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
nam | +0.041 |
pans | +0.040 |
ding | +0.039 |
counters | +0.039 |
forward | +0.038 |
Neg logit contributions | |
zag | -0.056 |
uzz | -0.053 |
oot | -0.053 |
seek | -0.050 |
gy | -0.049 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
nam | +0.039 |
pans | +0.038 |
ding | +0.037 |
counters | +0.037 |
forward | +0.037 |
Neg logit contributions | |
zag | -0.043 |
oot | -0.040 |
uzz | -0.039 |
gy | -0.037 |
seek | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
nam | +0.084 |
pans | +0.084 |
ding | +0.083 |
counters | +0.081 |
y | +0.079 |
Neg logit contributions | |
zag | -0.098 |
oot | -0.091 |
seek | -0.087 |
uzz | -0.086 |
sometime | -0.083 |
Token | mess |
Token ID | 2085 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
nam | +0.046 |
ding | +0.045 |
pans | +0.045 |
forward | +0.044 |
counters | +0.044 |
Neg logit contributions | |
zag | -0.052 |
oot | -0.048 |
uzz | -0.046 |
seek | -0.045 |
gy | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
nam | +0.025 |
pans | +0.024 |
ding | +0.024 |
forward | +0.024 |
counters | +0.024 |
Neg logit contributions | |
zag | -0.024 |
oot | -0.022 |
uzz | -0.022 |
seek | -0.021 |
sometime | -0.020 |
Token | big |
Token ID | 1263 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
nam | +0.031 |
forward | +0.028 |
sc | +0.027 |
stressed | +0.027 |
counters | +0.026 |
Neg logit contributions | |
zag | -0.039 |
onna | -0.032 |
gy | -0.031 |
castle | -0.031 |
mistake | -0.031 |
Token | mess |
Token ID | 2085 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
nam | +0.127 |
pans | +0.123 |
counters | +0.119 |
ding | +0.119 |
forward | +0.118 |
Neg logit contributions | |
zag | -0.160 |
oot | -0.148 |
uzz | -0.143 |
seek | -0.138 |
sometime | -0.137 |
Token | with |
Token ID | 351 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
zag | +0.040 |
oot | +0.037 |
uzz | +0.036 |
seek | +0.034 |
sometime | +0.034 |
Neg logit contributions | |
nam | -0.048 |
pans | -0.046 |
ding | -0.045 |
ju | -0.045 |
counters | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
ding | +0.027 |
counters | +0.027 |
forward | +0.027 |
nam | +0.026 |
sc | +0.026 |
Neg logit contributions | |
uzz | -0.022 |
zag | -0.022 |
oot | -0.020 |
sometime | -0.019 |
seek | -0.019 |
Token | flour |
Token ID | 10601 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
nam | +0.028 |
forward | +0.028 |
ding | +0.024 |
sc | +0.023 |
stressed | +0.023 |
Neg logit contributions | |
zag | -0.039 |
fault | -0.034 |
sometime | -0.032 |
gy | -0.032 |
seek | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
nam | +0.520 |
pans | +0.496 |
ding | +0.492 |
counters | +0.485 |
forward | +0.476 |
Neg logit contributions | |
zag | -0.370 |
oot | -0.329 |
uzz | -0.314 |
gy | -0.299 |
sometime | -0.298 |
Token | She |
Token ID | 1375 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
nam | +0.027 |
pans | +0.026 |
ding | +0.026 |
forward | +0.025 |
spec | +0.025 |
Neg logit contributions | |
zag | -0.026 |
uzz | -0.024 |
oot | -0.024 |
seek | -0.023 |
sometime | -0.023 |
Token | laughs |
Token ID | 22051 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
pans | +0.022 |
ding | +0.022 |
nam | +0.022 |
counters | +0.021 |
y | +0.020 |
Neg logit contributions | |
zag | -0.037 |
oot | -0.036 |
uzz | -0.034 |
seek | -0.034 |
gy | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
nam | +0.098 |
pans | +0.097 |
counters | +0.095 |
ding | +0.094 |
ju | +0.091 |
Neg logit contributions | |
zag | -0.072 |
oot | -0.067 |
uzz | -0.064 |
seek | -0.061 |
sometime | -0.060 |
Token | says |
Token ID | 1139 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
nam | +0.041 |
forward | +0.039 |
counters | +0.038 |
pans | +0.038 |
ding | +0.037 |
Neg logit contributions | |
zag | -0.047 |
oot | -0.043 |
seek | -0.043 |
uzz | -0.042 |
sometime | -0.042 |
Token | irens |
Token ID | 42917 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ding | +0.062 |
pans | +0.062 |
counters | +0.061 |
forward | +0.058 |
nam | +0.058 |
Neg logit contributions | |
zag | -0.088 |
oot | -0.081 |
uzz | -0.081 |
gy | -0.078 |
sometime | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
nam | +0.168 |
ju | +0.161 |
pans | +0.160 |
brightest | +0.155 |
redd | +0.153 |
Neg logit contributions | |
zag | -0.090 |
oot | -0.082 |
seek | -0.074 |
uzz | -0.071 |
gy | -0.070 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
forward | +0.038 |
sc | +0.037 |
ju | +0.037 |
counters | +0.036 |
nam | +0.036 |
Neg logit contributions | |
zag | -0.034 |
uzz | -0.031 |
sometime | -0.030 |
seek | -0.030 |
gy | -0.030 |
Token | red |
Token ID | 2266 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
nam | +0.089 |
pans | +0.088 |
ju | +0.085 |
counters | +0.085 |
forward | +0.085 |
Neg logit contributions | |
zag | -0.089 |
uzz | -0.088 |
oot | -0.083 |
gy | -0.079 |
seek | -0.078 |
Token | trucks |
Token ID | 13960 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
nam | +0.074 |
pans | +0.070 |
ding | +0.069 |
forward | +0.069 |
counters | +0.067 |
Neg logit contributions | |
zag | -0.106 |
oot | -0.099 |
uzz | -0.096 |
seek | -0.094 |
gy | -0.093 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
nam | +0.151 |
pans | +0.149 |
counters | +0.142 |
ding | +0.141 |
ju | +0.141 |
Neg logit contributions | |
zag | -0.127 |
oot | -0.116 |
uzz | -0.109 |
seek | -0.109 |
sometime | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
nam | +0.431 |
ju | +0.411 |
pans | +0.408 |
counters | +0.404 |
brightest | +0.387 |
Neg logit contributions | |
zag | -0.457 |
uzz | -0.437 |
oot | -0.425 |
gy | -0.418 |
sometime | -0.387 |
Token | The |
Token ID | 383 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
nam | +0.029 |
pans | +0.028 |
ding | +0.028 |
counters | +0.027 |
forward | +0.026 |
Neg logit contributions | |
zag | -0.033 |
uzz | -0.031 |
oot | -0.031 |
seek | -0.029 |
sometime | -0.029 |
Token | trucks |
Token ID | 13960 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
zag | +0.038 |
gy | +0.033 |
uzz | +0.032 |
seek | +0.030 |
oot | +0.030 |
Neg logit contributions | |
nam | -0.035 |
forward | -0.031 |
ju | -0.031 |
ding | -0.030 |
sc | -0.030 |
Token | had |
Token ID | 550 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
nam | +0.121 |
pans | +0.118 |
ding | +0.114 |
counters | +0.114 |
ju | +0.111 |
Neg logit contributions | |
zag | -0.157 |
oot | -0.144 |
uzz | -0.139 |
seek | -0.135 |
gy | -0.132 |
Token | big |
Token ID | 1263 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
zag | +0.045 |
oot | +0.043 |
uzz | +0.041 |
seek | +0.040 |
sometime | +0.039 |
Neg logit contributions | |
pans | -0.029 |
ding | -0.029 |
nam | -0.029 |
counters | -0.028 |
y | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
zag | +0.039 |
oot | +0.037 |
uzz | +0.036 |
seek | +0.034 |
sometime | +0.033 |
Neg logit contributions | |
nam | -0.041 |
pans | -0.041 |
ding | -0.041 |
counters | -0.040 |
forward | -0.039 |
Token | Now |
Token ID | 2735 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
nam | +0.017 |
pans | +0.017 |
ding | +0.017 |
counters | +0.017 |
forward | +0.016 |
Neg logit contributions | |
zag | -0.029 |
oot | -0.028 |
uzz | -0.027 |
seek | -0.026 |
sometime | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
pans | +0.016 |
nam | +0.016 |
counters | +0.016 |
ding | +0.015 |
forward | +0.015 |
Neg logit contributions | |
zag | -0.017 |
oot | -0.016 |
uzz | -0.015 |
sometime | -0.015 |
seek | -0.015 |
Token | stuffing |
Token ID | 43672 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
pans | +0.048 |
nam | +0.047 |
ding | +0.047 |
counters | +0.046 |
forward | +0.046 |
Neg logit contributions | |
zag | -0.051 |
oot | -0.046 |
uzz | -0.045 |
seek | -0.044 |
sometime | -0.042 |
Token | is |
Token ID | 318 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
pans | +0.143 |
nam | +0.143 |
ding | +0.143 |
counters | +0.139 |
forward | +0.136 |
Neg logit contributions | |
zag | -0.186 |
oot | -0.175 |
uzz | -0.170 |
seek | -0.165 |
sometime | -0.159 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.34e+00 |
Pos logit contributions | |
nam | +0.018 |
pans | +0.018 |
ding | +0.018 |
counters | +0.018 |
spec | +0.018 |
Neg logit contributions | |
zag | -0.022 |
oot | -0.020 |
uzz | -0.019 |
gy | -0.019 |
seek | -0.018 |
Token | out |
Token ID | 503 |
Feature activation | +6.36e+00 |
Pos logit contributions | |
ding | +0.418 |
pans | +0.417 |
nam | +0.415 |
counters | +0.404 |
forward | +0.402 |
Neg logit contributions | |
zag | -0.456 |
oot | -0.425 |
uzz | -0.410 |
seek | -0.403 |
sometime | -0.385 |
Token | . |
Token ID | 13 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
nam | +0.371 |
pans | +0.360 |
ding | +0.357 |
counters | +0.353 |
forward | +0.343 |
Neg logit contributions | |
zag | -0.296 |
oot | -0.274 |
uzz | -0.263 |
sometime | -0.251 |
seek | -0.250 |
Token | And |
Token ID | 843 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
nam | +0.021 |
pans | +0.020 |
ding | +0.020 |
counters | +0.019 |
forward | +0.019 |
Neg logit contributions | |
zag | -0.028 |
uzz | -0.027 |
oot | -0.027 |
seek | -0.026 |
sometime | -0.025 |
Token | you |
Token ID | 345 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
counters | +0.092 |
pans | +0.092 |
ding | +0.091 |
forward | +0.089 |
nam | +0.089 |
Neg logit contributions | |
zag | -0.092 |
oot | -0.087 |
uzz | -0.085 |
sometime | -0.084 |
seek | -0.078 |
Token | have |
Token ID | 423 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
nam | +0.095 |
pans | +0.094 |
ding | +0.094 |
y | +0.093 |
counters | +0.090 |
Neg logit contributions | |
zag | -0.139 |
oot | -0.131 |
uzz | -0.127 |
seek | -0.127 |
ippy | -0.120 |
Token | pieces |
Token ID | 5207 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
zag | +0.031 |
oot | +0.029 |
uzz | +0.028 |
seek | +0.028 |
sometime | +0.027 |
Neg logit contributions | |
pans | -0.019 |
nam | -0.019 |
ding | -0.019 |
counters | -0.018 |
forward | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
zag | +0.058 |
oot | +0.054 |
uzz | +0.051 |
seek | +0.049 |
sometime | +0.047 |
Neg logit contributions | |
nam | -0.068 |
pans | -0.067 |
ding | -0.067 |
counters | -0.066 |
ju | -0.064 |
Token | They |
Token ID | 1119 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
nam | +0.021 |
pans | +0.021 |
ding | +0.021 |
counters | +0.020 |
forward | +0.020 |
Neg logit contributions | |
zag | -0.028 |
oot | -0.027 |
uzz | -0.026 |
seek | -0.025 |
sometime | -0.024 |
Token | heard |
Token ID | 2982 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
pans | +0.022 |
ding | +0.022 |
forward | +0.022 |
counters | +0.022 |
nam | +0.022 |
Neg logit contributions | |
zag | -0.027 |
oot | -0.026 |
uzz | -0.025 |
seek | -0.024 |
gy | -0.024 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
nam | +0.076 |
pans | +0.076 |
counters | +0.073 |
forward | +0.073 |
ding | +0.073 |
Neg logit contributions | |
zag | -0.073 |
oot | -0.069 |
uzz | -0.069 |
seek | -0.064 |
sometime | -0.062 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.34e+00 |
Pos logit contributions | |
nam | +0.130 |
ju | +0.128 |
brightest | +0.123 |
redd | +0.120 |
fres | +0.113 |
Neg logit contributions | |
zag | -0.104 |
gy | -0.097 |
oot | -0.095 |
uzz | -0.090 |
istle | -0.089 |
Token | and |
Token ID | 290 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
nam | +0.452 |
ding | +0.438 |
pans | +0.438 |
counters | +0.430 |
ju | +0.427 |
Neg logit contributions | |
zag | -0.426 |
oot | -0.399 |
uzz | -0.392 |
seek | -0.365 |
gy | -0.365 |
Token | tried |
Token ID | 3088 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
brightest | +0.049 |
ju | +0.048 |
redd | +0.046 |
sc | +0.044 |
forward | +0.044 |
Neg logit contributions | |
uzz | -0.025 |
gy | -0.024 |
now | -0.024 |
oot | -0.023 |
again | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
zag | +0.040 |
oot | +0.040 |
ebra | +0.037 |
ogo | +0.037 |
ippy | +0.036 |
Neg logit contributions | |
nam | -0.024 |
pans | -0.024 |
ding | -0.023 |
y | -0.023 |
forward | -0.022 |
Token | hide |
Token ID | 7808 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
zag | +0.033 |
oot | +0.031 |
uzz | +0.030 |
seek | +0.029 |
sometime | +0.028 |
Neg logit contributions | |
pans | -0.026 |
nam | -0.026 |
ding | -0.026 |
counters | -0.025 |
forward | -0.024 |
Token | under |
Token ID | 739 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
zag | +0.023 |
oot | +0.022 |
uzz | +0.021 |
seek | +0.021 |
sometime | +0.020 |
Neg logit contributions | |
nam | -0.019 |
pans | -0.019 |
ding | -0.018 |
counters | -0.018 |
forward | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
nam | +0.162 |
pans | +0.158 |
ding | +0.156 |
counters | +0.154 |
ju | +0.150 |
Neg logit contributions | |
zag | -0.142 |
oot | -0.131 |
uzz | -0.128 |
seek | -0.122 |
sometime | -0.121 |
Token | They |
Token ID | 1119 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
nam | +0.030 |
pans | +0.029 |
ding | +0.029 |
counters | +0.028 |
forward | +0.028 |
Neg logit contributions | |
zag | -0.038 |
uzz | -0.036 |
oot | -0.036 |
seek | -0.034 |
sometime | -0.034 |
Token | see |
Token ID | 766 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
pans | +0.045 |
nam | +0.045 |
counters | +0.044 |
ding | +0.044 |
forward | +0.043 |
Neg logit contributions | |
zag | -0.040 |
oot | -0.036 |
uzz | -0.035 |
seek | -0.034 |
gy | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
zag | +0.003 |
uzz | +0.003 |
oot | +0.003 |
seek | +0.003 |
gy | +0.003 |
Neg logit contributions | |
pans | -0.004 |
nam | -0.004 |
ding | -0.003 |
counters | -0.003 |
forward | -0.003 |
Token | giant |
Token ID | 6175 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
nam | +0.041 |
counters | +0.039 |
forward | +0.039 |
pans | +0.038 |
sc | +0.037 |
Neg logit contributions | |
zag | -0.060 |
oot | -0.054 |
uzz | -0.052 |
gy | -0.050 |
sometime | -0.050 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.34e+00 |
Pos logit contributions | |
nam | +0.064 |
pans | +0.061 |
counters | +0.060 |
ding | +0.060 |
forward | +0.059 |
Neg logit contributions | |
zag | -0.053 |
oot | -0.048 |
uzz | -0.046 |
seek | -0.044 |
sometime | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
nam | +0.375 |
pans | +0.366 |
ding | +0.360 |
counters | +0.360 |
forward | +0.342 |
Neg logit contributions | |
zag | -0.503 |
oot | -0.474 |
uzz | -0.466 |
seek | -0.445 |
gy | -0.433 |
Token | the |
Token ID | 262 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
zag | +0.036 |
oot | +0.034 |
uzz | +0.031 |
seek | +0.031 |
ippy | +0.030 |
Neg logit contributions | |
pans | -0.021 |
ding | -0.021 |
nam | -0.020 |
y | -0.020 |
counters | -0.019 |
Token | hill |
Token ID | 12788 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
nam | +0.043 |
pans | +0.043 |
ding | +0.042 |
counters | +0.041 |
forward | +0.040 |
Neg logit contributions | |
zag | -0.052 |
oot | -0.049 |
uzz | -0.048 |
seek | -0.046 |
sometime | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
zag | +0.054 |
oot | +0.050 |
uzz | +0.048 |
seek | +0.047 |
sometime | +0.045 |
Neg logit contributions | |
nam | -0.059 |
pans | -0.059 |
ding | -0.058 |
counters | -0.057 |
forward | -0.056 |
Token | He |
Token ID | 679 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
nam | +0.034 |
pans | +0.032 |
ding | +0.032 |
counters | +0.032 |
forward | +0.031 |
Neg logit contributions | |
zag | -0.036 |
uzz | -0.034 |
oot | -0.033 |
seek | -0.032 |
sometime | -0.031 |
Token | lovely |
Token ID | 14081 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
ding | +0.089 |
pans | +0.086 |
y | +0.084 |
forward | +0.083 |
nam | +0.081 |
Neg logit contributions | |
zag | -0.145 |
oot | -0.138 |
seek | -0.136 |
uzz | -0.133 |
sometime | -0.129 |
Token | little |
Token ID | 1310 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
pans | +0.039 |
nam | +0.039 |
ding | +0.039 |
counters | +0.038 |
forward | +0.037 |
Neg logit contributions | |
zag | -0.042 |
oot | -0.039 |
uzz | -0.038 |
seek | -0.037 |
sometime | -0.035 |
Token | dog |
Token ID | 3290 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
nam | +0.130 |
counters | +0.124 |
pans | +0.124 |
ding | +0.123 |
forward | +0.115 |
Neg logit contributions | |
zag | -0.171 |
oot | -0.163 |
uzz | -0.160 |
gy | -0.155 |
sometime | -0.154 |
Token | called |
Token ID | 1444 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
zag | +0.109 |
oot | +0.102 |
uzz | +0.099 |
seek | +0.095 |
sometime | +0.091 |
Neg logit contributions | |
ding | -0.113 |
pans | -0.113 |
nam | -0.113 |
counters | -0.111 |
forward | -0.110 |
Token | Zig |
Token ID | 24992 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
pans | +0.218 |
nam | +0.217 |
ding | +0.215 |
counters | +0.213 |
forward | +0.204 |
Neg logit contributions | |
zag | -0.184 |
oot | -0.171 |
uzz | -0.167 |
seek | -0.158 |
gy | -0.153 |
Token | zag |
Token ID | 50183 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
oot | +0.081 |
seek | +0.067 |
sometime | +0.061 |
uzz | +0.058 |
zag | +0.052 |
Neg logit contributions | |
forward | -0.367 |
ding | -0.364 |
de | -0.358 |
spec | -0.356 |
low | -0.352 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
zag | +0.529 |
oot | +0.523 |
uzz | +0.501 |
seek | +0.480 |
sometime | +0.473 |
Neg logit contributions | |
ding | -0.481 |
pans | -0.474 |
nam | -0.474 |
counters | -0.465 |
forward | -0.457 |
Token | Zig |
Token ID | 24992 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
zag | +0.015 |
oot | +0.014 |
seek | +0.013 |
uzz | +0.013 |
sometime | +0.013 |
Neg logit contributions | |
ding | -0.014 |
nam | -0.013 |
pans | -0.013 |
forward | -0.013 |
counters | -0.013 |
Token | zag |
Token ID | 50183 |
Feature activation | -9.38e+00 |
Pos logit contributions | |
oot | +0.064 |
seek | +0.050 |
sometime | +0.050 |
recess | +0.046 |
seeker | +0.042 |
Neg logit contributions | |
ding | -0.291 |
de | -0.291 |
spec | -0.284 |
low | -0.280 |
forward | -0.278 |
Token | was |
Token ID | 373 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
oot | +0.543 |
zag | +0.542 |
uzz | +0.528 |
seek | +0.499 |
sometime | +0.490 |
Neg logit contributions | |
ding | -0.391 |
pans | -0.379 |
nam | -0.375 |
counters | -0.374 |
y | -0.369 |
Token | a |
Token ID | 257 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
zag | +0.041 |
oot | +0.038 |
uzz | +0.037 |
gy | +0.036 |
seek | +0.036 |
Neg logit contributions | |
pans | -0.026 |
nam | -0.026 |
counters | -0.025 |
ding | -0.024 |
ju | -0.023 |
Token | played |
Token ID | 2826 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
nam | +0.051 |
pans | +0.051 |
ding | +0.050 |
forward | +0.049 |
counters | +0.049 |
Neg logit contributions | |
zag | -0.077 |
oot | -0.073 |
uzz | -0.070 |
seek | -0.070 |
sometime | -0.067 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
zag | +0.197 |
oot | +0.193 |
uzz | +0.183 |
seek | +0.177 |
ogo | +0.174 |
Neg logit contributions | |
y | -0.111 |
ding | -0.110 |
pans | -0.109 |
forward | -0.109 |
counters | -0.108 |
Token | - |
Token ID | 12 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
zag | +0.069 |
oot | +0.064 |
seek | +0.061 |
uzz | +0.060 |
ogo | +0.057 |
Neg logit contributions | |
pans | -0.058 |
nam | -0.057 |
forward | -0.056 |
counters | -0.056 |
y | -0.055 |
Token | and |
Token ID | 392 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
zag | +0.083 |
oot | +0.079 |
uzz | +0.077 |
seek | +0.076 |
sometime | +0.073 |
Neg logit contributions | |
nam | -0.045 |
pans | -0.045 |
ding | -0.045 |
counters | -0.043 |
forward | -0.042 |
Token | - |
Token ID | 12 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
pans | +0.103 |
nam | +0.102 |
ding | +0.101 |
counters | +0.100 |
forward | +0.098 |
Neg logit contributions | |
zag | -0.091 |
oot | -0.084 |
uzz | -0.082 |
seek | -0.078 |
sometime | -0.077 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.94e+00 |
Pos logit contributions | |
zag | +0.018 |
oot | +0.013 |
uzz | +0.013 |
sometime | +0.009 |
ogo | +0.008 |
Neg logit contributions | |
sc | -0.109 |
nam | -0.109 |
ding | -0.109 |
counters | -0.108 |
pans | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
zag | +0.589 |
oot | +0.573 |
uzz | +0.538 |
seek | +0.520 |
gy | +0.509 |
Neg logit contributions | |
nam | -0.430 |
pans | -0.428 |
ding | -0.426 |
forward | -0.423 |
counters | -0.419 |
Token | After |
Token ID | 2293 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
zag | +0.000 |
oot | +0.000 |
uzz | +0.000 |
seek | +0.000 |
sometime | +0.000 |
Neg logit contributions | |
nam | -0.000 |
pans | -0.000 |
ding | -0.000 |
counters | -0.000 |
forward | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
y | +0.021 |
ding | +0.019 |
pans | +0.019 |
nam | +0.019 |
ready | +0.018 |
Neg logit contributions | |
zag | -0.038 |
oot | -0.036 |
uzz | -0.034 |
asured | -0.033 |
gy | -0.033 |
Token | while |
Token ID | 981 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
nam | +0.031 |
counters | +0.031 |
pans | +0.030 |
ding | +0.030 |
forward | +0.028 |
Neg logit contributions | |
zag | -0.046 |
oot | -0.041 |
sometime | -0.041 |
seek | -0.041 |
uzz | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
ding | +0.157 |
pans | +0.157 |
nam | +0.155 |
forward | +0.154 |
counters | +0.150 |
Neg logit contributions | |
zag | -0.171 |
oot | -0.160 |
uzz | -0.155 |
seek | -0.153 |
gy | -0.143 |
Token | play |
Token ID | 711 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
zag | +0.079 |
oot | +0.077 |
uzz | +0.074 |
seek | +0.071 |
ogo | +0.068 |
Neg logit contributions | |
nam | -0.065 |
ding | -0.065 |
pans | -0.064 |
counters | -0.063 |
y | -0.063 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
zag | +0.325 |
oot | +0.315 |
ogo | +0.314 |
fault | +0.301 |
ippy | +0.296 |
Neg logit contributions | |
y | -0.141 |
sc | -0.131 |
forward | -0.125 |
low | -0.118 |
pans | -0.112 |
Token | - |
Token ID | 12 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
zag | +0.070 |
oot | +0.065 |
seek | +0.062 |
uzz | +0.060 |
ogo | +0.058 |
Neg logit contributions | |
pans | -0.051 |
nam | -0.050 |
forward | -0.049 |
counters | -0.048 |
y | -0.047 |
Token | and |
Token ID | 392 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
zag | +0.075 |
oot | +0.071 |
uzz | +0.069 |
seek | +0.068 |
gy | +0.065 |
Neg logit contributions | |
pans | -0.043 |
nam | -0.043 |
ding | -0.043 |
counters | -0.042 |
forward | -0.040 |
Token | - |
Token ID | 12 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
pans | +0.114 |
nam | +0.114 |
ding | +0.112 |
counters | +0.111 |
forward | +0.109 |
Neg logit contributions | |
zag | -0.097 |
oot | -0.089 |
uzz | -0.087 |
seek | -0.083 |
sometime | -0.081 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.90e+00 |
Pos logit contributions | |
zag | +0.016 |
uzz | +0.013 |
oot | +0.013 |
sometime | +0.010 |
ogo | +0.010 |
Neg logit contributions | |
nam | -0.101 |
sc | -0.101 |
counters | -0.100 |
ding | -0.099 |
forward | -0.099 |
Token | behind |
Token ID | 2157 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
zag | +0.582 |
oot | +0.561 |
uzz | +0.523 |
seek | +0.509 |
gy | +0.503 |
Neg logit contributions | |
nam | -0.447 |
pans | -0.441 |
forward | -0.434 |
ding | -0.432 |
counters | -0.428 |
Token | them |
Token ID | 606 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
pans | +0.058 |
nam | +0.057 |
ding | +0.057 |
counters | +0.056 |
forward | +0.056 |
Neg logit contributions | |
zag | -0.080 |
oot | -0.076 |
uzz | -0.072 |
seek | -0.071 |
sometime | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
pans | +0.008 |
nam | +0.008 |
ding | +0.008 |
counters | +0.008 |
forward | +0.008 |
Neg logit contributions | |
zag | -0.007 |
oot | -0.006 |
uzz | -0.006 |
seek | -0.006 |
sometime | -0.006 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
zag | +0.024 |
oot | +0.023 |
uzz | +0.022 |
seek | +0.022 |
sometime | +0.021 |
Neg logit contributions | |
nam | -0.016 |
pans | -0.016 |
ding | -0.016 |
counters | -0.016 |
forward | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
pans | +0.085 |
nam | +0.085 |
ding | +0.085 |
counters | +0.083 |
forward | +0.082 |
Neg logit contributions | |
zag | -0.081 |
oot | -0.076 |
uzz | -0.073 |
seek | -0.071 |
sometime | -0.068 |
Token | play |
Token ID | 711 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
zag | +0.079 |
oot | +0.076 |
uzz | +0.075 |
seek | +0.070 |
ippy | +0.069 |
Neg logit contributions | |
pans | -0.069 |
y | -0.069 |
nam | -0.068 |
ding | -0.067 |
counters | -0.067 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
zag | +0.320 |
uzz | +0.311 |
oot | +0.304 |
seek | +0.290 |
ogo | +0.286 |
Neg logit contributions | |
pans | -0.126 |
y | -0.123 |
ding | -0.122 |
counters | -0.120 |
nam | -0.117 |
Token | - |
Token ID | 12 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
zag | +0.059 |
oot | +0.053 |
uzz | +0.052 |
seek | +0.051 |
sometime | +0.049 |
Neg logit contributions | |
pans | -0.052 |
nam | -0.050 |
counters | -0.049 |
y | -0.048 |
ding | -0.047 |
Token | and |
Token ID | 392 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
zag | +0.074 |
oot | +0.070 |
uzz | +0.068 |
seek | +0.067 |
sometime | +0.064 |
Neg logit contributions | |
nam | -0.040 |
pans | -0.039 |
ding | -0.039 |
counters | -0.038 |
forward | -0.037 |
Token | - |
Token ID | 12 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
nam | +0.123 |
pans | +0.122 |
ding | +0.122 |
counters | +0.120 |
forward | +0.118 |
Neg logit contributions | |
zag | -0.096 |
oot | -0.089 |
uzz | -0.085 |
seek | -0.082 |
sometime | -0.078 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.88e+00 |
Pos logit contributions | |
zag | +0.016 |
uzz | +0.012 |
sometime | +0.012 |
oot | +0.012 |
ogo | +0.008 |
Neg logit contributions | |
nam | -0.095 |
counters | -0.095 |
sc | -0.094 |
pans | -0.094 |
ding | -0.094 |
Token | with |
Token ID | 351 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
zag | +0.620 |
oot | +0.600 |
uzz | +0.566 |
seek | +0.545 |
gy | +0.539 |
Neg logit contributions | |
nam | -0.409 |
pans | -0.403 |
ding | -0.394 |
counters | -0.391 |
forward | -0.390 |
Token | her |
Token ID | 607 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
zag | +0.014 |
oot | +0.013 |
uzz | +0.012 |
seek | +0.012 |
sometime | +0.012 |
Neg logit contributions | |
nam | -0.011 |
pans | -0.010 |
ding | -0.010 |
counters | -0.010 |
y | -0.010 |
Token | friends |
Token ID | 2460 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
zag | +0.026 |
oot | +0.025 |
seek | +0.024 |
uzz | +0.024 |
sometime | +0.022 |
Neg logit contributions | |
pans | -0.029 |
nam | -0.029 |
y | -0.028 |
ding | -0.027 |
counters | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
zag | +0.156 |
oot | +0.144 |
uzz | +0.140 |
seek | +0.135 |
sometime | +0.132 |
Neg logit contributions | |
ding | -0.162 |
pans | -0.162 |
nam | -0.161 |
counters | -0.158 |
forward | -0.152 |
Token | One |
Token ID | 1881 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
zag | +0.035 |
oot | +0.033 |
uzz | +0.030 |
seek | +0.030 |
ogo | +0.028 |
Neg logit contributions | |
nam | -0.036 |
ding | -0.035 |
counters | -0.035 |
pans | -0.035 |
forward | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
zag | +0.133 |
oot | +0.123 |
uzz | +0.118 |
seek | +0.116 |
sometime | +0.112 |
Neg logit contributions | |
nam | -0.138 |
pans | -0.137 |
ding | -0.135 |
counters | -0.133 |
forward | -0.130 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
zag | +0.026 |
oot | +0.024 |
uzz | +0.023 |
seek | +0.023 |
sometime | +0.022 |
Neg logit contributions | |
nam | -0.019 |
pans | -0.019 |
ding | -0.019 |
counters | -0.018 |
forward | -0.018 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
zag | +0.067 |
oot | +0.062 |
seek | +0.059 |
uzz | +0.058 |
ogo | +0.055 |
Neg logit contributions | |
pans | -0.053 |
nam | -0.051 |
counters | -0.049 |
y | -0.049 |
ding | -0.048 |
Token | and |
Token ID | 392 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
zag | +0.066 |
oot | +0.062 |
uzz | +0.061 |
seek | +0.059 |
sometime | +0.057 |
Neg logit contributions | |
nam | -0.044 |
pans | -0.044 |
ding | -0.043 |
counters | -0.042 |
forward | -0.041 |
Token | - |
Token ID | 12 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
pans | +0.103 |
nam | +0.103 |
ding | +0.101 |
counters | +0.100 |
forward | +0.099 |
Neg logit contributions | |
zag | -0.089 |
oot | -0.082 |
uzz | -0.080 |
seek | -0.076 |
sometime | -0.075 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.84e+00 |
Pos logit contributions | |
zag | +0.015 |
uzz | +0.012 |
oot | +0.011 |
sometime | +0.007 |
ogo | +0.007 |
Neg logit contributions | |
sc | -0.096 |
nam | -0.096 |
ding | -0.095 |
counters | -0.095 |
pans | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | -7.12e-06 |
Pos logit contributions | |
zag | +0.557 |
oot | +0.535 |
uzz | +0.504 |
seek | +0.488 |
gy | +0.474 |
Neg logit contributions | |
nam | -0.462 |
pans | -0.460 |
ding | -0.457 |
counters | -0.448 |
forward | -0.447 |
Token | Mia |
Token ID | 32189 |
Feature activation | -8.45e-01 |
Token | was |
Token ID | 373 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
zag | +0.051 |
oot | +0.050 |
uzz | +0.047 |
seek | +0.045 |
ippy | +0.043 |
Neg logit contributions | |
ding | -0.035 |
pans | -0.035 |
counters | -0.035 |
y | -0.035 |
nam | -0.034 |
Token | so |
Token ID | 523 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
zag | +0.032 |
oot | +0.030 |
uzz | +0.029 |
seek | +0.029 |
sometime | +0.028 |
Neg logit contributions | |
pans | -0.017 |
nam | -0.017 |
counters | -0.016 |
ding | -0.016 |
forward | -0.015 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
pans | +0.025 |
counters | +0.025 |
nam | +0.023 |
spec | +0.023 |
sc | +0.023 |
Neg logit contributions | |
zag | -0.035 |
uzz | -0.033 |
oot | -0.032 |
seek | -0.031 |
sometime | -0.030 |
Token | played |
Token ID | 2826 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
zag | +0.039 |
uzz | +0.036 |
gy | +0.035 |
oot | +0.034 |
sometime | +0.033 |
Neg logit contributions | |
pans | -0.043 |
nam | -0.042 |
counters | -0.041 |
ding | -0.041 |
spec | -0.040 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
zag | +0.181 |
oot | +0.168 |
uzz | +0.163 |
seek | +0.159 |
sometime | +0.154 |
Neg logit contributions | |
nam | -0.159 |
pans | -0.157 |
ding | -0.156 |
counters | -0.152 |
forward | -0.149 |
Token | - |
Token ID | 12 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
zag | +0.053 |
oot | +0.049 |
uzz | +0.047 |
seek | +0.046 |
sometime | +0.044 |
Neg logit contributions | |
pans | -0.058 |
nam | -0.057 |
ding | -0.057 |
counters | -0.056 |
forward | -0.056 |
Token | and |
Token ID | 392 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
zag | +0.067 |
oot | +0.064 |
seek | +0.064 |
uzz | +0.060 |
gy | +0.057 |
Neg logit contributions | |
nam | -0.051 |
pans | -0.050 |
ding | -0.049 |
counters | -0.048 |
spec | -0.047 |
Token | - |
Token ID | 12 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
nam | +0.131 |
ding | +0.128 |
pans | +0.126 |
counters | +0.124 |
ju | +0.122 |
Neg logit contributions | |
zag | -0.088 |
oot | -0.083 |
uzz | -0.075 |
seek | -0.075 |
gy | -0.071 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.84e+00 |
Pos logit contributions | |
zag | +0.024 |
oot | +0.020 |
uzz | +0.018 |
seek | +0.017 |
sometime | +0.014 |
Neg logit contributions | |
nam | -0.094 |
pans | -0.094 |
ding | -0.093 |
counters | -0.092 |
forward | -0.091 |
Token | and |
Token ID | 290 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
zag | +0.516 |
oot | +0.481 |
uzz | +0.464 |
seek | +0.451 |
sometime | +0.434 |
Neg logit contributions | |
nam | -0.508 |
pans | -0.507 |
ding | -0.504 |
counters | -0.494 |
forward | -0.485 |
Token | had |
Token ID | 550 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
zag | +0.022 |
oot | +0.020 |
uzz | +0.020 |
seek | +0.019 |
sometime | +0.018 |
Neg logit contributions | |
nam | -0.023 |
pans | -0.023 |
ding | -0.023 |
counters | -0.022 |
forward | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
zag | +0.103 |
oot | +0.097 |
uzz | +0.094 |
seek | +0.092 |
sometime | +0.089 |
Neg logit contributions | |
nam | -0.066 |
pans | -0.066 |
ding | -0.065 |
counters | -0.063 |
forward | -0.062 |
Token | grand |
Token ID | 4490 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
nam | +0.015 |
pans | +0.015 |
counters | +0.015 |
ding | +0.015 |
forward | +0.013 |
Neg logit contributions | |
zag | -0.027 |
uzz | -0.024 |
oot | -0.024 |
sometime | -0.024 |
gy | -0.023 |
Token | time |
Token ID | 640 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
ding | +0.096 |
counters | +0.095 |
pans | +0.095 |
forward | +0.092 |
y | +0.092 |
Neg logit contributions | |
zag | -0.077 |
oot | -0.070 |
uzz | -0.069 |
seek | -0.065 |
sometime | -0.063 |
Token | like |
Token ID | 588 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
zag | +0.031 |
oot | +0.028 |
uzz | +0.027 |
seek | +0.027 |
sometime | +0.025 |
Neg logit contributions | |
nam | -0.036 |
pans | -0.035 |
ding | -0.035 |
counters | -0.035 |
forward | -0.034 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
nam | +0.022 |
pans | +0.022 |
counters | +0.021 |
ding | +0.021 |
forward | +0.021 |
Neg logit contributions | |
zag | -0.018 |
oot | -0.017 |
uzz | -0.016 |
seek | -0.016 |
sometime | -0.015 |
Token | - |
Token ID | 12 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
zag | +0.059 |
oot | +0.055 |
uzz | +0.053 |
seek | +0.052 |
sometime | +0.049 |
Neg logit contributions | |
pans | -0.061 |
nam | -0.059 |
ding | -0.059 |
counters | -0.059 |
y | -0.058 |
Token | and |
Token ID | 392 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
zag | +0.077 |
oot | +0.073 |
seek | +0.071 |
uzz | +0.070 |
gy | +0.066 |
Neg logit contributions | |
nam | -0.049 |
ding | -0.048 |
pans | -0.048 |
counters | -0.047 |
forward | -0.045 |
Token | - |
Token ID | 12 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
nam | +0.128 |
ding | +0.126 |
pans | +0.123 |
counters | +0.122 |
forward | +0.122 |
Neg logit contributions | |
zag | -0.089 |
oot | -0.083 |
seek | -0.077 |
uzz | -0.076 |
gy | -0.072 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.82e+00 |
Pos logit contributions | |
zag | +0.013 |
oot | +0.009 |
uzz | +0.008 |
sometime | +0.006 |
gy | +0.003 |
Neg logit contributions | |
nam | -0.108 |
pans | -0.108 |
ding | -0.107 |
counters | -0.106 |
forward | -0.106 |
Token | and |
Token ID | 290 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
zag | +0.537 |
oot | +0.513 |
uzz | +0.487 |
seek | +0.470 |
gy | +0.454 |
Neg logit contributions | |
pans | -0.480 |
nam | -0.478 |
ding | -0.476 |
counters | -0.467 |
forward | -0.463 |
Token | tag |
Token ID | 7621 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
zag | +0.032 |
oot | +0.029 |
uzz | +0.028 |
seek | +0.027 |
sometime | +0.026 |
Neg logit contributions | |
pans | -0.035 |
nam | -0.035 |
ding | -0.035 |
counters | -0.035 |
forward | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
zag | +0.123 |
oot | +0.115 |
uzz | +0.111 |
seek | +0.108 |
sometime | +0.103 |
Neg logit contributions | |
nam | -0.124 |
pans | -0.124 |
ding | -0.123 |
counters | -0.121 |
forward | -0.119 |
Token | One |
Token ID | 1881 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
zag | +0.051 |
oot | +0.049 |
uzz | +0.045 |
seek | +0.045 |
gy | +0.042 |
Neg logit contributions | |
nam | -0.048 |
ding | -0.048 |
pans | -0.048 |
counters | -0.047 |
forward | -0.046 |
Token | day |
Token ID | 1110 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
zag | +0.282 |
oot | +0.277 |
uzz | +0.267 |
seek | +0.264 |
sometime | +0.250 |
Neg logit contributions | |
ding | -0.165 |
pans | -0.165 |
y | -0.159 |
forward | -0.159 |
nam | -0.159 |
Token | of |
Token ID | 286 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
zag | +0.230 |
oot | +0.212 |
uzz | +0.211 |
gy | +0.204 |
seek | +0.200 |
Neg logit contributions | |
forward | -0.168 |
nam | -0.165 |
pans | -0.165 |
sc | -0.164 |
y | -0.161 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
nam | +0.142 |
pans | +0.141 |
ding | +0.139 |
y | +0.137 |
counters | +0.136 |
Neg logit contributions | |
zag | -0.164 |
oot | -0.155 |
uzz | -0.149 |
seek | -0.144 |
gy | -0.142 |
Token | - |
Token ID | 12 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
zag | +0.058 |
oot | +0.053 |
seek | +0.051 |
uzz | +0.050 |
sometime | +0.048 |
Neg logit contributions | |
pans | -0.051 |
nam | -0.050 |
counters | -0.049 |
forward | -0.049 |
ding | -0.048 |
Token | and |
Token ID | 392 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
zag | +0.075 |
oot | +0.072 |
uzz | +0.069 |
seek | +0.068 |
sometime | +0.066 |
Neg logit contributions | |
nam | -0.044 |
pans | -0.044 |
ding | -0.044 |
counters | -0.043 |
forward | -0.041 |
Token | - |
Token ID | 12 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
pans | +0.118 |
nam | +0.118 |
ding | +0.117 |
counters | +0.115 |
forward | +0.113 |
Neg logit contributions | |
zag | -0.098 |
oot | -0.090 |
uzz | -0.087 |
seek | -0.083 |
sometime | -0.081 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.82e+00 |
Pos logit contributions | |
zag | +0.016 |
uzz | +0.011 |
oot | +0.011 |
sometime | +0.008 |
gy | +0.007 |
Neg logit contributions | |
nam | -0.101 |
counters | -0.100 |
ding | -0.100 |
pans | -0.100 |
forward | -0.099 |
Token | , |
Token ID | 11 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
zag | +0.543 |
oot | +0.514 |
uzz | +0.488 |
seek | +0.474 |
gy | +0.460 |
Neg logit contributions | |
pans | -0.479 |
nam | -0.479 |
ding | -0.470 |
counters | -0.467 |
forward | -0.461 |
Token | so |
Token ID | 523 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
zag | +0.045 |
oot | +0.042 |
uzz | +0.041 |
sometime | +0.040 |
seek | +0.040 |
Neg logit contributions | |
pans | -0.038 |
nam | -0.038 |
ding | -0.037 |
counters | -0.036 |
forward | -0.036 |
Token | she |
Token ID | 673 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
nam | +0.015 |
pans | +0.015 |
ding | +0.015 |
counters | +0.014 |
forward | +0.014 |
Neg logit contributions | |
zag | -0.030 |
oot | -0.028 |
uzz | -0.027 |
seek | -0.027 |
sometime | -0.026 |
Token | decided |
Token ID | 3066 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
pans | +0.037 |
nam | +0.036 |
y | +0.036 |
counters | +0.036 |
ding | +0.035 |
Neg logit contributions | |
zag | -0.065 |
oot | -0.063 |
uzz | -0.060 |
seek | -0.059 |
ippy | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
nam | +0.032 |
forward | +0.032 |
ding | +0.031 |
pans | +0.031 |
y | +0.030 |
Neg logit contributions | |
zag | -0.042 |
uzz | -0.040 |
oot | -0.038 |
ippy | -0.038 |
gy | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
zag | +0.121 |
oot | +0.114 |
uzz | +0.110 |
seek | +0.106 |
sometime | +0.102 |
Neg logit contributions | |
ding | -0.129 |
pans | -0.129 |
nam | -0.128 |
counters | -0.126 |
forward | -0.125 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
zag | +0.055 |
oot | +0.049 |
seek | +0.048 |
uzz | +0.047 |
sometime | +0.045 |
Neg logit contributions | |
nam | -0.053 |
pans | -0.053 |
ding | -0.053 |
counters | -0.052 |
forward | -0.052 |
Token | - |
Token ID | 12 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
zag | +0.056 |
oot | +0.052 |
uzz | +0.050 |
seek | +0.049 |
sometime | +0.047 |
Neg logit contributions | |
pans | -0.060 |
nam | -0.059 |
ding | -0.059 |
counters | -0.058 |
forward | -0.057 |
Token | and |
Token ID | 392 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
zag | +0.072 |
oot | +0.068 |
seek | +0.067 |
uzz | +0.065 |
gy | +0.061 |
Neg logit contributions | |
nam | -0.048 |
pans | -0.048 |
ding | -0.047 |
counters | -0.046 |
forward | -0.044 |
Token | - |
Token ID | 12 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
nam | +0.124 |
ding | +0.123 |
pans | +0.122 |
counters | +0.120 |
forward | +0.118 |
Neg logit contributions | |
zag | -0.093 |
oot | -0.086 |
uzz | -0.081 |
seek | -0.079 |
gy | -0.075 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.81e+00 |
Pos logit contributions | |
zag | +0.013 |
oot | +0.008 |
uzz | +0.007 |
sometime | +0.004 |
seek | +0.004 |
Neg logit contributions | |
nam | -0.107 |
ding | -0.107 |
pans | -0.106 |
counters | -0.105 |
forward | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
zag | +0.498 |
oot | +0.463 |
uzz | +0.447 |
seek | +0.433 |
sometime | +0.416 |
Neg logit contributions | |
nam | -0.524 |
pans | -0.523 |
ding | -0.520 |
counters | -0.510 |
forward | -0.500 |
Token | and |
Token ID | 290 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
zag | +0.036 |
oot | +0.030 |
seek | +0.030 |
uzz | +0.029 |
gy | +0.028 |
Neg logit contributions | |
nam | -0.056 |
pans | -0.055 |
ding | -0.054 |
counters | -0.054 |
forward | -0.052 |
Token | even |
Token ID | 772 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
zag | +0.020 |
oot | +0.019 |
uzz | +0.018 |
seek | +0.018 |
sometime | +0.017 |
Neg logit contributions | |
pans | -0.022 |
ding | -0.021 |
nam | -0.021 |
counters | -0.021 |
forward | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
zag | +0.156 |
seek | +0.139 |
oot | +0.138 |
uzz | +0.137 |
sometime | +0.137 |
Neg logit contributions | |
pans | -0.155 |
counters | -0.155 |
ding | -0.152 |
nam | -0.147 |
forward | -0.144 |
Token | game |
Token ID | 983 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
nam | +0.011 |
counters | +0.011 |
pans | +0.011 |
ding | +0.011 |
forward | +0.011 |
Neg logit contributions | |
zag | -0.016 |
uzz | -0.014 |
sometime | -0.014 |
oot | -0.014 |
seek | -0.013 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
pans | +0.062 |
nam | +0.061 |
counters | +0.060 |
ding | +0.059 |
ju | +0.058 |
Neg logit contributions | |
zag | -0.049 |
oot | -0.044 |
uzz | -0.042 |
gy | -0.040 |
seek | -0.040 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
zag | +0.101 |
oot | +0.099 |
uzz | +0.095 |
seek | +0.091 |
ogo | +0.090 |
Neg logit contributions | |
pans | -0.052 |
y | -0.052 |
ding | -0.051 |
nam | -0.051 |
forward | -0.051 |
Token | - |
Token ID | 12 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
zag | +0.061 |
oot | +0.057 |
uzz | +0.054 |
seek | +0.054 |
sometime | +0.051 |
Neg logit contributions | |
pans | -0.056 |
nam | -0.054 |
counters | -0.054 |
ding | -0.053 |
forward | -0.052 |
Token | and |
Token ID | 392 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
zag | +0.079 |
oot | +0.075 |
uzz | +0.073 |
seek | +0.072 |
gy | +0.068 |
Neg logit contributions | |
nam | -0.045 |
pans | -0.045 |
ding | -0.045 |
counters | -0.043 |
forward | -0.042 |
Token | - |
Token ID | 12 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
nam | +0.123 |
pans | +0.123 |
ding | +0.122 |
counters | +0.120 |
forward | +0.118 |
Neg logit contributions | |
zag | -0.100 |
oot | -0.092 |
uzz | -0.088 |
seek | -0.085 |
sometime | -0.082 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.76e+00 |
Pos logit contributions | |
zag | +0.016 |
uzz | +0.012 |
oot | +0.012 |
sometime | +0.009 |
ogo | +0.008 |
Neg logit contributions | |
nam | -0.104 |
counters | -0.103 |
sc | -0.103 |
pans | -0.103 |
ding | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
zag | +0.574 |
oot | +0.546 |
uzz | +0.522 |
seek | +0.507 |
gy | +0.490 |
Neg logit contributions | |
nam | -0.440 |
pans | -0.439 |
ding | -0.434 |
counters | -0.427 |
forward | -0.422 |
Token | Sammy |
Token ID | 44067 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
zag | +0.029 |
oot | +0.028 |
uzz | +0.027 |
seek | +0.026 |
sometime | +0.025 |
Neg logit contributions | |
nam | -0.023 |
pans | -0.023 |
ding | -0.023 |
counters | -0.022 |
forward | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
zag | +0.065 |
oot | +0.062 |
uzz | +0.061 |
seek | +0.058 |
sometime | +0.056 |
Neg logit contributions | |
pans | -0.044 |
ding | -0.043 |
counters | -0.043 |
nam | -0.043 |
y | -0.042 |
Token | hiding |
Token ID | 11816 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
zag | +0.054 |
oot | +0.051 |
uzz | +0.049 |
seek | +0.048 |
sometime | +0.047 |
Neg logit contributions | |
nam | -0.033 |
ding | -0.033 |
pans | -0.032 |
counters | -0.032 |
forward | -0.031 |
Token | behind |
Token ID | 2157 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
zag | +0.367 |
oot | +0.356 |
seek | +0.343 |
uzz | +0.331 |
sometime | +0.322 |
Neg logit contributions | |
pans | -0.166 |
forward | -0.165 |
nam | -0.164 |
ding | -0.154 |
y | -0.153 |
Token | play |
Token ID | 711 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
zag | +0.081 |
oot | +0.077 |
uzz | +0.076 |
seek | +0.070 |
ogo | +0.068 |
Neg logit contributions | |
pans | -0.077 |
nam | -0.076 |
y | -0.075 |
ding | -0.074 |
counters | -0.074 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
zag | +0.342 |
uzz | +0.329 |
oot | +0.326 |
seek | +0.305 |
ogo | +0.301 |
Neg logit contributions | |
pans | -0.149 |
ding | -0.146 |
y | -0.145 |
counters | -0.144 |
nam | -0.140 |
Token | - |
Token ID | 12 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
zag | +0.070 |
oot | +0.063 |
uzz | +0.062 |
seek | +0.060 |
sometime | +0.058 |
Neg logit contributions | |
pans | -0.068 |
nam | -0.066 |
counters | -0.066 |
ding | -0.064 |
y | -0.063 |
Token | and |
Token ID | 392 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
zag | +0.075 |
oot | +0.071 |
uzz | +0.069 |
seek | +0.068 |
gy | +0.066 |
Neg logit contributions | |
nam | -0.041 |
pans | -0.041 |
ding | -0.041 |
counters | -0.040 |
forward | -0.039 |
Token | - |
Token ID | 12 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
nam | +0.128 |
pans | +0.127 |
ding | +0.127 |
counters | +0.124 |
forward | +0.122 |
Neg logit contributions | |
zag | -0.099 |
oot | -0.092 |
uzz | -0.088 |
seek | -0.085 |
sometime | -0.081 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.75e+00 |
Pos logit contributions | |
zag | +0.016 |
sometime | +0.013 |
uzz | +0.013 |
oot | +0.012 |
ogo | +0.010 |
Neg logit contributions | |
nam | -0.094 |
counters | -0.093 |
forward | -0.092 |
sc | -0.092 |
ding | -0.092 |
Token | with |
Token ID | 351 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
zag | +0.623 |
oot | +0.600 |
uzz | +0.564 |
seek | +0.546 |
gy | +0.539 |
Neg logit contributions | |
nam | -0.406 |
pans | -0.400 |
ding | -0.387 |
y | -0.384 |
counters | -0.383 |
Token | her |
Token ID | 607 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
zag | +0.032 |
oot | +0.030 |
uzz | +0.028 |
seek | +0.028 |
sometime | +0.027 |
Neg logit contributions | |
nam | -0.026 |
pans | -0.026 |
ding | -0.025 |
counters | -0.025 |
y | -0.024 |
Token | friends |
Token ID | 2460 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
zag | +0.035 |
oot | +0.034 |
uzz | +0.032 |
seek | +0.031 |
sometime | +0.030 |
Neg logit contributions | |
nam | -0.040 |
pans | -0.040 |
y | -0.038 |
ding | -0.038 |
counters | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
zag | +0.166 |
oot | +0.154 |
uzz | +0.149 |
seek | +0.144 |
sometime | +0.139 |
Neg logit contributions | |
pans | -0.173 |
nam | -0.173 |
ding | -0.172 |
counters | -0.169 |
forward | -0.164 |
Token | One |
Token ID | 1881 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
zag | +0.048 |
oot | +0.044 |
uzz | +0.042 |
seek | +0.041 |
gy | +0.039 |
Neg logit contributions | |
nam | -0.057 |
pans | -0.056 |
ding | -0.056 |
counters | -0.056 |
forward | -0.055 |
Token | played |
Token ID | 2826 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
zag | +0.043 |
oot | +0.041 |
seek | +0.039 |
uzz | +0.038 |
ippy | +0.037 |
Neg logit contributions | |
nam | -0.032 |
pans | -0.029 |
ding | -0.028 |
y | -0.028 |
forward | -0.028 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
zag | +0.212 |
oot | +0.208 |
uzz | +0.205 |
seek | +0.194 |
ogo | +0.189 |
Neg logit contributions | |
y | -0.117 |
sc | -0.111 |
ding | -0.109 |
forward | -0.107 |
pans | -0.106 |
Token | - |
Token ID | 12 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
zag | +0.057 |
oot | +0.053 |
seek | +0.051 |
uzz | +0.051 |
sometime | +0.049 |
Neg logit contributions | |
pans | -0.050 |
nam | -0.048 |
counters | -0.048 |
y | -0.047 |
ding | -0.047 |
Token | and |
Token ID | 392 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
zag | +0.068 |
oot | +0.065 |
uzz | +0.063 |
seek | +0.062 |
sometime | +0.060 |
Neg logit contributions | |
nam | -0.037 |
pans | -0.037 |
ding | -0.036 |
counters | -0.035 |
forward | -0.034 |
Token | - |
Token ID | 12 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
pans | +0.125 |
nam | +0.125 |
ding | +0.123 |
counters | +0.122 |
forward | +0.119 |
Neg logit contributions | |
zag | -0.104 |
oot | -0.095 |
uzz | -0.093 |
seek | -0.089 |
sometime | -0.087 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.73e+00 |
Pos logit contributions | |
zag | +0.015 |
uzz | +0.012 |
sometime | +0.011 |
oot | +0.010 |
ogo | +0.009 |
Neg logit contributions | |
sc | -0.088 |
nam | -0.087 |
counters | -0.086 |
ding | -0.086 |
forward | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
zag | +0.569 |
oot | +0.557 |
uzz | +0.522 |
seek | +0.499 |
ogo | +0.493 |
Neg logit contributions | |
nam | -0.426 |
pans | -0.425 |
ding | -0.424 |
y | -0.422 |
forward | -0.419 |
Token | tag |
Token ID | 7621 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
zag | +0.037 |
oot | +0.033 |
uzz | +0.032 |
seek | +0.031 |
gy | +0.031 |
Neg logit contributions | |
pans | -0.041 |
nam | -0.040 |
ding | -0.040 |
counters | -0.040 |
forward | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
zag | +0.112 |
oot | +0.107 |
uzz | +0.102 |
seek | +0.097 |
sometime | +0.095 |
Neg logit contributions | |
pans | -0.113 |
ding | -0.112 |
nam | -0.112 |
counters | -0.110 |
forward | -0.108 |
Token | and |
Token ID | 290 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
zag | +0.029 |
oot | +0.026 |
uzz | +0.025 |
seek | +0.024 |
gy | +0.023 |
Neg logit contributions | |
nam | -0.041 |
pans | -0.041 |
ding | -0.041 |
counters | -0.040 |
forward | -0.040 |
Token | other |
Token ID | 584 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
zag | +0.022 |
oot | +0.020 |
uzz | +0.019 |
seek | +0.019 |
sometime | +0.018 |
Neg logit contributions | |
nam | -0.023 |
pans | -0.023 |
ding | -0.023 |
counters | -0.022 |
forward | -0.022 |
Token | finally |
Token ID | 3443 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
zag | +0.025 |
oot | +0.023 |
uzz | +0.022 |
seek | +0.022 |
gy | +0.021 |
Neg logit contributions | |
ding | -0.028 |
nam | -0.028 |
pans | -0.028 |
forward | -0.027 |
counters | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
zag | +0.235 |
uzz | +0.220 |
oot | +0.212 |
seek | +0.203 |
ogo | +0.203 |
Neg logit contributions | |
forward | -0.177 |
ding | -0.172 |
y | -0.161 |
nam | -0.159 |
spec | -0.155 |
Token | the |
Token ID | 262 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
zag | +0.032 |
oot | +0.030 |
uzz | +0.029 |
seek | +0.028 |
sometime | +0.028 |
Neg logit contributions | |
pans | -0.028 |
nam | -0.028 |
ding | -0.028 |
counters | -0.027 |
forward | -0.026 |
Token | z |
Token ID | 1976 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
nam | +0.027 |
pans | +0.026 |
counters | +0.026 |
ding | +0.026 |
forward | +0.025 |
Neg logit contributions | |
zag | -0.031 |
oot | -0.027 |
uzz | -0.027 |
sometime | -0.026 |
seek | -0.026 |
Token | ig |
Token ID | 328 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
gy | +0.074 |
zag | +0.074 |
uzz | +0.074 |
seek | +0.073 |
oot | +0.069 |
Neg logit contributions | |
forward | -0.165 |
ding | -0.161 |
spec | -0.155 |
pans | -0.149 |
brightest | -0.147 |
Token | zag |
Token ID | 50183 |
Feature activation | -9.73e+00 |
Pos logit contributions | |
uzz | +0.371 |
oot | +0.369 |
zag | +0.365 |
seek | +0.356 |
sometime | +0.343 |
Neg logit contributions | |
ding | -0.302 |
pans | -0.294 |
counters | -0.292 |
forward | -0.290 |
y | -0.276 |
Token | had |
Token ID | 550 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
zag | +0.538 |
oot | +0.513 |
uzz | +0.500 |
seek | +0.483 |
sometime | +0.465 |
Neg logit contributions | |
ding | -0.461 |
pans | -0.458 |
nam | -0.455 |
counters | -0.449 |
forward | -0.440 |
Token | an |
Token ID | 281 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
zag | +0.093 |
oot | +0.087 |
uzz | +0.085 |
ippy | +0.081 |
seek | +0.079 |
Neg logit contributions | |
y | -0.068 |
ding | -0.067 |
nam | -0.066 |
counters | -0.065 |
ju | -0.065 |
Token | idea |
Token ID | 2126 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
zag | +0.078 |
uzz | +0.072 |
oot | +0.071 |
seek | +0.071 |
gy | +0.068 |
Neg logit contributions | |
nam | -0.044 |
ding | -0.044 |
forward | -0.042 |
y | -0.042 |
counters | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
zag | +0.146 |
oot | +0.134 |
uzz | +0.130 |
seek | +0.128 |
gy | +0.123 |
Neg logit contributions | |
pans | -0.138 |
ding | -0.138 |
nam | -0.137 |
counters | -0.136 |
forward | -0.135 |
Token | It |
Token ID | 632 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
zag | +0.008 |
oot | +0.007 |
uzz | +0.007 |
seek | +0.007 |
sometime | +0.007 |
Neg logit contributions | |
pans | -0.006 |
nam | -0.006 |
ding | -0.006 |
counters | -0.006 |
forward | -0.006 |
Token | would |
Token ID | 561 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
nam | +0.034 |
forward | +0.033 |
ding | +0.032 |
pans | +0.032 |
y | +0.031 |
Neg logit contributions | |
zag | -0.054 |
oot | -0.051 |
seek | -0.049 |
uzz | -0.049 |
ippy | -0.047 |
Token | splash |
Token ID | 22870 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
y | +0.072 |
ding | +0.070 |
forward | +0.069 |
neat | +0.065 |
low | +0.065 |
Neg logit contributions | |
oot | -0.102 |
zag | -0.101 |
seek | -0.099 |
uzz | -0.094 |
ippy | -0.092 |
Token | and |
Token ID | 290 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
zag | +0.138 |
oot | +0.131 |
seek | +0.126 |
uzz | +0.125 |
ippy | +0.120 |
Neg logit contributions | |
pans | -0.069 |
nam | -0.068 |
ding | -0.068 |
forward | -0.067 |
y | -0.065 |
Token | z |
Token ID | 1976 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
zag | +0.017 |
oot | +0.016 |
uzz | +0.015 |
seek | +0.015 |
sometime | +0.014 |
Neg logit contributions | |
nam | -0.021 |
pans | -0.021 |
ding | -0.021 |
counters | -0.020 |
forward | -0.020 |
Token | ig |
Token ID | 328 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
zag | +0.129 |
seek | +0.124 |
gy | +0.122 |
sometime | +0.119 |
mistake | +0.113 |
Neg logit contributions | |
forward | -0.121 |
ding | -0.104 |
pans | -0.100 |
sc | -0.099 |
y | -0.097 |
Token | zag |
Token ID | 50183 |
Feature activation | -9.73e+00 |
Pos logit contributions | |
sometime | +0.251 |
uzz | +0.247 |
oot | +0.246 |
zag | +0.246 |
seek | +0.240 |
Neg logit contributions | |
pans | -0.373 |
forward | -0.372 |
ding | -0.372 |
counters | -0.359 |
y | -0.351 |
Token | in |
Token ID | 287 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
zag | +0.603 |
oot | +0.576 |
uzz | +0.557 |
seek | +0.543 |
sometime | +0.526 |
Neg logit contributions | |
ding | -0.399 |
pans | -0.398 |
nam | -0.396 |
counters | -0.386 |
forward | -0.382 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
nam | +0.015 |
y | +0.015 |
pans | +0.015 |
forward | +0.015 |
ding | +0.014 |
Neg logit contributions | |
zag | -0.031 |
oot | -0.030 |
seek | -0.028 |
ogo | -0.027 |
uzz | -0.027 |
Token | water |
Token ID | 1660 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
nam | +0.015 |
pans | +0.014 |
ding | +0.014 |
counters | +0.013 |
forward | +0.013 |
Neg logit contributions | |
zag | -0.015 |
oot | -0.013 |
gy | -0.013 |
uzz | -0.013 |
seek | -0.013 |
Token | together |
Token ID | 1978 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
nam | +0.124 |
pans | +0.124 |
ding | +0.123 |
counters | +0.121 |
forward | +0.117 |
Neg logit contributions | |
zag | -0.113 |
oot | -0.105 |
uzz | -0.101 |
seek | -0.098 |
sometime | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
zag | +0.138 |
oot | +0.128 |
uzz | +0.123 |
seek | +0.119 |
sometime | +0.116 |
Neg logit contributions | |
pans | -0.155 |
nam | -0.155 |
ding | -0.154 |
counters | -0.152 |
forward | -0.145 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
pans | +0.071 |
nam | +0.069 |
counters | +0.068 |
ding | +0.067 |
ju | +0.066 |
Neg logit contributions | |
zag | -0.049 |
oot | -0.043 |
gy | -0.041 |
uzz | -0.040 |
seek | -0.039 |
Token | hide |
Token ID | 7808 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
zag | +0.097 |
oot | +0.095 |
uzz | +0.092 |
ogo | +0.088 |
seek | +0.087 |
Neg logit contributions | |
y | -0.045 |
pans | -0.044 |
ding | -0.044 |
counters | -0.043 |
forward | -0.043 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
zag | +0.053 |
oot | +0.048 |
uzz | +0.047 |
seek | +0.046 |
sometime | +0.044 |
Neg logit contributions | |
pans | -0.049 |
counters | -0.047 |
nam | -0.047 |
ding | -0.046 |
forward | -0.045 |
Token | and |
Token ID | 392 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
zag | +0.071 |
oot | +0.067 |
uzz | +0.065 |
seek | +0.064 |
sometime | +0.062 |
Neg logit contributions | |
nam | -0.038 |
pans | -0.038 |
ding | -0.038 |
counters | -0.037 |
forward | -0.036 |
Token | - |
Token ID | 12 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
pans | +0.127 |
nam | +0.126 |
ding | +0.125 |
counters | +0.123 |
forward | +0.121 |
Neg logit contributions | |
zag | -0.107 |
oot | -0.098 |
uzz | -0.096 |
seek | -0.091 |
sometime | -0.089 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.71e+00 |
Pos logit contributions | |
zag | +0.015 |
uzz | +0.013 |
oot | +0.012 |
sometime | +0.011 |
ogo | +0.010 |
Neg logit contributions | |
nam | -0.091 |
sc | -0.090 |
counters | -0.090 |
ding | -0.089 |
pans | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
zag | +0.587 |
oot | +0.563 |
uzz | +0.534 |
seek | +0.516 |
gy | +0.502 |
Neg logit contributions | |
nam | -0.423 |
pans | -0.420 |
ding | -0.415 |
counters | -0.409 |
forward | -0.406 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
zag | +0.035 |
oot | +0.032 |
uzz | +0.031 |
seek | +0.030 |
gy | +0.030 |
Neg logit contributions | |
nam | -0.033 |
pans | -0.033 |
ding | -0.033 |
counters | -0.032 |
forward | -0.032 |
Token | my |
Token ID | 1820 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
zag | +0.120 |
oot | +0.119 |
uzz | +0.118 |
seek | +0.115 |
sometime | +0.106 |
Neg logit contributions | |
counters | -0.054 |
pans | -0.053 |
ding | -0.053 |
y | -0.052 |
forward | -0.051 |
Token | was |
Token ID | 373 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
counters | +0.031 |
y | +0.031 |
pans | +0.031 |
ding | +0.030 |
nam | +0.029 |
Neg logit contributions | |
zag | -0.057 |
oot | -0.056 |
uzz | -0.055 |
seek | -0.052 |
ippy | -0.050 |
Token | hiding |
Token ID | 11816 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
zag | +0.049 |
oot | +0.047 |
uzz | +0.045 |
seek | +0.044 |
sometime | +0.043 |
Neg logit contributions | |
nam | -0.030 |
ding | -0.030 |
pans | -0.029 |
forward | -0.029 |
counters | -0.029 |
Token | ement |
Token ID | 972 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
nam | +0.175 |
pans | +0.174 |
ding | +0.173 |
counters | +0.168 |
forward | +0.164 |
Neg logit contributions | |
zag | -0.302 |
oot | -0.286 |
uzz | -0.278 |
seek | -0.272 |
sometime | -0.264 |
Token | as |
Token ID | 355 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
pans | +0.027 |
nam | +0.027 |
ding | +0.027 |
counters | +0.027 |
forward | +0.026 |
Neg logit contributions | |
zag | -0.026 |
oot | -0.025 |
uzz | -0.024 |
seek | -0.023 |
sometime | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
zag | +0.035 |
uzz | +0.033 |
oot | +0.032 |
sometime | +0.030 |
seek | +0.028 |
Neg logit contributions | |
counters | -0.047 |
pans | -0.046 |
nam | -0.046 |
ding | -0.045 |
ju | -0.045 |
Token | z |
Token ID | 1976 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
nam | +0.029 |
forward | +0.028 |
counters | +0.028 |
pans | +0.027 |
ding | +0.027 |
Neg logit contributions | |
zag | -0.032 |
oot | -0.029 |
uzz | -0.028 |
ad | -0.027 |
seek | -0.026 |
Token | ig |
Token ID | 328 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
uzz | +0.080 |
sometime | +0.079 |
seek | +0.079 |
zag | +0.079 |
gy | +0.074 |
Neg logit contributions | |
ding | -0.143 |
forward | -0.142 |
spec | -0.141 |
pans | -0.139 |
de | -0.134 |
Token | zag |
Token ID | 50183 |
Feature activation | -9.70e+00 |
Pos logit contributions | |
zag | +0.317 |
oot | +0.305 |
uzz | +0.302 |
seek | +0.293 |
sometime | +0.283 |
Neg logit contributions | |
pans | -0.359 |
ding | -0.359 |
nam | -0.348 |
counters | -0.348 |
forward | -0.346 |
Token | soared |
Token ID | 35292 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
zag | +0.551 |
oot | +0.510 |
uzz | +0.490 |
seek | +0.479 |
gy | +0.463 |
Neg logit contributions | |
nam | -0.470 |
pans | -0.466 |
ding | -0.459 |
counters | -0.453 |
forward | -0.442 |
Token | in |
Token ID | 287 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
zag | +0.002 |
oot | +0.002 |
uzz | +0.002 |
seek | +0.002 |
sometime | +0.002 |
Neg logit contributions | |
nam | -0.001 |
pans | -0.001 |
ding | -0.001 |
counters | -0.001 |
forward | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
ding | +0.020 |
pans | +0.019 |
forward | +0.019 |
nam | +0.019 |
y | +0.018 |
Neg logit contributions | |
zag | -0.034 |
oot | -0.033 |
seek | -0.031 |
uzz | -0.030 |
ogo | -0.029 |
Token | sky |
Token ID | 6766 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
nam | +0.020 |
pans | +0.019 |
counters | +0.018 |
forward | +0.017 |
stressed | +0.016 |
Neg logit contributions | |
zag | -0.031 |
oot | -0.027 |
gy | -0.027 |
ad | -0.027 |
seek | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
nam | +0.088 |
pans | +0.086 |
counters | +0.084 |
ding | +0.084 |
forward | +0.081 |
Neg logit contributions | |
zag | -0.072 |
oot | -0.065 |
uzz | -0.063 |
seek | -0.061 |
sometime | -0.060 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
pans | +0.129 |
ding | +0.128 |
nam | +0.127 |
counters | +0.125 |
forward | +0.121 |
Neg logit contributions | |
zag | -0.179 |
oot | -0.170 |
uzz | -0.164 |
seek | -0.160 |
sometime | -0.156 |
Token | hide |
Token ID | 7808 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
zag | +0.096 |
oot | +0.091 |
uzz | +0.089 |
seek | +0.085 |
ogo | +0.085 |
Neg logit contributions | |
forward | -0.049 |
counters | -0.048 |
pans | -0.048 |
ding | -0.048 |
nam | -0.047 |
Token | - |
Token ID | 12 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
zag | +0.051 |
oot | +0.047 |
uzz | +0.046 |
seek | +0.045 |
sometime | +0.042 |
Neg logit contributions | |
nam | -0.048 |
pans | -0.048 |
forward | -0.047 |
counters | -0.047 |
ding | -0.047 |
Token | and |
Token ID | 392 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
zag | +0.070 |
oot | +0.066 |
seek | +0.064 |
uzz | +0.064 |
gy | +0.061 |
Neg logit contributions | |
pans | -0.045 |
nam | -0.044 |
ding | -0.044 |
counters | -0.043 |
forward | -0.041 |
Token | - |
Token ID | 12 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
nam | +0.136 |
pans | +0.136 |
ding | +0.136 |
counters | +0.133 |
forward | +0.129 |
Neg logit contributions | |
zag | -0.106 |
oot | -0.098 |
uzz | -0.093 |
seek | -0.091 |
gy | -0.086 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.68e+00 |
Pos logit contributions | |
zag | +0.013 |
oot | +0.009 |
uzz | +0.008 |
sometime | +0.005 |
ogo | +0.004 |
Neg logit contributions | |
nam | -0.099 |
ding | -0.098 |
pans | -0.097 |
counters | -0.097 |
forward | -0.097 |
Token | with |
Token ID | 351 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
zag | +0.509 |
oot | +0.475 |
uzz | +0.458 |
seek | +0.443 |
gy | +0.425 |
Neg logit contributions | |
nam | -0.499 |
pans | -0.496 |
ding | -0.494 |
counters | -0.485 |
forward | -0.480 |
Token | her |
Token ID | 607 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
zag | +0.011 |
oot | +0.011 |
uzz | +0.010 |
seek | +0.010 |
sometime | +0.010 |
Neg logit contributions | |
ding | -0.011 |
pans | -0.011 |
nam | -0.011 |
counters | -0.011 |
forward | -0.010 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
zag | +0.020 |
oot | +0.018 |
uzz | +0.018 |
seek | +0.017 |
sometime | +0.016 |
Neg logit contributions | |
nam | -0.018 |
pans | -0.018 |
ding | -0.017 |
counters | -0.017 |
forward | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
zag | +0.149 |
oot | +0.139 |
uzz | +0.134 |
seek | +0.130 |
sometime | +0.124 |
Neg logit contributions | |
nam | -0.160 |
pans | -0.159 |
ding | -0.158 |
counters | -0.155 |
forward | -0.153 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
zag | +0.025 |
oot | +0.023 |
uzz | +0.022 |
seek | +0.022 |
ogo | +0.021 |
Neg logit contributions | |
forward | -0.015 |
nam | -0.015 |
ding | -0.015 |
counters | -0.014 |
pans | -0.014 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
pans | +0.068 |
nam | +0.065 |
counters | +0.065 |
ju | +0.064 |
ding | +0.064 |
Neg logit contributions | |
zag | -0.059 |
oot | -0.053 |
uzz | -0.052 |
seek | -0.050 |
gy | -0.050 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
zag | +0.106 |
oot | +0.102 |
uzz | +0.098 |
seek | +0.094 |
ogo | +0.091 |
Neg logit contributions | |
pans | -0.063 |
nam | -0.063 |
ding | -0.062 |
counters | -0.061 |
forward | -0.061 |
Token | - |
Token ID | 12 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
zag | +0.065 |
oot | +0.060 |
uzz | +0.058 |
seek | +0.056 |
sometime | +0.054 |
Neg logit contributions | |
pans | -0.066 |
nam | -0.066 |
ding | -0.065 |
counters | -0.065 |
forward | -0.064 |
Token | and |
Token ID | 392 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
zag | +0.071 |
oot | +0.067 |
seek | +0.065 |
uzz | +0.065 |
gy | +0.061 |
Neg logit contributions | |
pans | -0.043 |
ding | -0.043 |
nam | -0.043 |
counters | -0.041 |
forward | -0.040 |
Token | - |
Token ID | 12 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
nam | +0.127 |
pans | +0.127 |
ding | +0.126 |
counters | +0.124 |
forward | +0.122 |
Neg logit contributions | |
zag | -0.101 |
oot | -0.093 |
uzz | -0.089 |
seek | -0.087 |
sometime | -0.082 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.68e+00 |
Pos logit contributions | |
zag | +0.013 |
oot | +0.010 |
uzz | +0.010 |
sometime | +0.008 |
ogo | +0.007 |
Neg logit contributions | |
nam | -0.095 |
counters | -0.094 |
sc | -0.094 |
ding | -0.094 |
forward | -0.094 |
Token | behind |
Token ID | 2157 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
zag | +0.542 |
oot | +0.511 |
uzz | +0.491 |
seek | +0.477 |
sometime | +0.459 |
Neg logit contributions | |
nam | -0.467 |
pans | -0.465 |
ding | -0.461 |
counters | -0.453 |
forward | -0.445 |
Token | the |
Token ID | 262 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
nam | +0.045 |
pans | +0.045 |
counters | +0.044 |
ding | +0.043 |
y | +0.042 |
Neg logit contributions | |
zag | -0.069 |
oot | -0.067 |
uzz | -0.061 |
seek | -0.060 |
ogo | -0.058 |
Token | old |
Token ID | 1468 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
nam | +0.011 |
ding | +0.011 |
pans | +0.011 |
forward | +0.010 |
counters | +0.010 |
Neg logit contributions | |
zag | -0.016 |
oot | -0.015 |
uzz | -0.014 |
seek | -0.014 |
gy | -0.014 |
Token | barn |
Token ID | 25203 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
pans | +0.015 |
nam | +0.015 |
ding | +0.014 |
counters | +0.014 |
spec | +0.013 |
Neg logit contributions | |
zag | -0.020 |
oot | -0.019 |
uzz | -0.019 |
seek | -0.018 |
sometime | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
nam | +0.046 |
pans | +0.046 |
ding | +0.045 |
counters | +0.044 |
forward | +0.044 |
Neg logit contributions | |
zag | -0.041 |
oot | -0.038 |
uzz | -0.036 |
seek | -0.036 |
gy | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
zag | +0.172 |
oot | +0.163 |
uzz | +0.162 |
sometime | +0.155 |
gy | +0.153 |
Neg logit contributions | |
pans | -0.125 |
ding | -0.125 |
counters | -0.125 |
nam | -0.122 |
forward | -0.115 |
Token | hide |
Token ID | 7808 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
pans | +0.031 |
ding | +0.031 |
counters | +0.031 |
forward | +0.031 |
nam | +0.030 |
Neg logit contributions | |
zag | -0.035 |
uzz | -0.032 |
oot | -0.032 |
sometime | -0.030 |
seek | -0.030 |
Token | - |
Token ID | 12 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
zag | +0.051 |
oot | +0.048 |
seek | +0.046 |
uzz | +0.045 |
sometime | +0.043 |
Neg logit contributions | |
pans | -0.036 |
nam | -0.035 |
counters | -0.034 |
ding | -0.034 |
forward | -0.034 |
Token | and |
Token ID | 392 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
zag | +0.050 |
oot | +0.048 |
uzz | +0.046 |
seek | +0.046 |
sometime | +0.043 |
Neg logit contributions | |
nam | -0.030 |
pans | -0.030 |
ding | -0.030 |
counters | -0.029 |
forward | -0.028 |
Token | - |
Token ID | 12 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
pans | +0.098 |
nam | +0.098 |
ding | +0.097 |
counters | +0.096 |
forward | +0.095 |
Neg logit contributions | |
zag | -0.098 |
oot | -0.090 |
uzz | -0.088 |
seek | -0.084 |
sometime | -0.082 |
Token | seek |
Token ID | 36163 |
Feature activation | -9.68e+00 |
Pos logit contributions | |
zag | +0.020 |
oot | +0.015 |
uzz | +0.015 |
sometime | +0.012 |
gy | +0.011 |
Neg logit contributions | |
nam | -0.081 |
ding | -0.080 |
sc | -0.080 |
counters | -0.080 |
forward | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
zag | +0.550 |
oot | +0.531 |
uzz | +0.498 |
seek | +0.482 |
gy | +0.471 |
Neg logit contributions | |
nam | -0.446 |
pans | -0.445 |
ding | -0.442 |
forward | -0.436 |
counters | -0.435 |
Token | The |
Token ID | 383 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
nam | +0.007 |
pans | +0.007 |
ding | +0.007 |
counters | +0.006 |
forward | +0.006 |
Neg logit contributions | |
zag | -0.008 |
oot | -0.008 |
uzz | -0.008 |
seek | -0.007 |
sometime | -0.007 |
Token | monkey |
Token ID | 21657 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
zag | +0.071 |
oot | +0.066 |
uzz | +0.064 |
seek | +0.062 |
sometime | +0.060 |
Neg logit contributions | |
nam | -0.063 |
pans | -0.062 |
ding | -0.062 |
counters | -0.061 |
forward | -0.060 |
Token | was |
Token ID | 373 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
zag | +0.180 |
oot | +0.178 |
uzz | +0.170 |
seek | +0.163 |
ippy | +0.158 |
Neg logit contributions | |
ding | -0.129 |
pans | -0.126 |
counters | -0.126 |
y | -0.126 |
nam | -0.122 |
Token | very |
Token ID | 845 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
zag | +0.035 |
oot | +0.033 |
uzz | +0.033 |
seek | +0.032 |
sometime | +0.031 |
Neg logit contributions | |
pans | -0.016 |
nam | -0.016 |
ding | -0.015 |
counters | -0.015 |
forward | -0.014 |
Token | He |
Token ID | 679 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
zag | +0.040 |
seek | +0.037 |
oot | +0.037 |
uzz | +0.035 |
gy | +0.034 |
Neg logit contributions | |
pans | -0.045 |
nam | -0.045 |
ding | -0.044 |
forward | -0.043 |
counters | -0.042 |
Token | had |
Token ID | 550 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
zag | +0.043 |
oot | +0.042 |
uzz | +0.041 |
seek | +0.040 |
ippy | +0.039 |
Neg logit contributions | |
pans | -0.027 |
ding | -0.026 |
nam | -0.026 |
y | -0.026 |
counters | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
zag | +0.082 |
oot | +0.079 |
uzz | +0.075 |
ippy | +0.070 |
seek | +0.069 |
Neg logit contributions | |
nam | -0.074 |
ding | -0.074 |
pans | -0.073 |
y | -0.073 |
counters | -0.072 |
Token | z |
Token ID | 1976 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
zag | +0.082 |
oot | +0.079 |
uzz | +0.076 |
seek | +0.073 |
ogo | +0.070 |
Neg logit contributions | |
ding | -0.051 |
nam | -0.051 |
pans | -0.051 |
counters | -0.050 |
y | -0.049 |
Token | ig |
Token ID | 328 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
gy | +0.134 |
zag | +0.131 |
seek | +0.124 |
sometime | +0.121 |
onna | +0.115 |
Neg logit contributions | |
forward | -0.128 |
ding | -0.106 |
pans | -0.094 |
nam | -0.094 |
counters | -0.091 |
Token | zag |
Token ID | 50183 |
Feature activation | -9.68e+00 |
Pos logit contributions | |
uzz | +0.399 |
sometime | +0.396 |
oot | +0.382 |
seek | +0.380 |
zag | +0.369 |
Neg logit contributions | |
ding | -0.240 |
forward | -0.240 |
counters | -0.219 |
pans | -0.218 |
nam | -0.203 |
Token | around |
Token ID | 1088 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
zag | +0.542 |
oot | +0.534 |
uzz | +0.515 |
seek | +0.492 |
ippy | +0.483 |
Neg logit contributions | |
ding | -0.444 |
forward | -0.432 |
pans | -0.428 |
nam | -0.428 |
counters | -0.421 |
Token | and |
Token ID | 290 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
zag | +0.014 |
oot | +0.013 |
uzz | +0.012 |
seek | +0.012 |
sometime | +0.011 |
Neg logit contributions | |
ding | -0.012 |
nam | -0.012 |
pans | -0.012 |
counters | -0.012 |
forward | -0.012 |
Token | make |
Token ID | 787 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
zag | +0.012 |
oot | +0.010 |
seek | +0.010 |
uzz | +0.010 |
sometime | +0.010 |
Neg logit contributions | |
pans | -0.012 |
nam | -0.011 |
ding | -0.011 |
counters | -0.011 |
forward | -0.011 |
Token | big |
Token ID | 1263 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
zag | +0.009 |
oot | +0.008 |
uzz | +0.008 |
seek | +0.008 |
sometime | +0.008 |
Neg logit contributions | |
nam | -0.007 |
pans | -0.007 |
ding | -0.007 |
counters | -0.007 |
forward | -0.007 |
Token | circles |
Token ID | 13332 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
nam | +0.095 |
pans | +0.095 |
ding | +0.094 |
counters | +0.092 |
forward | +0.090 |
Neg logit contributions | |
zag | -0.132 |
oot | -0.125 |
uzz | -0.121 |
seek | -0.118 |
sometime | -0.114 |
Token | porch |
Token ID | 33179 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
nam | +0.012 |
forward | +0.012 |
ding | +0.012 |
sc | +0.012 |
pans | +0.012 |
Neg logit contributions | |
zag | -0.013 |
gy | -0.012 |
oot | -0.011 |
uzz | -0.011 |
seek | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
nam | +0.077 |
pans | +0.077 |
ding | +0.074 |
counters | +0.072 |
forward | +0.071 |
Neg logit contributions | |
zag | -0.063 |
oot | -0.057 |
uzz | -0.055 |
seek | -0.054 |
gy | -0.052 |
Token | They |
Token ID | 1119 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
nam | +0.005 |
pans | +0.005 |
ding | +0.005 |
counters | +0.004 |
forward | +0.004 |
Neg logit contributions | |
zag | -0.006 |
uzz | -0.005 |
oot | -0.005 |
seek | -0.005 |
sometime | -0.005 |
Token | both |
Token ID | 1111 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
nam | +0.006 |
pans | +0.006 |
ding | +0.006 |
counters | +0.006 |
forward | +0.006 |
Neg logit contributions | |
zag | -0.010 |
oot | -0.009 |
uzz | -0.009 |
seek | -0.009 |
gy | -0.008 |
Token | reached |
Token ID | 4251 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
zag | +0.115 |
oot | +0.108 |
uzz | +0.106 |
seek | +0.102 |
sometime | +0.100 |
Neg logit contributions | |
pans | -0.083 |
nam | -0.082 |
ding | -0.081 |
counters | -0.080 |
forward | -0.078 |
Token | out |
Token ID | 503 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
nam | +0.020 |
pans | +0.020 |
ding | +0.020 |
counters | +0.019 |
forward | +0.019 |
Neg logit contributions | |
zag | -0.047 |
oot | -0.044 |
uzz | -0.043 |
seek | -0.043 |
sometime | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
forward | +0.284 |
ding | +0.282 |
pans | +0.279 |
y | +0.274 |
nam | +0.271 |
Neg logit contributions | |
zag | -0.328 |
oot | -0.308 |
seek | -0.302 |
uzz | -0.281 |
gy | -0.279 |
Token | touch |
Token ID | 3638 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
zag | +0.071 |
oot | +0.067 |
seek | +0.063 |
uzz | +0.062 |
ogo | +0.060 |
Neg logit contributions | |
nam | -0.050 |
pans | -0.049 |
ding | -0.049 |
y | -0.047 |
counters | -0.046 |
Token | them |
Token ID | 606 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
zag | +0.031 |
oot | +0.029 |
uzz | +0.029 |
sometime | +0.027 |
seek | +0.026 |
Neg logit contributions | |
nam | -0.037 |
pans | -0.037 |
counters | -0.036 |
ding | -0.036 |
forward | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
pans | +0.021 |
nam | +0.021 |
ding | +0.021 |
counters | +0.021 |
forward | +0.020 |
Neg logit contributions | |
zag | -0.017 |
oot | -0.016 |
uzz | -0.015 |
seek | -0.014 |
sometime | -0.014 |
Token | feeling |
Token ID | 4203 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
zag | +0.020 |
uzz | +0.019 |
oot | +0.017 |
sometime | +0.017 |
seek | +0.016 |
Neg logit contributions | |
pans | -0.024 |
nam | -0.023 |
counters | -0.023 |
ding | -0.022 |
sc | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
zag | +0.049 |
oot | +0.045 |
uzz | +0.043 |
seek | +0.042 |
sometime | +0.041 |
Neg logit contributions | |
nam | -0.045 |
pans | -0.045 |
ding | -0.044 |
counters | -0.044 |
forward | -0.041 |
Token | prevent |
Token ID | 2948 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
zag | +0.089 |
oot | +0.085 |
uzz | +0.082 |
seek | +0.079 |
ippy | +0.076 |
Neg logit contributions | |
ding | -0.079 |
nam | -0.078 |
pans | -0.078 |
counters | -0.076 |
y | -0.074 |
Token | things |
Token ID | 1243 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
nam | +0.019 |
pans | +0.019 |
ding | +0.019 |
counters | +0.019 |
ju | +0.018 |
Neg logit contributions | |
zag | -0.019 |
oot | -0.018 |
uzz | -0.017 |
seek | -0.016 |
gy | -0.016 |
Token | from |
Token ID | 422 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
nam | +0.051 |
pans | +0.049 |
ding | +0.048 |
counters | +0.048 |
spec | +0.047 |
Neg logit contributions | |
zag | -0.047 |
oot | -0.044 |
seek | -0.039 |
uzz | -0.038 |
gy | -0.038 |
Token | getting |
Token ID | 1972 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
nam | +0.031 |
pans | +0.031 |
ding | +0.031 |
counters | +0.029 |
forward | +0.029 |
Neg logit contributions | |
zag | -0.039 |
oot | -0.037 |
uzz | -0.036 |
seek | -0.035 |
sometime | -0.033 |
Token | out |
Token ID | 503 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
counters | +0.033 |
pans | +0.033 |
nam | +0.033 |
ding | +0.032 |
spec | +0.032 |
Neg logit contributions | |
zag | -0.036 |
oot | -0.034 |
uzz | -0.032 |
seek | -0.031 |
gy | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
nam | +0.253 |
ding | +0.249 |
pans | +0.249 |
counters | +0.241 |
forward | +0.234 |
Neg logit contributions | |
zag | -0.297 |
oot | -0.277 |
uzz | -0.269 |
seek | -0.260 |
sometime | -0.255 |
Token | hand |
Token ID | 1021 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
pans | +0.128 |
nam | +0.128 |
ding | +0.127 |
counters | +0.124 |
forward | +0.122 |
Neg logit contributions | |
zag | -0.151 |
oot | -0.142 |
uzz | -0.136 |
seek | -0.134 |
sometime | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
nam | +0.201 |
ding | +0.192 |
pans | +0.185 |
brightest | +0.181 |
forward | +0.181 |
Neg logit contributions | |
zag | -0.135 |
oot | -0.123 |
gy | -0.116 |
seek | -0.115 |
uzz | -0.110 |
Token | Every |
Token ID | 3887 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
zag | +0.041 |
oot | +0.039 |
uzz | +0.037 |
seek | +0.037 |
sometime | +0.035 |
Neg logit contributions | |
nam | -0.031 |
pans | -0.031 |
ding | -0.031 |
counters | -0.030 |
forward | -0.029 |
Token | day |
Token ID | 1110 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
zag | +0.087 |
oot | +0.082 |
uzz | +0.080 |
seek | +0.078 |
sometime | +0.075 |
Neg logit contributions | |
nam | -0.063 |
pans | -0.062 |
ding | -0.062 |
counters | -0.061 |
forward | -0.059 |
Token | for |
Token ID | 329 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
pans | +0.087 |
nam | +0.086 |
ding | +0.085 |
forward | +0.084 |
counters | +0.084 |
Neg logit contributions | |
zag | -0.093 |
oot | -0.087 |
uzz | -0.084 |
seek | -0.082 |
sometime | -0.078 |
Token | this |
Token ID | 428 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
zag | +0.057 |
oot | +0.053 |
uzz | +0.052 |
seek | +0.051 |
gy | +0.049 |
Neg logit contributions | |
nam | -0.031 |
pans | -0.031 |
ding | -0.031 |
counters | -0.029 |
forward | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
zag | +0.098 |
oot | +0.090 |
uzz | +0.086 |
sometime | +0.084 |
seek | +0.084 |
Neg logit contributions | |
nam | -0.096 |
pans | -0.095 |
ding | -0.094 |
counters | -0.093 |
forward | -0.090 |
Token | It |
Token ID | 632 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
pans | +0.017 |
nam | +0.017 |
counters | +0.016 |
ding | +0.016 |
y | +0.015 |
Neg logit contributions | |
zag | -0.021 |
uzz | -0.021 |
oot | -0.020 |
sometime | -0.019 |
seek | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
zag | +0.038 |
oot | +0.034 |
gy | +0.033 |
uzz | +0.033 |
sometime | +0.032 |
Neg logit contributions | |
nam | -0.032 |
pans | -0.029 |
ding | -0.029 |
counters | -0.029 |
forward | -0.029 |
Token | called |
Token ID | 1444 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
counters | +0.062 |
ding | +0.061 |
pans | +0.060 |
spec | +0.060 |
nam | +0.060 |
Neg logit contributions | |
zag | -0.059 |
uzz | -0.055 |
oot | -0.054 |
sometime | -0.052 |
gy | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
nam | +0.280 |
pans | +0.276 |
counters | +0.274 |
ding | +0.271 |
spec | +0.265 |
Neg logit contributions | |
zag | -0.282 |
oot | -0.268 |
uzz | -0.263 |
gy | -0.241 |
sometime | -0.240 |
Token | net |
Token ID | 2010 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
counters | +0.044 |
nam | +0.044 |
spec | +0.041 |
pans | +0.040 |
forward | +0.040 |
Neg logit contributions | |
zag | -0.044 |
sometime | -0.036 |
oot | -0.035 |
gy | -0.035 |
uzz | -0.034 |
Token | ." |
Token ID | 526 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
nam | +0.052 |
pans | +0.051 |
ding | +0.051 |
counters | +0.050 |
forward | +0.049 |
Neg logit contributions | |
zag | -0.048 |
oot | -0.044 |
uzz | -0.043 |
seek | -0.042 |
sometime | -0.040 |
Token | He |
Token ID | 679 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
zag | +0.043 |
oot | +0.040 |
uzz | +0.039 |
seek | +0.038 |
gy | +0.036 |
Neg logit contributions | |
pans | -0.032 |
ding | -0.032 |
nam | -0.032 |
counters | -0.031 |
forward | -0.030 |
Token | takes |
Token ID | 2753 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
pans | +0.017 |
ding | +0.017 |
counters | +0.016 |
y | +0.016 |
nam | +0.016 |
Neg logit contributions | |
zag | -0.035 |
oot | -0.034 |
uzz | -0.033 |
seek | -0.033 |
gy | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
nam | +0.317 |
ding | +0.308 |
pans | +0.300 |
forward | +0.299 |
brightest | +0.298 |
Neg logit contributions | |
zag | -0.172 |
sometime | -0.151 |
seek | -0.146 |
uzz | -0.139 |
oot | -0.139 |
Token | They |
Token ID | 1119 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
zag | +0.021 |
uzz | +0.020 |
oot | +0.019 |
seek | +0.019 |
sometime | +0.018 |
Neg logit contributions | |
nam | -0.019 |
pans | -0.018 |
ding | -0.018 |
counters | -0.017 |
forward | -0.017 |
Token | got |
Token ID | 1392 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
zag | +0.009 |
oot | +0.009 |
uzz | +0.009 |
seek | +0.008 |
sometime | +0.008 |
Neg logit contributions | |
ding | -0.008 |
nam | -0.008 |
pans | -0.008 |
counters | -0.008 |
forward | -0.007 |
Token | out |
Token ID | 503 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
uzz | +0.017 |
sometime | +0.016 |
zag | +0.015 |
now | +0.015 |
gy | +0.015 |
Neg logit contributions | |
ding | -0.020 |
spec | -0.020 |
pared | -0.020 |
sc | -0.019 |
de | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
nam | +0.280 |
ding | +0.276 |
pans | +0.273 |
counters | +0.267 |
forward | +0.261 |
Neg logit contributions | |
zag | -0.334 |
oot | -0.312 |
uzz | -0.305 |
seek | -0.292 |
gy | -0.285 |
Token | pots |
Token ID | 32195 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
nam | +0.025 |
spec | +0.023 |
ding | +0.023 |
pared | +0.021 |
forward | +0.021 |
Neg logit contributions | |
zag | -0.026 |
ippy | -0.022 |
fault | -0.022 |
gy | -0.021 |
uzz | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
nam | +0.428 |
pans | +0.408 |
ding | +0.406 |
counters | +0.399 |
spec | +0.390 |
Neg logit contributions | |
zag | -0.266 |
oot | -0.242 |
uzz | -0.228 |
seek | -0.214 |
gy | -0.212 |
Token | pans |
Token ID | 36209 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
sometime | +0.004 |
seek | +0.004 |
gy | +0.004 |
zag | +0.004 |
now | +0.004 |
Neg logit contributions | |
forward | -0.002 |
pared | -0.002 |
spec | -0.001 |
sc | -0.001 |
ding | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
nam | +0.518 |
ding | +0.490 |
spec | +0.484 |
pans | +0.478 |
Hungry | +0.473 |
Neg logit contributions | |
zag | -0.282 |
oot | -0.235 |
gy | -0.231 |
uzz | -0.230 |
seek | -0.217 |
Token | and |
Token ID | 290 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
sometime | +0.014 |
zag | +0.014 |
now | +0.013 |
uzz | +0.013 |
gy | +0.013 |
Neg logit contributions | |
forward | -0.027 |
ding | -0.026 |
spec | -0.025 |
nam | -0.025 |
pared | -0.025 |
Token | started |
Token ID | 2067 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
forward | +0.002 |
ding | +0.002 |
spec | +0.002 |
pared | +0.002 |
sc | +0.002 |
Neg logit contributions | |
sometime | -0.001 |
zag | -0.001 |
now | -0.001 |
uzz | -0.001 |
gy | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
zag | +0.080 |
oot | +0.074 |
uzz | +0.071 |
seek | +0.069 |
gy | +0.066 |
Neg logit contributions | |
nam | -0.066 |
pans | -0.064 |
ding | -0.062 |
y | -0.062 |
counters | -0.062 |
Token | test |
Token ID | 1332 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
zag | +0.015 |
oot | +0.014 |
uzz | +0.013 |
seek | +0.013 |
sometime | +0.013 |
Neg logit contributions | |
nam | -0.015 |
ding | -0.015 |
pans | -0.015 |
counters | -0.015 |
forward | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
zag | +0.085 |
oot | +0.080 |
uzz | +0.078 |
seek | +0.074 |
gy | +0.071 |
Neg logit contributions | |
nam | -0.078 |
pans | -0.078 |
ding | -0.077 |
counters | -0.076 |
forward | -0.076 |
Token | She |
Token ID | 1375 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
zag | +0.005 |
uzz | +0.004 |
oot | +0.004 |
seek | +0.004 |
gy | +0.004 |
Neg logit contributions | |
nam | -0.005 |
pans | -0.005 |
ding | -0.005 |
forward | -0.004 |
counters | -0.004 |
Token | hugged |
Token ID | 41130 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
zag | +0.006 |
oot | +0.005 |
uzz | +0.005 |
seek | +0.005 |
gy | +0.005 |
Neg logit contributions | |
pans | -0.004 |
ding | -0.003 |
nam | -0.003 |
y | -0.003 |
counters | -0.003 |
Token | Mr |
Token ID | 1770 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
pans | +0.148 |
nam | +0.147 |
ding | +0.146 |
counters | +0.144 |
forward | +0.140 |
Neg logit contributions | |
zag | -0.136 |
oot | -0.128 |
uzz | -0.124 |
seek | -0.119 |
sometime | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
pans | +0.228 |
forward | +0.221 |
de | +0.218 |
y | +0.217 |
ding | +0.216 |
Neg logit contributions | |
zag | -0.308 |
oot | -0.290 |
seek | -0.281 |
uzz | -0.273 |
sometime | -0.256 |
Token | Fox |
Token ID | 5426 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
nam | +0.024 |
pans | +0.024 |
ding | +0.024 |
counters | +0.024 |
forward | +0.023 |
Neg logit contributions | |
zag | -0.020 |
oot | -0.019 |
uzz | -0.018 |
seek | -0.017 |
sometime | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
zag | +0.010 |
oot | +0.009 |
uzz | +0.009 |
seek | +0.009 |
sometime | +0.008 |
Neg logit contributions | |
pans | -0.010 |
ding | -0.009 |
nam | -0.009 |
counters | -0.009 |
forward | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
nam | +0.010 |
pans | +0.010 |
ding | +0.010 |
counters | +0.010 |
forward | +0.009 |
Neg logit contributions | |
zag | -0.015 |
oot | -0.014 |
uzz | -0.013 |
seek | -0.013 |
sometime | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
pans | +0.091 |
counters | +0.089 |
nam | +0.089 |
ding | +0.087 |
brightest | +0.085 |
Neg logit contributions | |
zag | -0.061 |
oot | -0.060 |
uzz | -0.058 |
seek | -0.053 |
sometime | -0.053 |
Token | slide |
Token ID | 10649 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
nam | +0.032 |
forward | +0.032 |
ding | +0.032 |
pans | +0.032 |
counters | +0.031 |
Neg logit contributions | |
zag | -0.035 |
oot | -0.031 |
seek | -0.030 |
uzz | -0.030 |
gy | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
zag | +0.114 |
oot | +0.107 |
uzz | +0.103 |
seek | +0.100 |
sometime | +0.095 |
Neg logit contributions | |
nam | -0.119 |
pans | -0.119 |
ding | -0.118 |
counters | -0.115 |
forward | -0.114 |
Token | It |
Token ID | 632 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
pans | +0.023 |
nam | +0.023 |
counters | +0.022 |
ding | +0.022 |
y | +0.020 |
Neg logit contributions | |
zag | -0.034 |
uzz | -0.034 |
oot | -0.033 |
sometime | -0.032 |
seek | -0.031 |
Token | will |
Token ID | 481 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
zag | +0.055 |
oot | +0.049 |
uzz | +0.049 |
sometime | +0.047 |
seek | +0.047 |
Neg logit contributions | |
nam | -0.040 |
pans | -0.038 |
counters | -0.038 |
ding | -0.037 |
forward | -0.036 |
Token | make |
Token ID | 787 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ding | +0.084 |
nam | +0.083 |
pans | +0.081 |
y | +0.080 |
brightest | +0.077 |
Neg logit contributions | |
zag | -0.094 |
oot | -0.091 |
seek | -0.088 |
uzz | -0.087 |
ippy | -0.084 |
Token | you |
Token ID | 345 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
nam | +0.013 |
pans | +0.013 |
counters | +0.013 |
forward | +0.013 |
ju | +0.012 |
Neg logit contributions | |
zag | -0.014 |
oot | -0.014 |
uzz | -0.013 |
sometime | -0.013 |
seek | -0.012 |
Token | happy |
Token ID | 3772 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
nam | +0.083 |
ding | +0.082 |
pans | +0.082 |
counters | +0.079 |
forward | +0.077 |
Neg logit contributions | |
zag | -0.127 |
oot | -0.121 |
uzz | -0.117 |
seek | -0.115 |
sometime | -0.110 |
Token | ." |
Token ID | 526 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
ding | +0.028 |
pans | +0.028 |
nam | +0.028 |
counters | +0.027 |
forward | +0.027 |
Neg logit contributions | |
zag | -0.030 |
oot | -0.028 |
uzz | -0.027 |
seek | -0.026 |
ippy | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
zag | +0.004 |
oot | +0.004 |
uzz | +0.004 |
seek | +0.003 |
sometime | +0.003 |
Neg logit contributions | |
nam | -0.004 |
pans | -0.004 |
ding | -0.004 |
counters | -0.004 |
forward | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
pans | +0.030 |
ding | +0.030 |
nam | +0.030 |
counters | +0.029 |
forward | +0.029 |
Neg logit contributions | |
zag | -0.040 |
oot | -0.038 |
seek | -0.036 |
uzz | -0.036 |
gy | -0.035 |
Token | Ben |
Token ID | 11696 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
pans | +0.041 |
nam | +0.041 |
ding | +0.041 |
counters | +0.040 |
forward | +0.039 |
Neg logit contributions | |
zag | -0.034 |
oot | -0.032 |
uzz | -0.030 |
seek | -0.030 |
gy | -0.028 |
Token | when |
Token ID | 618 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
zag | +0.034 |
oot | +0.031 |
seek | +0.029 |
uzz | +0.029 |
sometime | +0.028 |
Neg logit contributions | |
pans | -0.030 |
nam | -0.029 |
ding | -0.029 |
counters | -0.029 |
spec | -0.027 |
Token | her |
Token ID | 607 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
nam | +0.154 |
ding | +0.137 |
pans | +0.135 |
forward | +0.131 |
y | +0.128 |
Neg logit contributions | |
zag | -0.322 |
oot | -0.311 |
uzz | -0.295 |
seek | -0.289 |
ogo | -0.284 |
Token | little |
Token ID | 1310 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
zag | +0.021 |
oot | +0.017 |
uzz | +0.017 |
gy | +0.016 |
seek | +0.016 |
Neg logit contributions | |
nam | -0.033 |
sc | -0.033 |
ding | -0.033 |
forward | -0.032 |
counters | -0.032 |
Token | brother |
Token ID | 3956 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
nam | +0.200 |
ding | +0.199 |
counters | +0.196 |
pans | +0.196 |
sc | +0.196 |
Neg logit contributions | |
zag | -0.119 |
oot | -0.105 |
gy | -0.104 |
uzz | -0.097 |
sometime | -0.095 |
Token | came |
Token ID | 1625 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
zag | +0.112 |
oot | +0.104 |
uzz | +0.100 |
seek | +0.099 |
gy | +0.096 |
Neg logit contributions | |
nam | -0.102 |
pans | -0.101 |
ding | -0.100 |
counters | -0.098 |
forward | -0.096 |
Token | in |
Token ID | 287 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
forward | +0.106 |
pans | +0.087 |
nam | +0.086 |
ding | +0.081 |
deep | +0.080 |
Neg logit contributions | |
zag | -0.222 |
oot | -0.217 |
seek | -0.211 |
ogo | -0.202 |
uzz | -0.198 |
Token | . |
Token ID | 13 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
pans | +0.021 |
forward | +0.021 |
y | +0.020 |
ding | +0.020 |
counters | +0.020 |
Neg logit contributions | |
zag | -0.029 |
oot | -0.028 |
uzz | -0.026 |
seek | -0.026 |
ogo | -0.025 |
Token | |
Token ID | 220 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
zag | +0.035 |
uzz | +0.032 |
seek | +0.031 |
oot | +0.031 |
sometime | +0.030 |
Neg logit contributions | |
nam | -0.044 |
pans | -0.042 |
ding | -0.042 |
forward | -0.041 |
brightest | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
nam | +0.158 |
pans | +0.158 |
ding | +0.156 |
counters | +0.153 |
forward | +0.150 |
Neg logit contributions | |
zag | -0.171 |
oot | -0.160 |
uzz | -0.155 |
seek | -0.150 |
sometime | -0.145 |
Token |
|
Token ID | 198 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
zag | +0.025 |
oot | +0.024 |
uzz | +0.023 |
seek | +0.022 |
sometime | +0.021 |
Neg logit contributions | |
nam | -0.025 |
pans | -0.025 |
ding | -0.025 |
counters | -0.024 |
forward | -0.023 |
Token | " |
Token ID | 1 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
zag | +0.017 |
oot | +0.014 |
seek | +0.014 |
uzz | +0.014 |
sometime | +0.014 |
Neg logit contributions | |
nam | -0.030 |
spec | -0.029 |
ding | -0.028 |
pans | -0.028 |
brightest | -0.028 |
Token | found |
Token ID | 1043 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
zag | +0.038 |
oot | +0.036 |
uzz | +0.034 |
seek | +0.034 |
sometime | +0.032 |
Neg logit contributions | |
pans | -0.028 |
nam | -0.028 |
ding | -0.028 |
counters | -0.027 |
forward | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
zag | +0.070 |
uzz | +0.068 |
oot | +0.067 |
gy | +0.061 |
seek | +0.061 |
Neg logit contributions | |
ding | -0.108 |
nam | -0.108 |
pans | -0.106 |
counters | -0.105 |
forward | -0.101 |
Token | biggest |
Token ID | 4094 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
ding | +0.011 |
nam | +0.011 |
counters | +0.011 |
pans | +0.011 |
sc | +0.011 |
Neg logit contributions | |
zag | -0.017 |
gy | -0.016 |
uzz | -0.015 |
oot | -0.015 |
sometime | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
nam | +0.109 |
ding | +0.107 |
pans | +0.106 |
counters | +0.104 |
forward | +0.101 |
Neg logit contributions | |
zag | -0.121 |
oot | -0.113 |
uzz | -0.109 |
sometime | -0.105 |
gy | -0.105 |
Token | brightest |
Token ID | 33871 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
sometime | +0.036 |
zag | +0.036 |
now | +0.035 |
gy | +0.035 |
himself | +0.035 |
Neg logit contributions | |
ding | -0.023 |
counters | -0.023 |
forward | -0.022 |
slot | -0.021 |
channels | -0.021 |
Token | rad |
Token ID | 2511 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
nam | +0.106 |
ding | +0.106 |
pans | +0.103 |
counters | +0.102 |
forward | +0.099 |
Neg logit contributions | |
zag | -0.128 |
oot | -0.121 |
uzz | -0.118 |
sometime | -0.114 |
gy | -0.113 |
Token | ish |
Token ID | 680 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ding | +0.189 |
counters | +0.185 |
nam | +0.184 |
pans | +0.176 |
forward | +0.173 |
Neg logit contributions | |
zag | -0.160 |
oot | -0.152 |
gy | -0.146 |
uzz | -0.143 |
sometime | -0.138 |
Token | and |
Token ID | 290 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
zag | +0.136 |
oot | +0.127 |
uzz | +0.122 |
seek | +0.116 |
sometime | +0.114 |
Neg logit contributions | |
nam | -0.145 |
ding | -0.143 |
pans | -0.141 |
counters | -0.140 |
forward | -0.135 |
Token | he |
Token ID | 339 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
sometime | +0.011 |
zag | +0.011 |
oot | +0.010 |
now | +0.010 |
uzz | +0.010 |
Neg logit contributions | |
ding | -0.012 |
forward | -0.012 |
counters | -0.011 |
nam | -0.011 |
pans | -0.011 |
Token | hopped |
Token ID | 45230 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
nam | +0.040 |
pans | +0.040 |
ding | +0.040 |
counters | +0.039 |
forward | +0.038 |
Neg logit contributions | |
zag | -0.053 |
oot | -0.050 |
uzz | -0.049 |
seek | -0.047 |
sometime | -0.046 |
Token | back |
Token ID | 736 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
nam | +0.055 |
pans | +0.055 |
ding | +0.054 |
counters | +0.053 |
forward | +0.050 |
Neg logit contributions | |
zag | -0.096 |
oot | -0.091 |
uzz | -0.088 |
seek | -0.086 |
sometime | -0.084 |
Token | Today |
Token ID | 8888 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
nam | +0.097 |
counters | +0.095 |
pans | +0.091 |
ding | +0.090 |
y | +0.089 |
Neg logit contributions | |
zag | -0.132 |
uzz | -0.129 |
sometime | -0.126 |
oot | -0.125 |
seek | -0.123 |
Token | we |
Token ID | 356 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
zag | +0.174 |
oot | +0.155 |
sometime | +0.151 |
uzz | +0.148 |
seek | +0.144 |
Neg logit contributions | |
nam | -0.216 |
pans | -0.212 |
counters | -0.205 |
ding | -0.204 |
forward | -0.199 |
Token | 're |
Token ID | 821 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
nam | +0.024 |
pans | +0.024 |
ding | +0.024 |
counters | +0.024 |
forward | +0.023 |
Neg logit contributions | |
zag | -0.039 |
oot | -0.037 |
uzz | -0.036 |
seek | -0.035 |
sometime | -0.034 |
Token | going |
Token ID | 1016 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
sc | +0.102 |
counters | +0.095 |
pans | +0.094 |
nam | +0.093 |
ding | +0.092 |
Neg logit contributions | |
zag | -0.092 |
now | -0.090 |
uzz | -0.089 |
oot | -0.089 |
sometime | -0.088 |
Token | on |
Token ID | 319 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
forward | +0.193 |
pans | +0.180 |
ding | +0.174 |
ready | +0.169 |
y | +0.169 |
Neg logit contributions | |
zag | -0.245 |
uzz | -0.241 |
oot | -0.241 |
seek | -0.225 |
ogo | -0.215 |
Token | a |
Token ID | 257 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
oot | +0.037 |
zag | +0.036 |
uzz | +0.035 |
ogo | +0.033 |
ebra | +0.032 |
Neg logit contributions | |
y | -0.016 |
flour | -0.014 |
pans | -0.014 |
ready | -0.013 |
delicious | -0.013 |
Token | picnic |
Token ID | 35715 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
nam | +0.020 |
pans | +0.020 |
ding | +0.020 |
counters | +0.019 |
forward | +0.019 |
Neg logit contributions | |
zag | -0.018 |
oot | -0.017 |
uzz | -0.017 |
seek | -0.016 |
sometime | -0.015 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
zag | +0.135 |
oot | +0.128 |
uzz | +0.123 |
seek | +0.118 |
gy | +0.111 |
Neg logit contributions | |
pans | -0.147 |
nam | -0.145 |
ding | -0.145 |
counters | -0.142 |
forward | -0.141 |
Token | Maria |
Token ID | 14200 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
zag | +0.122 |
uzz | +0.112 |
oot | +0.110 |
sometime | +0.108 |
gy | +0.107 |
Neg logit contributions | |
nam | -0.129 |
forward | -0.121 |
pans | -0.119 |
ju | -0.119 |
ding | -0.118 |
Token | was |
Token ID | 373 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
y | +0.022 |
pans | +0.022 |
ding | +0.022 |
counters | +0.022 |
nam | +0.021 |
Neg logit contributions | |
zag | -0.039 |
oot | -0.038 |
seek | -0.036 |
uzz | -0.036 |
ogo | -0.035 |
Token | very |
Token ID | 845 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
zag | +0.034 |
uzz | +0.032 |
oot | +0.031 |
sometime | +0.030 |
seek | +0.030 |
Neg logit contributions | |
pans | -0.022 |
counters | -0.021 |
sc | -0.021 |
nam | -0.020 |
ding | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
nam | +0.011 |
pans | +0.011 |
ding | +0.011 |
counters | +0.011 |
forward | +0.010 |
Neg logit contributions | |
zag | -0.015 |
uzz | -0.014 |
oot | -0.014 |
seek | -0.014 |
sometime | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
pans | +0.011 |
ding | +0.011 |
counters | +0.011 |
nam | +0.011 |
y | +0.010 |
Neg logit contributions | |
zag | -0.019 |
oot | -0.018 |
seek | -0.018 |
uzz | -0.017 |
gy | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
pans | +0.015 |
ding | +0.015 |
nam | +0.015 |
counters | +0.014 |
forward | +0.014 |
Neg logit contributions | |
zag | -0.024 |
oot | -0.023 |
seek | -0.021 |
uzz | -0.021 |
gy | -0.021 |
Token | Maybe |
Token ID | 13300 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
zag | +0.016 |
oot | +0.015 |
uzz | +0.014 |
seek | +0.014 |
gy | +0.013 |
Neg logit contributions | |
pans | -0.008 |
nam | -0.008 |
ding | -0.008 |
counters | -0.008 |
forward | -0.007 |
Token | we |
Token ID | 356 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
nam | +0.025 |
pans | +0.025 |
ding | +0.025 |
counters | +0.025 |
forward | +0.024 |
Neg logit contributions | |
zag | -0.034 |
oot | -0.032 |
uzz | -0.031 |
seek | -0.030 |
sometime | -0.029 |
Token | should |
Token ID | 815 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
nam | +0.029 |
forward | +0.029 |
y | +0.028 |
pans | +0.028 |
ding | +0.028 |
Neg logit contributions | |
zag | -0.090 |
oot | -0.086 |
seek | -0.084 |
uzz | -0.083 |
ippy | -0.080 |
Token | have |
Token ID | 423 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
y | +0.013 |
nam | +0.012 |
ding | +0.012 |
pans | +0.012 |
counters | +0.012 |
Neg logit contributions | |
zag | -0.016 |
oot | -0.015 |
seek | -0.014 |
uzz | -0.014 |
ippy | -0.014 |
Token | played |
Token ID | 2826 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
zag | +0.238 |
oot | +0.224 |
uzz | +0.209 |
ippy | +0.199 |
seek | +0.198 |
Neg logit contributions | |
nam | -0.173 |
pans | -0.172 |
y | -0.171 |
ding | -0.164 |
counters | -0.160 |
Token | with |
Token ID | 351 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
zag | +0.188 |
oot | +0.181 |
uzz | +0.169 |
seek | +0.169 |
ogo | +0.166 |
Neg logit contributions | |
y | -0.099 |
ding | -0.096 |
pans | -0.095 |
forward | -0.095 |
nam | -0.092 |
Token | Frost |
Token ID | 15122 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
nam | +0.017 |
ding | +0.017 |
counters | +0.017 |
pans | +0.017 |
forward | +0.017 |
Neg logit contributions | |
zag | -0.018 |
uzz | -0.017 |
oot | -0.017 |
sometime | -0.016 |
seek | -0.015 |
Token | y |
Token ID | 88 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
oot | +0.061 |
seek | +0.060 |
zag | +0.059 |
uzz | +0.053 |
sometime | +0.052 |
Neg logit contributions | |
pans | -0.048 |
ding | -0.045 |
forward | -0.043 |
y | -0.043 |
nam | -0.043 |
Token | delicious |
Token ID | 12625 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
zag | +0.018 |
oot | +0.016 |
uzz | +0.016 |
sometime | +0.015 |
seek | +0.015 |
Neg logit contributions | |
nam | -0.013 |
pans | -0.013 |
ding | -0.013 |
counters | -0.013 |
forward | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
nam | +0.184 |
pans | +0.184 |
ding | +0.183 |
counters | +0.179 |
forward | +0.176 |
Neg logit contributions | |
zag | -0.162 |
oot | -0.150 |
uzz | -0.144 |
seek | -0.140 |
sometime | -0.134 |
Token | but |
Token ID | 475 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
zag | +0.013 |
oot | +0.012 |
uzz | +0.012 |
sometime | +0.012 |
seek | +0.011 |
Neg logit contributions | |
nam | -0.016 |
pans | -0.016 |
ding | -0.015 |
counters | -0.015 |
forward | -0.015 |
Token | because |
Token ID | 780 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
pans | +0.076 |
counters | +0.075 |
nam | +0.075 |
ding | +0.075 |
forward | +0.069 |
Neg logit contributions | |
zag | -0.080 |
oot | -0.074 |
uzz | -0.074 |
sometime | -0.070 |
seek | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
zag | +0.171 |
oot | +0.158 |
uzz | +0.155 |
seek | +0.148 |
sometime | +0.148 |
Neg logit contributions | |
nam | -0.143 |
ding | -0.143 |
pans | -0.143 |
counters | -0.141 |
forward | -0.134 |
Token | monster |
Token ID | 9234 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
nam | +0.036 |
pans | +0.036 |
ding | +0.035 |
counters | +0.035 |
forward | +0.034 |
Neg logit contributions | |
zag | -0.026 |
oot | -0.024 |
uzz | -0.023 |
seek | -0.022 |
sometime | -0.021 |
Token | wasn |
Token ID | 2492 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
zag | +0.129 |
oot | +0.123 |
uzz | +0.119 |
seek | +0.116 |
sometime | +0.110 |
Neg logit contributions | |
pans | -0.105 |
ding | -0.105 |
nam | -0.104 |
counters | -0.102 |
y | -0.100 |
Token | 't |
Token ID | 470 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
forward | +0.069 |
ding | +0.068 |
y | +0.065 |
nam | +0.065 |
pans | +0.064 |
Neg logit contributions | |
zag | -0.053 |
oot | -0.049 |
uzz | -0.048 |
seek | -0.048 |
gy | -0.045 |
Token | scary |
Token ID | 14343 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
zag | +0.289 |
oot | +0.274 |
uzz | +0.267 |
seek | +0.259 |
sometime | +0.253 |
Neg logit contributions | |
pans | -0.189 |
ding | -0.188 |
nam | -0.188 |
counters | -0.185 |
forward | -0.178 |
Token | after |
Token ID | 706 |
Feature activation | +6.65e-03 |
Pos logit contributions | |
zag | +0.026 |
oot | +0.024 |
uzz | +0.022 |
seek | +0.021 |
sometime | +0.020 |
Neg logit contributions | |
nam | -0.054 |
pans | -0.054 |
ding | -0.053 |
counters | -0.052 |
forward | -0.051 |
Token | all |
Token ID | 477 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
nam | +0.000 |
ding | +0.000 |
pans | +0.000 |
y | +0.000 |
forward | +0.000 |
Neg logit contributions | |
zag | -0.000 |
oot | -0.000 |
seek | -0.000 |
gy | -0.000 |
uzz | -0.000 |
Token | little |
Token ID | 1310 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
counters | +0.013 |
nam | +0.013 |
sc | +0.013 |
forward | +0.013 |
pans | +0.012 |
Neg logit contributions | |
zag | -0.022 |
oot | -0.020 |
uzz | -0.020 |
gy | -0.019 |
sometime | -0.019 |
Token | boy |
Token ID | 2933 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
counters | +0.135 |
nam | +0.134 |
ding | +0.128 |
forward | +0.127 |
pans | +0.126 |
Neg logit contributions | |
zag | -0.193 |
oot | -0.185 |
uzz | -0.180 |
gy | -0.175 |
ippy | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
nam | +0.025 |
pans | +0.025 |
ding | +0.025 |
counters | +0.024 |
forward | +0.024 |
Neg logit contributions | |
zag | -0.022 |
oot | -0.020 |
uzz | -0.019 |
seek | -0.019 |
sometime | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
zag | +0.050 |
oot | +0.047 |
uzz | +0.045 |
seek | +0.044 |
sometime | +0.043 |
Neg logit contributions | |
ding | -0.035 |
nam | -0.035 |
pans | -0.035 |
counters | -0.034 |
forward | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
zag | +0.049 |
oot | +0.047 |
uzz | +0.046 |
seek | +0.044 |
sometime | +0.043 |
Neg logit contributions | |
pans | -0.020 |
nam | -0.020 |
y | -0.020 |
ding | -0.020 |
counters | -0.019 |
Token | three |
Token ID | 1115 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
zag | +0.038 |
uzz | +0.037 |
gy | +0.036 |
oot | +0.035 |
seek | +0.033 |
Neg logit contributions | |
counters | -0.028 |
pans | -0.028 |
sc | -0.027 |
ding | -0.025 |
spec | -0.025 |
Token | years |
Token ID | 812 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
zag | +0.088 |
oot | +0.083 |
uzz | +0.081 |
seek | +0.076 |
sometime | +0.076 |
Neg logit contributions | |
ding | -0.084 |
nam | -0.084 |
pans | -0.081 |
forward | -0.081 |
counters | -0.079 |
Token | old |
Token ID | 1468 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
nam | +0.077 |
ding | +0.075 |
forward | +0.072 |
pans | +0.071 |
sc | +0.071 |
Neg logit contributions | |
zag | -0.115 |
oot | -0.113 |
uzz | -0.108 |
seek | -0.100 |
ippy | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
nam | +0.025 |
pans | +0.025 |
ding | +0.024 |
counters | +0.024 |
y | +0.024 |
Neg logit contributions | |
zag | -0.032 |
oot | -0.029 |
uzz | -0.028 |
seek | -0.027 |
ogo | -0.026 |
Token | had |
Token ID | 550 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
zag | +0.017 |
uzz | +0.016 |
gy | +0.016 |
oot | +0.016 |
seek | +0.015 |
Neg logit contributions | |
counters | -0.018 |
sc | -0.018 |
spec | -0.018 |
ding | -0.018 |
forward | -0.018 |
Token | lots |
Token ID | 6041 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
zag | +0.059 |
seek | +0.057 |
uzz | +0.055 |
sometime | +0.052 |
gy | +0.052 |
Neg logit contributions | |
forward | -0.092 |
pans | -0.092 |
sc | -0.092 |
ding | -0.092 |
counters | -0.090 |
Token | had |
Token ID | 550 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
pans | +0.046 |
nam | +0.044 |
ding | +0.044 |
y | +0.043 |
counters | +0.043 |
Neg logit contributions | |
zag | -0.074 |
oot | -0.071 |
uzz | -0.069 |
seek | -0.067 |
ippy | -0.063 |
Token | an |
Token ID | 281 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
zag | +0.119 |
oot | +0.113 |
uzz | +0.102 |
ebra | +0.102 |
ippy | +0.102 |
Neg logit contributions | |
y | -0.061 |
ju | -0.051 |
flour | -0.049 |
nam | -0.046 |
fres | -0.045 |
Token | idea |
Token ID | 2126 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
zag | +0.080 |
seek | +0.073 |
uzz | +0.073 |
oot | +0.072 |
gy | +0.069 |
Neg logit contributions | |
y | -0.041 |
forward | -0.039 |
ding | -0.039 |
pans | -0.039 |
nam | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
zag | +0.137 |
oot | +0.124 |
uzz | +0.123 |
seek | +0.120 |
gy | +0.119 |
Neg logit contributions | |
y | -0.088 |
forward | -0.088 |
pans | -0.087 |
nam | -0.084 |
ding | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
zag | +0.034 |
oot | +0.031 |
uzz | +0.030 |
seek | +0.030 |
sometime | +0.029 |
Neg logit contributions | |
nam | -0.030 |
ding | -0.030 |
pans | -0.030 |
counters | -0.029 |
forward | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
zag | +0.035 |
oot | +0.033 |
uzz | +0.032 |
seek | +0.032 |
gy | +0.031 |
Neg logit contributions | |
pans | -0.020 |
ding | -0.020 |
forward | -0.020 |
y | -0.019 |
counters | -0.019 |
Token | R |
Token ID | 49 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
zag | +0.027 |
oot | +0.026 |
uzz | +0.025 |
seek | +0.024 |
sometime | +0.023 |
Neg logit contributions | |
pans | -0.021 |
ding | -0.020 |
nam | -0.020 |
counters | -0.020 |
forward | -0.020 |
Token | emy |
Token ID | 3065 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
zag | +0.045 |
uzz | +0.042 |
oot | +0.040 |
seek | +0.040 |
sometime | +0.034 |
Neg logit contributions | |
pans | -0.095 |
y | -0.093 |
counters | -0.092 |
forward | -0.092 |
ding | -0.091 |
Token | went |
Token ID | 1816 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
zag | +0.225 |
oot | +0.216 |
uzz | +0.211 |
seek | +0.202 |
ippy | +0.195 |
Neg logit contributions | |
pans | -0.153 |
counters | -0.149 |
ding | -0.147 |
y | -0.145 |
nam | -0.143 |
Token | to |
Token ID | 284 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
forward | +0.080 |
pans | +0.078 |
counters | +0.074 |
ding | +0.073 |
y | +0.071 |
Neg logit contributions | |
zag | -0.105 |
oot | -0.103 |
uzz | -0.100 |
sometime | -0.095 |
seek | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
zag | +0.072 |
oot | +0.071 |
uzz | +0.066 |
seek | +0.065 |
sometime | +0.060 |
Neg logit contributions | |
pans | -0.049 |
y | -0.048 |
nam | -0.048 |
ding | -0.047 |
counters | -0.045 |
Token | brave |
Token ID | 14802 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
nam | +0.019 |
pans | +0.018 |
counters | +0.018 |
ding | +0.018 |
forward | +0.017 |
Neg logit contributions | |
zag | -0.020 |
oot | -0.018 |
seek | -0.018 |
uzz | -0.017 |
sometime | -0.017 |
Token | Princess |
Token ID | 8449 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
nam | +0.031 |
pans | +0.031 |
ding | +0.030 |
counters | +0.030 |
forward | +0.029 |
Neg logit contributions | |
zag | -0.043 |
oot | -0.041 |
uzz | -0.040 |
seek | -0.039 |
sometime | -0.037 |
Token | for |
Token ID | 329 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
nam | +0.074 |
ding | +0.073 |
pans | +0.073 |
forward | +0.073 |
counters | +0.071 |
Neg logit contributions | |
zag | -0.091 |
oot | -0.084 |
uzz | -0.082 |
seek | -0.080 |
sometime | -0.077 |
Token | protecting |
Token ID | 10192 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
zag | +0.076 |
oot | +0.070 |
uzz | +0.067 |
seek | +0.066 |
gy | +0.063 |
Neg logit contributions | |
nam | -0.066 |
ding | -0.064 |
pans | -0.063 |
forward | -0.062 |
counters | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
pans | +0.078 |
ding | +0.078 |
nam | +0.078 |
counters | +0.076 |
forward | +0.073 |
Neg logit contributions | |
zag | -0.076 |
oot | -0.072 |
uzz | -0.070 |
seek | -0.067 |
gy | -0.065 |
Token | castle |
Token ID | 16669 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
nam | +0.021 |
pans | +0.020 |
counters | +0.020 |
ding | +0.020 |
sc | +0.019 |
Neg logit contributions | |
zag | -0.015 |
seek | -0.013 |
oot | -0.013 |
sometime | -0.013 |
gy | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
zag | +0.153 |
oot | +0.138 |
seek | +0.128 |
uzz | +0.128 |
gy | +0.124 |
Neg logit contributions | |
pans | -0.186 |
nam | -0.186 |
ding | -0.182 |
counters | -0.179 |
spec | -0.175 |
Token | saving |
Token ID | 8914 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
zag | +0.011 |
oot | +0.010 |
uzz | +0.010 |
seek | +0.010 |
sometime | +0.009 |
Neg logit contributions | |
pans | -0.011 |
counters | -0.011 |
ding | -0.011 |
nam | -0.010 |
forward | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
pans | +0.099 |
ding | +0.097 |
counters | +0.097 |
nam | +0.095 |
ju | +0.093 |
Neg logit contributions | |
oot | -0.067 |
uzz | -0.067 |
zag | -0.065 |
gy | -0.062 |
sometime | -0.061 |
Token | day |
Token ID | 1110 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
pans | +0.018 |
nam | +0.018 |
counters | +0.018 |
ding | +0.017 |
sc | +0.016 |
Neg logit contributions | |
zag | -0.015 |
sometime | -0.013 |
seek | -0.013 |
oot | -0.013 |
gy | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
zag | +0.000 |
oot | +0.000 |
seek | +0.000 |
sometime | +0.000 |
uzz | +0.000 |
Neg logit contributions | |
pans | -0.001 |
nam | -0.001 |
counters | -0.001 |
ding | -0.001 |
spec | -0.001 |
Token | special |
Token ID | 2041 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
zag | +0.039 |
uzz | +0.037 |
oot | +0.037 |
sometime | +0.037 |
emo | +0.035 |
Neg logit contributions | |
counters | -0.030 |
ding | -0.030 |
nam | -0.029 |
pans | -0.028 |
sc | -0.028 |
Token | as |
Token ID | 355 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
zag | +0.019 |
oot | +0.017 |
uzz | +0.017 |
seek | +0.016 |
gy | +0.016 |
Neg logit contributions | |
pans | -0.017 |
nam | -0.017 |
ding | -0.017 |
forward | -0.017 |
counters | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
zag | +0.037 |
oot | +0.035 |
uzz | +0.034 |
sometime | +0.033 |
seek | +0.032 |
Neg logit contributions | |
ding | -0.038 |
nam | -0.038 |
counters | -0.037 |
pans | -0.037 |
forward | -0.035 |
Token | butter |
Token ID | 9215 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ding | +0.001 |
nam | +0.001 |
counters | +0.001 |
forward | +0.001 |
sc | +0.001 |
Neg logit contributions | |
zag | -0.001 |
sometime | -0.001 |
seek | -0.001 |
oot | -0.001 |
seek | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
pans | +0.118 |
nam | +0.117 |
ding | +0.117 |
counters | +0.114 |
forward | +0.112 |
Neg logit contributions | |
zag | -0.141 |
oot | -0.133 |
uzz | -0.129 |
seek | -0.126 |
sometime | -0.121 |
Token | found |
Token ID | 1043 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
pans | +0.031 |
nam | +0.031 |
ding | +0.031 |
counters | +0.030 |
forward | +0.029 |
Neg logit contributions | |
zag | -0.055 |
oot | -0.053 |
uzz | -0.051 |
seek | -0.050 |
sometime | -0.048 |
Token | when |
Token ID | 618 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
zag | +0.087 |
oot | +0.081 |
uzz | +0.078 |
sometime | +0.074 |
seek | +0.074 |
Neg logit contributions | |
nam | -0.115 |
pans | -0.115 |
ding | -0.114 |
counters | -0.111 |
forward | -0.104 |
Token | he |
Token ID | 339 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
nam | +0.193 |
pans | +0.192 |
ding | +0.191 |
counters | +0.186 |
forward | +0.184 |
Neg logit contributions | |
zag | -0.227 |
oot | -0.214 |
uzz | -0.207 |
seek | -0.200 |
gy | -0.192 |
Token | climbed |
Token ID | 19952 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
y | +0.031 |
ding | +0.030 |
forward | +0.029 |
pans | +0.029 |
counters | +0.029 |
Neg logit contributions | |
zag | -0.052 |
oot | -0.051 |
uzz | -0.050 |
seek | -0.046 |
ippy | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
zag | +0.014 |
oot | +0.013 |
uzz | +0.013 |
seek | +0.013 |
sometime | +0.012 |
Neg logit contributions | |
pans | -0.009 |
nam | -0.009 |
ding | -0.009 |
forward | -0.009 |
counters | -0.008 |
Token | wall |
Token ID | 3355 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
zag | +0.002 |
oot | +0.002 |
seek | +0.002 |
uzz | +0.002 |
sometime | +0.002 |
Neg logit contributions | |
nam | -0.002 |
pans | -0.002 |
ding | -0.002 |
counters | -0.002 |
forward | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
zag | +0.119 |
oot | +0.111 |
uzz | +0.107 |
seek | +0.104 |
sometime | +0.100 |
Neg logit contributions | |
nam | -0.113 |
pans | -0.113 |
ding | -0.112 |
counters | -0.109 |
forward | -0.107 |
Token | He |
Token ID | 679 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
zag | +0.012 |
uzz | +0.011 |
oot | +0.011 |
seek | +0.011 |
sometime | +0.011 |
Neg logit contributions | |
nam | -0.015 |
pans | -0.015 |
ding | -0.015 |
forward | -0.014 |
counters | -0.014 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
zag | +0.014 |
oot | +0.013 |
uzz | +0.013 |
seek | +0.012 |
gy | +0.012 |
Neg logit contributions | |
nam | -0.009 |
pans | -0.009 |
ding | -0.009 |
counters | -0.009 |
y | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
nam | +0.052 |
pans | +0.051 |
ding | +0.051 |
forward | +0.051 |
y | +0.050 |
Neg logit contributions | |
zag | -0.058 |
oot | -0.053 |
uzz | -0.052 |
seek | -0.050 |
gy | -0.049 |
Token | so |
Token ID | 523 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
forward | +0.006 |
y | +0.005 |
nam | +0.005 |
ding | +0.005 |
brightest | +0.005 |
Neg logit contributions | |
zag | -0.013 |
uzz | -0.012 |
oot | -0.012 |
seek | -0.012 |
gy | -0.012 |
Token | badly |
Token ID | 11234 |
Feature activation | -6.37e+00 |
Pos logit contributions | |
y | +0.035 |
nam | +0.034 |
forward | +0.033 |
ding | +0.033 |
de | +0.032 |
Neg logit contributions | |
zag | -0.047 |
oot | -0.043 |
seek | -0.042 |
uzz | -0.041 |
istle | -0.040 |
Token | ! |
Token ID | 0 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
zag | +0.413 |
uzz | +0.400 |
isk | +0.384 |
ogo | +0.374 |
oot | +0.374 |
Neg logit contributions | |
forward | -0.238 |
y | -0.225 |
de | -0.220 |
ready | -0.214 |
spec | -0.204 |
Token | |
Token ID | 220 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
zag | +0.064 |
oot | +0.060 |
uzz | +0.059 |
seek | +0.058 |
sometime | +0.057 |
Neg logit contributions | |
nam | -0.065 |
pans | -0.064 |
ding | -0.064 |
counters | -0.060 |
forward | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
nam | +0.162 |
pans | +0.161 |
ding | +0.161 |
counters | +0.158 |
forward | +0.155 |
Neg logit contributions | |
zag | -0.191 |
oot | -0.179 |
uzz | -0.173 |
seek | -0.169 |
sometime | -0.163 |
Token |
|
Token ID | 198 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
zag | +0.007 |
oot | +0.006 |
uzz | +0.006 |
seek | +0.006 |
sometime | +0.006 |
Neg logit contributions | |
nam | -0.007 |
pans | -0.007 |
ding | -0.007 |
counters | -0.007 |
spec | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
zag | +0.004 |
sometime | +0.004 |
oot | +0.004 |
uzz | +0.004 |
seek | +0.004 |
Neg logit contributions | |
nam | -0.006 |
spec | -0.006 |
ding | -0.006 |
de | -0.006 |
pans | -0.006 |
Token | wanted |
Token ID | 2227 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
pans | +0.084 |
ding | +0.084 |
counters | +0.082 |
nam | +0.082 |
forward | +0.081 |
Neg logit contributions | |
zag | -0.137 |
oot | -0.132 |
uzz | -0.129 |
seek | -0.125 |
sometime | -0.119 |
Token | to |
Token ID | 284 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
y | +0.039 |
pans | +0.038 |
nam | +0.038 |
flour | +0.038 |
counters | +0.035 |
Neg logit contributions | |
zag | -0.060 |
oot | -0.056 |
uzz | -0.052 |
ogo | -0.052 |
ippy | -0.052 |
Token | play |
Token ID | 711 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
zag | +0.073 |
oot | +0.071 |
uzz | +0.070 |
ogo | +0.067 |
seek | +0.065 |
Neg logit contributions | |
y | -0.045 |
counters | -0.042 |
pans | -0.041 |
nam | -0.041 |
ding | -0.041 |
Token | hide |
Token ID | 7808 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
zag | +0.319 |
uzz | +0.304 |
oot | +0.301 |
ogo | +0.300 |
ert | +0.290 |
Neg logit contributions | |
y | -0.151 |
forward | -0.127 |
soft | -0.121 |
low | -0.120 |
sc | -0.114 |
Token | and |
Token ID | 290 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
zag | +0.051 |
oot | +0.047 |
seek | +0.045 |
uzz | +0.044 |
ogo | +0.042 |
Neg logit contributions | |
pans | -0.041 |
nam | -0.039 |
forward | -0.039 |
y | -0.039 |
counters | -0.039 |
Token | seek |
Token ID | 5380 |
Feature activation | -7.46e+00 |
Pos logit contributions | |
ding | +0.001 |
forward | +0.001 |
counters | +0.001 |
pans | +0.001 |
nam | +0.001 |
Neg logit contributions | |
zag | -0.000 |
oot | -0.000 |
seek | -0.000 |
uzz | -0.000 |
sometime | -0.000 |
Token | with |
Token ID | 351 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
zag | +0.489 |
oot | +0.466 |
uzz | +0.438 |
ogo | +0.420 |
seek | +0.420 |
Neg logit contributions | |
nam | -0.306 |
forward | -0.298 |
y | -0.296 |
pans | -0.291 |
counters | -0.287 |
Token | the |
Token ID | 262 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
zag | +0.005 |
oot | +0.004 |
uzz | +0.004 |
seek | +0.004 |
sometime | +0.004 |
Neg logit contributions | |
pans | -0.005 |
ding | -0.005 |
nam | -0.005 |
counters | -0.005 |
forward | -0.004 |
Token | sun |
Token ID | 4252 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ding | +0.020 |
sc | +0.019 |
counters | +0.019 |
forward | +0.019 |
nam | +0.019 |
Neg logit contributions | |
zag | -0.019 |
fault | -0.016 |
oot | -0.016 |
uzz | -0.016 |
gy | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
nam | +0.202 |
ding | +0.200 |
pans | +0.200 |
counters | +0.196 |
forward | +0.190 |
Neg logit contributions | |
zag | -0.175 |
oot | -0.159 |
uzz | -0.153 |
seek | -0.147 |
gy | -0.146 |
Token | The |
Token ID | 383 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
zag | +0.023 |
oot | +0.021 |
seek | +0.021 |
uzz | +0.021 |
gy | +0.020 |
Neg logit contributions | |
nam | -0.022 |
pans | -0.022 |
forward | -0.021 |
ding | -0.021 |
counters | -0.021 |
Token | something |
Token ID | 1223 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
zag | +0.029 |
oot | +0.028 |
uzz | +0.027 |
ogo | +0.026 |
seek | +0.026 |
Neg logit contributions | |
y | -0.013 |
nam | -0.013 |
spec | -0.012 |
forward | -0.012 |
low | -0.012 |
Token | so |
Token ID | 523 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
pans | +0.047 |
nam | +0.047 |
ding | +0.047 |
counters | +0.046 |
forward | +0.042 |
Neg logit contributions | |
zag | -0.084 |
oot | -0.080 |
uzz | -0.076 |
sometime | -0.076 |
seek | -0.075 |
Token | hard |
Token ID | 1327 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
pans | +0.029 |
counters | +0.029 |
ding | +0.028 |
nam | +0.028 |
spec | +0.025 |
Neg logit contributions | |
zag | -0.039 |
oot | -0.038 |
uzz | -0.036 |
sometime | -0.035 |
seek | -0.034 |
Token | ! |
Token ID | 0 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
forward | +0.011 |
ding | +0.011 |
pans | +0.011 |
counters | +0.011 |
y | +0.011 |
Neg logit contributions | |
zag | -0.014 |
uzz | -0.014 |
oot | -0.013 |
seek | -0.013 |
ippy | -0.012 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
zag | +0.063 |
oot | +0.059 |
uzz | +0.057 |
seek | +0.056 |
sometime | +0.054 |
Neg logit contributions | |
nam | -0.044 |
pans | -0.044 |
ding | -0.043 |
counters | -0.042 |
forward | -0.041 |
Token | One |
Token ID | 3198 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
zag | +0.010 |
oot | +0.009 |
uzz | +0.009 |
seek | +0.009 |
sometime | +0.009 |
Neg logit contributions | |
pans | -0.008 |
ding | -0.007 |
nam | -0.007 |
counters | -0.007 |
forward | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
zag | +0.341 |
oot | +0.332 |
uzz | +0.319 |
seek | +0.315 |
gy | +0.304 |
Neg logit contributions | |
ding | -0.188 |
y | -0.184 |
pans | -0.183 |
forward | -0.182 |
nam | -0.180 |
Token | , |
Token ID | 11 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
zag | +0.004 |
oot | +0.004 |
uzz | +0.003 |
seek | +0.003 |
sometime | +0.003 |
Neg logit contributions | |
nam | -0.005 |
pans | -0.005 |
ding | -0.005 |
counters | -0.005 |
forward | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
zag | +0.027 |
oot | +0.025 |
uzz | +0.024 |
seek | +0.024 |
sometime | +0.023 |
Neg logit contributions | |
nam | -0.024 |
pans | -0.024 |
ding | -0.024 |
counters | -0.023 |
forward | -0.023 |
Token | little |
Token ID | 1310 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
counters | +0.022 |
nam | +0.021 |
sc | +0.019 |
forward | +0.019 |
pans | +0.019 |
Neg logit contributions | |
zag | -0.030 |
oot | -0.027 |
uzz | -0.026 |
gy | -0.026 |
ah | -0.026 |
Token | boy |
Token ID | 2933 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
counters | +0.152 |
nam | +0.149 |
pans | +0.142 |
ding | +0.139 |
forward | +0.133 |
Neg logit contributions | |
zag | -0.206 |
oot | -0.199 |
uzz | -0.191 |
gy | -0.188 |
ippy | -0.180 |
Token | he |
Token ID | 339 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
zag | +0.006 |
oot | +0.005 |
uzz | +0.005 |
sometime | +0.004 |
gy | +0.004 |
Neg logit contributions | |
counters | -0.016 |
pans | -0.016 |
nam | -0.016 |
ju | -0.015 |
ding | -0.015 |
Token | wanted |
Token ID | 2227 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
pans | +0.027 |
y | +0.026 |
nam | +0.025 |
ding | +0.025 |
sc | +0.025 |
Neg logit contributions | |
oot | -0.062 |
zag | -0.061 |
uzz | -0.059 |
seek | -0.057 |
ippy | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
nam | +0.030 |
pans | +0.030 |
ding | +0.029 |
y | +0.029 |
counters | +0.029 |
Neg logit contributions | |
zag | -0.036 |
oot | -0.034 |
uzz | -0.032 |
gy | -0.031 |
ippy | -0.030 |
Token | try |
Token ID | 1949 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
oot | +0.081 |
zag | +0.081 |
uzz | +0.080 |
ogo | +0.074 |
gy | +0.072 |
Neg logit contributions | |
y | -0.056 |
nam | -0.054 |
pans | -0.053 |
ding | -0.053 |
counters | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
zag | +0.032 |
oot | +0.032 |
uzz | +0.032 |
seek | +0.030 |
gy | +0.030 |
Neg logit contributions | |
nam | -0.019 |
pans | -0.019 |
ding | -0.019 |
y | -0.018 |
forward | -0.018 |
Token | win |
Token ID | 1592 |
Feature activation | -7.22e+00 |
Pos logit contributions | |
zag | +0.076 |
oot | +0.076 |
uzz | +0.075 |
gy | +0.068 |
ogo | +0.068 |
Neg logit contributions | |
nam | -0.062 |
y | -0.060 |
ding | -0.060 |
pans | -0.059 |
counters | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
zag | +0.466 |
oot | +0.445 |
uzz | +0.430 |
gy | +0.413 |
ippy | +0.412 |
Neg logit contributions | |
nam | -0.315 |
forward | -0.292 |
y | -0.286 |
pans | -0.284 |
ding | -0.280 |
Token | He |
Token ID | 679 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
zag | +0.046 |
oot | +0.043 |
uzz | +0.042 |
seek | +0.041 |
sometime | +0.039 |
Neg logit contributions | |
pans | -0.047 |
nam | -0.047 |
ding | -0.046 |
counters | -0.045 |
forward | -0.044 |
Token | kept |
Token ID | 4030 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
oot | +0.053 |
zag | +0.051 |
uzz | +0.049 |
seek | +0.048 |
ogo | +0.047 |
Neg logit contributions | |
y | -0.021 |
pans | -0.020 |
nam | -0.020 |
sc | -0.019 |
forward | -0.018 |
Token | trying |
Token ID | 2111 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
zag | +0.049 |
oot | +0.046 |
uzz | +0.045 |
seek | +0.043 |
gy | +0.042 |
Neg logit contributions | |
nam | -0.040 |
ding | -0.040 |
pans | -0.039 |
forward | -0.039 |
counters | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
nam | +0.043 |
ding | +0.043 |
pans | +0.042 |
forward | +0.042 |
counters | +0.041 |
Neg logit contributions | |
zag | -0.047 |
oot | -0.044 |
uzz | -0.043 |
seek | -0.041 |
gy | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
pans | +0.107 |
nam | +0.107 |
ding | +0.106 |
counters | +0.105 |
forward | +0.102 |
Neg logit contributions | |
zag | -0.122 |
oot | -0.114 |
uzz | -0.110 |
seek | -0.107 |
sometime | -0.103 |
Token | bridge |
Token ID | 7696 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
pans | +0.040 |
nam | +0.040 |
ding | +0.040 |
counters | +0.039 |
forward | +0.038 |
Neg logit contributions | |
zag | -0.039 |
oot | -0.036 |
uzz | -0.035 |
seek | -0.034 |
sometime | -0.033 |
Token | shakes |
Token ID | 29959 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
zag | +0.088 |
oot | +0.082 |
uzz | +0.079 |
seek | +0.077 |
sometime | +0.074 |
Neg logit contributions | |
nam | -0.073 |
pans | -0.072 |
ding | -0.070 |
counters | -0.070 |
forward | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
zag | +0.012 |
oot | +0.011 |
uzz | +0.011 |
seek | +0.010 |
sometime | +0.010 |
Neg logit contributions | |
nam | -0.015 |
pans | -0.015 |
ding | -0.014 |
counters | -0.014 |
forward | -0.014 |
Token | Sara |
Token ID | 24799 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
nam | +0.036 |
pans | +0.036 |
ding | +0.035 |
counters | +0.035 |
forward | +0.033 |
Neg logit contributions | |
zag | -0.041 |
oot | -0.039 |
uzz | -0.039 |
seek | -0.037 |
sometime | -0.036 |
Token | loses |
Token ID | 14754 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
zag | +0.050 |
oot | +0.047 |
uzz | +0.046 |
seek | +0.045 |
sometime | +0.043 |
Neg logit contributions | |
pans | -0.034 |
nam | -0.034 |
ding | -0.034 |
counters | -0.033 |
forward | -0.032 |
Token | her |
Token ID | 607 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
zag | +0.359 |
oot | +0.327 |
seek | +0.311 |
sometime | +0.299 |
ogo | +0.297 |
Neg logit contributions | |
pans | -0.196 |
nam | -0.195 |
ding | -0.190 |
counters | -0.185 |
spec | -0.182 |
Token | balance |
Token ID | 5236 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
nam | +0.015 |
ding | +0.015 |
pans | +0.014 |
forward | +0.014 |
y | +0.014 |
Neg logit contributions | |
zag | -0.010 |
oot | -0.009 |
uzz | -0.009 |
seek | -0.009 |
sometime | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
zag | +0.097 |
oot | +0.090 |
uzz | +0.085 |
seek | +0.081 |
sometime | +0.079 |
Neg logit contributions | |
nam | -0.121 |
pans | -0.120 |
ding | -0.118 |
counters | -0.117 |
ju | -0.112 |
Token | drops |
Token ID | 10532 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
nam | +0.046 |
pans | +0.046 |
counters | +0.046 |
ding | +0.043 |
ju | +0.043 |
Neg logit contributions | |
zag | -0.048 |
oot | -0.044 |
uzz | -0.042 |
seek | -0.041 |
sometime | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
nam | +0.082 |
counters | +0.080 |
pans | +0.080 |
ding | +0.077 |
brightest | +0.075 |
Neg logit contributions | |
uzz | -0.063 |
zag | -0.063 |
oot | -0.062 |
seek | -0.055 |
ippy | -0.053 |