Token | " |
Token ID | 366 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
loe | +0.001 |
ocolate | +0.001 |
ird | +0.001 |
' | +0.001 |
tted | +0.001 |
Neg logit contributions | |
blurry | -0.002 |
nam | -0.002 |
wil | -0.002 |
prett | -0.002 |
cks | -0.002 |
Token | We |
Token ID | 1135 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
blurry | +0.010 |
nam | +0.009 |
wil | +0.008 |
ateful | +0.008 |
lands | +0.008 |
Neg logit contributions | |
ocolate | -0.009 |
loe | -0.009 |
' | -0.008 |
ird | -0.008 |
tted | -0.008 |
Token | are |
Token ID | 389 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ocolate | +0.002 |
loe | +0.002 |
' | +0.002 |
ird | +0.002 |
uster | +0.002 |
Neg logit contributions | |
blurry | -0.003 |
nam | -0.002 |
wil | -0.002 |
ateful | -0.002 |
lands | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
blurry | +0.048 |
nam | +0.045 |
wil | +0.042 |
ateful | +0.041 |
lands | +0.041 |
Neg logit contributions | |
ocolate | -0.045 |
loe | -0.045 |
' | -0.043 |
ird | -0.042 |
tted | -0.041 |
Token | weapon |
Token ID | 4282 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
blurry | +0.012 |
nam | +0.011 |
wil | +0.010 |
cks | +0.010 |
ateful | +0.010 |
Neg logit contributions | |
ocolate | -0.008 |
loe | -0.008 |
' | -0.007 |
ird | -0.007 |
uster | -0.007 |
Token | creators |
Token ID | 16294 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
blurry | +0.189 |
lands | +0.167 |
nam | +0.166 |
wil | +0.163 |
prett | +0.160 |
Neg logit contributions | |
ocolate | -0.140 |
loe | -0.139 |
ird | -0.123 |
uster | -0.121 |
' | -0.119 |
Token | ! |
Token ID | 0 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
ocolate | +0.282 |
loe | +0.275 |
uster | +0.257 |
ird | +0.254 |
tted | +0.251 |
Neg logit contributions | |
blurry | -0.372 |
lands | -0.331 |
nam | -0.331 |
cks | -0.327 |
wil | -0.326 |
Token | We |
Token ID | 775 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ocolate | +0.003 |
loe | +0.003 |
ird | +0.003 |
' | +0.003 |
uster | +0.002 |
Neg logit contributions | |
blurry | -0.003 |
nam | -0.002 |
lands | -0.002 |
flashes | -0.002 |
cks | -0.002 |
Token | can |
Token ID | 460 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
blurry | +0.090 |
nam | +0.082 |
wil | +0.078 |
prett | +0.076 |
lands | +0.076 |
Neg logit contributions | |
ocolate | -0.084 |
loe | -0.083 |
' | -0.076 |
ird | -0.075 |
uster | -0.074 |
Token | stop |
Token ID | 2245 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
blurry | +0.045 |
nam | +0.043 |
wil | +0.040 |
ateful | +0.039 |
prett | +0.038 |
Neg logit contributions | |
ocolate | -0.038 |
loe | -0.038 |
' | -0.037 |
ird | -0.035 |
tted | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
blurry | +0.022 |
nam | +0.021 |
wil | +0.020 |
ateful | +0.019 |
prett | +0.019 |
Neg logit contributions | |
' | -0.018 |
ocolate | -0.016 |
loe | -0.015 |
of | -0.015 |
oning | -0.015 |
Token | by |
Token ID | 416 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
ocolate | +0.025 |
uster | +0.023 |
loe | +0.022 |
tted | +0.022 |
ird | +0.022 |
Neg logit contributions | |
blurry | -0.017 |
nam | -0.016 |
lands | -0.015 |
cks | -0.015 |
wil | -0.014 |
Token | one |
Token ID | 530 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
ocolate | +0.038 |
loe | +0.038 |
' | +0.036 |
ird | +0.034 |
of | +0.033 |
Neg logit contributions | |
blurry | -0.038 |
nam | -0.035 |
prett | -0.032 |
wil | -0.031 |
ateful | -0.031 |
Token | � |
Token ID | 6184 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
' | +0.022 |
ocolate | +0.022 |
loe | +0.022 |
of | +0.021 |
ird | +0.020 |
Neg logit contributions | |
blurry | -0.040 |
nam | -0.039 |
ateful | -0.036 |
wil | -0.036 |
cks | -0.036 |
Token | � |
Token ID | 95 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
blurry | +0.050 |
nam | +0.047 |
wil | +0.044 |
ateful | +0.044 |
lands | +0.043 |
Neg logit contributions | |
ocolate | -0.039 |
loe | -0.037 |
' | -0.036 |
ird | -0.036 |
tted | -0.034 |
Token | € |
Token ID | 26391 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
blurry | +0.125 |
nam | +0.115 |
lands | +0.112 |
ateful | +0.111 |
prett | +0.111 |
Neg logit contributions | |
ocolate | -0.087 |
loe | -0.080 |
' | -0.076 |
ird | -0.076 |
uster | -0.074 |
Token | � |
Token ID | 447 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
ocolate | +0.089 |
loe | +0.083 |
' | +0.078 |
uster | +0.078 |
ird | +0.076 |
Neg logit contributions | |
blurry | -0.130 |
nam | -0.124 |
lands | -0.118 |
wil | -0.116 |
cks | -0.116 |
Token | � |
Token ID | 250 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
ocolate | +0.163 |
loe | +0.159 |
' | +0.156 |
ird | +0.147 |
tted | +0.133 |
Neg logit contributions | |
blurry | -0.494 |
nam | -0.465 |
wil | -0.448 |
ateful | -0.437 |
cks | -0.436 |
Token | 1 |
Token ID | 352 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
blurry | +0.057 |
nam | +0.053 |
wil | +0.049 |
lands | +0.048 |
ateful | +0.048 |
Neg logit contributions | |
ocolate | -0.057 |
loe | -0.056 |
' | -0.054 |
ird | -0.053 |
tted | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
ocolate | +0.024 |
loe | +0.024 |
uster | +0.022 |
tted | +0.022 |
oning | +0.021 |
Neg logit contributions | |
blurry | -0.035 |
nam | -0.034 |
lands | -0.034 |
cks | -0.033 |
ateful | -0.032 |
Token | 2 |
Token ID | 362 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ocolate | +0.018 |
loe | +0.018 |
tted | +0.016 |
ird | +0.015 |
' | +0.015 |
Neg logit contributions | |
blurry | -0.028 |
nam | -0.027 |
prett | -0.026 |
lands | -0.025 |
ateful | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
blurry | +0.042 |
nam | +0.041 |
lands | +0.040 |
cks | +0.039 |
prett | +0.038 |
Neg logit contributions | |
ocolate | -0.027 |
loe | -0.026 |
tted | -0.025 |
uster | -0.024 |
oning | -0.022 |
Token | perfect |
Token ID | 2818 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
ocolate | +0.103 |
loe | +0.101 |
' | +0.097 |
ird | +0.095 |
tted | +0.089 |
Neg logit contributions | |
blurry | -0.130 |
nam | -0.121 |
wil | -0.113 |
ateful | -0.112 |
cks | -0.111 |
Token | bag |
Token ID | 6131 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ocolate | +0.036 |
loe | +0.035 |
' | +0.033 |
ird | +0.033 |
tted | +0.032 |
Neg logit contributions | |
blurry | -0.047 |
nam | -0.044 |
wil | -0.042 |
lands | -0.041 |
prett | -0.041 |
Token | � |
Token ID | 6184 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
loe | +0.066 |
ocolate | +0.065 |
uster | +0.058 |
oning | +0.056 |
ird | +0.056 |
Neg logit contributions | |
blurry | -0.070 |
nam | -0.066 |
wil | -0.062 |
prett | -0.062 |
lands | -0.061 |
Token | � |
Token ID | 95 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
nam | +0.064 |
blurry | +0.063 |
lands | +0.062 |
prett | +0.061 |
rings | +0.058 |
Neg logit contributions | |
ocolate | -0.046 |
loe | -0.042 |
other | -0.040 |
adult | -0.039 |
umbs | -0.038 |
Token | € |
Token ID | 26391 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
blurry | +0.135 |
lands | +0.125 |
prett | +0.124 |
nam | +0.124 |
ateful | +0.119 |
Neg logit contributions | |
ocolate | -0.093 |
loe | -0.082 |
adult | -0.076 |
umbs | -0.075 |
uster | -0.074 |
Token | � |
Token ID | 447 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
ocolate | +0.085 |
loe | +0.078 |
uster | +0.072 |
adult | +0.071 |
' | +0.071 |
Neg logit contributions | |
blurry | -0.122 |
nam | -0.116 |
lands | -0.112 |
wil | -0.110 |
cks | -0.109 |
Token | � |
Token ID | 250 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
ocolate | +0.228 |
loe | +0.223 |
' | +0.215 |
ird | +0.208 |
tted | +0.198 |
Neg logit contributions | |
blurry | -0.393 |
nam | -0.370 |
wil | -0.349 |
ateful | -0.344 |
lands | -0.341 |
Token | now |
Token ID | 783 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
blurry | +0.059 |
nam | +0.056 |
wil | +0.051 |
ateful | +0.050 |
prett | +0.050 |
Neg logit contributions | |
ocolate | -0.065 |
loe | -0.064 |
' | -0.061 |
ird | -0.060 |
tted | -0.058 |
Token | I |
Token ID | 314 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
ocolate | +0.036 |
loe | +0.035 |
' | +0.033 |
ird | +0.032 |
tted | +0.032 |
Neg logit contributions | |
blurry | -0.043 |
nam | -0.041 |
wil | -0.037 |
lands | -0.037 |
prett | -0.037 |
Token | 'm |
Token ID | 1101 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
blurry | +0.002 |
nam | +0.001 |
lands | +0.001 |
wil | +0.001 |
prett | +0.001 |
Neg logit contributions | |
ocolate | -0.002 |
loe | -0.001 |
uster | -0.001 |
kids | -0.001 |
' | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ocolate | +0.031 |
loe | +0.030 |
' | +0.029 |
tted | +0.028 |
ay | +0.028 |
Neg logit contributions | |
blurry | -0.031 |
nam | -0.029 |
wil | -0.027 |
prett | -0.027 |
lands | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
blurry | +0.052 |
nam | +0.048 |
wil | +0.044 |
lands | +0.043 |
ateful | +0.043 |
Neg logit contributions | |
ocolate | -0.052 |
loe | -0.052 |
' | -0.049 |
ird | -0.049 |
tted | -0.047 |
Token | rocked |
Token ID | 36872 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
' | +0.018 |
ird | +0.017 |
days | +0.016 |
of | +0.016 |
hours | +0.016 |
Neg logit contributions | |
ateful | -0.026 |
blurry | -0.025 |
cks | -0.022 |
ric | -0.022 |
nam | -0.022 |
Token | � |
Token ID | 6184 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
blurry | +0.062 |
nam | +0.058 |
prett | +0.052 |
lands | +0.052 |
wil | +0.051 |
Neg logit contributions | |
ocolate | -0.054 |
loe | -0.054 |
ird | -0.051 |
' | -0.049 |
tted | -0.047 |
Token | � |
Token ID | 95 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
blurry | +0.064 |
nam | +0.061 |
cks | +0.059 |
lands | +0.058 |
wil | +0.058 |
Neg logit contributions | |
ocolate | -0.030 |
loe | -0.030 |
' | -0.027 |
ird | -0.027 |
other | -0.027 |
Token | € |
Token ID | 26391 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
blurry | +0.141 |
cks | +0.132 |
nam | +0.128 |
lands | +0.126 |
prett | +0.125 |
Neg logit contributions | |
ocolate | -0.112 |
loe | -0.107 |
of | -0.104 |
ird | -0.101 |
uster | -0.099 |
Token | � |
Token ID | 447 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
ocolate | +0.086 |
loe | +0.081 |
' | +0.074 |
uster | +0.073 |
ird | +0.073 |
Neg logit contributions | |
blurry | -0.117 |
nam | -0.110 |
cks | -0.106 |
lands | -0.105 |
wil | -0.104 |
Token | � |
Token ID | 250 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
ocolate | +0.140 |
loe | +0.134 |
' | +0.133 |
ird | +0.122 |
tted | +0.113 |
Neg logit contributions | |
blurry | -0.478 |
nam | -0.451 |
wil | -0.433 |
ateful | -0.428 |
lands | -0.423 |
Token | higher |
Token ID | 2440 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
blurry | +0.061 |
nam | +0.058 |
wil | +0.053 |
ateful | +0.052 |
lands | +0.052 |
Neg logit contributions | |
ocolate | -0.061 |
loe | -0.060 |
' | -0.058 |
ird | -0.057 |
tted | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
blurry | +0.082 |
nam | +0.078 |
wil | +0.074 |
ateful | +0.073 |
lands | +0.072 |
Neg logit contributions | |
ocolate | -0.040 |
loe | -0.039 |
' | -0.037 |
ird | -0.035 |
tted | -0.033 |
Token | higher |
Token ID | 2440 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
' | +0.021 |
ird | +0.020 |
of | +0.020 |
ocolate | +0.020 |
tted | +0.019 |
Neg logit contributions | |
blurry | -0.022 |
nam | -0.021 |
ateful | -0.020 |
wil | -0.019 |
cks | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
blurry | +0.083 |
nam | +0.079 |
wil | +0.075 |
ateful | +0.074 |
prett | +0.072 |
Neg logit contributions | |
ocolate | -0.038 |
loe | -0.037 |
' | -0.036 |
ird | -0.034 |
tted | -0.031 |
Token | rare |
Token ID | 4071 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
ocolate | +0.043 |
loe | +0.042 |
' | +0.040 |
ird | +0.039 |
tted | +0.038 |
Neg logit contributions | |
blurry | -0.046 |
nam | -0.043 |
wil | -0.040 |
ateful | -0.039 |
lands | -0.039 |
Token | silence |
Token ID | 9550 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
ocolate | +0.045 |
loe | +0.044 |
' | +0.043 |
ird | +0.042 |
tted | +0.040 |
Neg logit contributions | |
blurry | -0.051 |
nam | -0.048 |
ateful | -0.044 |
wil | -0.044 |
cks | -0.044 |
Token | � |
Token ID | 6184 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
ocolate | +0.018 |
loe | +0.018 |
' | +0.018 |
ird | +0.017 |
tted | +0.016 |
Neg logit contributions | |
blurry | -0.030 |
nam | -0.028 |
wil | -0.026 |
ateful | -0.026 |
cks | -0.026 |
Token | � |
Token ID | 95 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
blurry | +0.063 |
nam | +0.059 |
wil | +0.057 |
lands | +0.057 |
ateful | +0.056 |
Neg logit contributions | |
ocolate | -0.042 |
loe | -0.039 |
ird | -0.037 |
' | -0.037 |
uster | -0.035 |
Token | € |
Token ID | 26391 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
blurry | +0.141 |
nam | +0.128 |
wil | +0.125 |
lands | +0.124 |
ateful | +0.123 |
Neg logit contributions | |
ocolate | -0.097 |
loe | -0.092 |
ird | -0.086 |
' | -0.086 |
uster | -0.083 |
Token | � |
Token ID | 447 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
ocolate | +0.083 |
loe | +0.077 |
' | +0.072 |
ird | +0.071 |
uster | +0.070 |
Neg logit contributions | |
blurry | -0.118 |
nam | -0.111 |
wil | -0.106 |
lands | -0.106 |
cks | -0.104 |
Token | � |
Token ID | 250 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ocolate | +0.186 |
loe | +0.181 |
' | +0.179 |
ird | +0.169 |
tted | +0.159 |
Neg logit contributions | |
blurry | -0.427 |
nam | -0.405 |
wil | -0.383 |
ateful | -0.378 |
cks | -0.375 |
Token | that |
Token ID | 326 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
blurry | +0.069 |
nam | +0.064 |
wil | +0.060 |
lands | +0.058 |
cks | +0.058 |
Neg logit contributions | |
ocolate | -0.066 |
loe | -0.064 |
' | -0.063 |
ird | -0.061 |
tted | -0.060 |
Token | added |
Token ID | 2087 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
blurry | +0.071 |
nam | +0.068 |
ateful | +0.063 |
cks | +0.063 |
wil | +0.063 |
Neg logit contributions | |
' | -0.038 |
loe | -0.036 |
ocolate | -0.036 |
ird | -0.033 |
of | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
blurry | +0.025 |
nam | +0.023 |
wil | +0.021 |
lands | +0.021 |
ateful | +0.021 |
Neg logit contributions | |
ocolate | -0.025 |
loe | -0.024 |
' | -0.023 |
ird | -0.023 |
tted | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
blurry | +0.016 |
nam | +0.015 |
wil | +0.014 |
ateful | +0.013 |
cks | +0.013 |
Neg logit contributions | |
ocolate | -0.014 |
loe | -0.014 |
' | -0.014 |
ird | -0.013 |
tted | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
blurry | +0.019 |
nam | +0.017 |
wil | +0.016 |
ateful | +0.016 |
cks | +0.016 |
Neg logit contributions | |
ocolate | -0.020 |
loe | -0.020 |
' | -0.019 |
ird | -0.019 |
uster | -0.018 |
Token | forever |
Token ID | 8097 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ocolate | +0.046 |
loe | +0.045 |
' | +0.042 |
ird | +0.042 |
tted | +0.040 |
Neg logit contributions | |
blurry | -0.054 |
nam | -0.051 |
wil | -0.047 |
prett | -0.046 |
lands | -0.046 |
Token | � |
Token ID | 6184 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
blurry | +0.010 |
nam | +0.009 |
wil | +0.009 |
ateful | +0.008 |
lands | +0.008 |
Neg logit contributions | |
ocolate | -0.007 |
loe | -0.006 |
' | -0.006 |
ird | -0.006 |
tted | -0.006 |
Token | � |
Token ID | 95 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
nam | +0.048 |
blurry | +0.048 |
ateful | +0.045 |
wil | +0.044 |
prett | +0.044 |
Neg logit contributions | |
ocolate | -0.032 |
loe | -0.031 |
kids | -0.029 |
umbs | -0.029 |
other | -0.029 |
Token | € |
Token ID | 26391 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
blurry | +0.127 |
nam | +0.115 |
prett | +0.114 |
ateful | +0.112 |
lands | +0.110 |
Neg logit contributions | |
ocolate | -0.101 |
loe | -0.095 |
umbs | -0.087 |
of | -0.087 |
ay | -0.086 |
Token | � |
Token ID | 447 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
ocolate | +0.077 |
loe | +0.074 |
' | +0.069 |
ird | +0.068 |
tted | +0.066 |
Neg logit contributions | |
blurry | -0.120 |
nam | -0.113 |
wil | -0.107 |
lands | -0.106 |
cks | -0.105 |
Token | � |
Token ID | 250 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
ocolate | +0.218 |
loe | +0.213 |
' | +0.212 |
ird | +0.204 |
tted | +0.193 |
Neg logit contributions | |
blurry | -0.396 |
nam | -0.369 |
wil | -0.351 |
cks | -0.345 |
ateful | -0.344 |
Token | things |
Token ID | 1243 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
blurry | +0.061 |
nam | +0.056 |
wil | +0.052 |
lands | +0.051 |
ateful | +0.051 |
Neg logit contributions | |
ocolate | -0.062 |
loe | -0.061 |
' | -0.059 |
ird | -0.058 |
tted | -0.056 |
Token | are |
Token ID | 389 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
blurry | +0.085 |
nam | +0.080 |
wil | +0.074 |
ateful | +0.074 |
cks | +0.073 |
Neg logit contributions | |
ocolate | -0.067 |
loe | -0.066 |
' | -0.065 |
ird | -0.063 |
tted | -0.060 |
Token | only |
Token ID | 691 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
blurry | +0.035 |
nam | +0.032 |
wil | +0.030 |
prett | +0.030 |
lands | +0.029 |
Neg logit contributions | |
ocolate | -0.037 |
loe | -0.037 |
ird | -0.034 |
' | -0.034 |
tted | -0.033 |
Token | available |
Token ID | 1695 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
blurry | +0.059 |
nam | +0.056 |
wil | +0.052 |
ateful | +0.051 |
lands | +0.050 |
Neg logit contributions | |
ocolate | -0.051 |
loe | -0.050 |
' | -0.048 |
ird | -0.047 |
tted | -0.045 |
Token | anxious |
Token ID | 18116 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
ocolate | +0.078 |
loe | +0.077 |
' | +0.075 |
ird | +0.074 |
tted | +0.071 |
Neg logit contributions | |
blurry | -0.056 |
nam | -0.052 |
wil | -0.047 |
lands | -0.046 |
cks | -0.046 |
Token | anymore |
Token ID | 7471 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ocolate | +0.015 |
loe | +0.015 |
' | +0.014 |
ird | +0.014 |
tted | +0.013 |
Neg logit contributions | |
blurry | -0.014 |
nam | -0.013 |
wil | -0.012 |
ateful | -0.012 |
lands | -0.012 |
Token | � |
Token ID | 6184 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
blurry | +0.082 |
nam | +0.077 |
wil | +0.072 |
ateful | +0.070 |
lands | +0.070 |
Neg logit contributions | |
ocolate | -0.068 |
loe | -0.067 |
' | -0.062 |
ird | -0.062 |
tted | -0.061 |
Token | � |
Token ID | 95 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
blurry | +0.067 |
nam | +0.063 |
wil | +0.059 |
ateful | +0.059 |
lands | +0.058 |
Neg logit contributions | |
ocolate | -0.041 |
loe | -0.041 |
' | -0.038 |
ird | -0.037 |
tted | -0.036 |
Token | € |
Token ID | 26391 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
blurry | +0.147 |
nam | +0.134 |
ateful | +0.128 |
lands | +0.126 |
prett | +0.126 |
Neg logit contributions | |
ocolate | -0.116 |
loe | -0.112 |
ird | -0.104 |
' | -0.102 |
uster | -0.101 |
Token | � |
Token ID | 447 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
ocolate | +0.082 |
loe | +0.080 |
' | +0.076 |
ird | +0.075 |
tted | +0.072 |
Neg logit contributions | |
blurry | -0.115 |
nam | -0.109 |
wil | -0.102 |
ateful | -0.100 |
lands | -0.100 |
Token | � |
Token ID | 251 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ocolate | +0.106 |
' | +0.100 |
loe | +0.099 |
ird | +0.089 |
tted | +0.080 |
Neg logit contributions | |
blurry | -0.506 |
nam | -0.480 |
wil | -0.462 |
ateful | -0.455 |
lands | -0.452 |
Token | he |
Token ID | 339 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
blurry | +0.151 |
nam | +0.142 |
wil | +0.134 |
ateful | +0.132 |
lands | +0.131 |
Neg logit contributions | |
ocolate | -0.094 |
loe | -0.093 |
' | -0.088 |
ird | -0.086 |
tted | -0.082 |
Token | knew |
Token ID | 2993 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
blurry | +0.035 |
nam | +0.033 |
cks | +0.031 |
ateful | +0.031 |
wil | +0.030 |
Neg logit contributions | |
loe | -0.033 |
ocolate | -0.032 |
' | -0.032 |
ird | -0.032 |
tted | -0.030 |
Token | he |
Token ID | 339 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
ocolate | +0.031 |
loe | +0.030 |
' | +0.029 |
ird | +0.028 |
tted | +0.028 |
Neg logit contributions | |
blurry | -0.022 |
nam | -0.020 |
wil | -0.018 |
ateful | -0.017 |
prett | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
blurry | +0.037 |
nam | +0.034 |
wil | +0.032 |
lands | +0.031 |
ateful | +0.031 |
Neg logit contributions | |
ocolate | -0.036 |
loe | -0.035 |
' | -0.033 |
ird | -0.033 |
tted | -0.031 |
Token | special |
Token ID | 2041 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
ocolate | +0.021 |
loe | +0.021 |
' | +0.020 |
ird | +0.020 |
tted | +0.019 |
Neg logit contributions | |
blurry | -0.025 |
nam | -0.023 |
wil | -0.022 |
ateful | -0.021 |
lands | -0.021 |
Token | home |
Token ID | 1363 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
loe | +0.016 |
ocolate | +0.016 |
' | +0.015 |
ird | +0.015 |
tted | +0.014 |
Neg logit contributions | |
blurry | -0.018 |
nam | -0.017 |
wil | -0.016 |
prett | -0.016 |
lands | -0.016 |
Token | � |
Token ID | 6184 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
loe | +0.175 |
ocolate | +0.174 |
tted | +0.159 |
ird | +0.159 |
uster | +0.158 |
Neg logit contributions | |
blurry | -0.153 |
nam | -0.145 |
wil | -0.129 |
prett | -0.127 |
lands | -0.125 |
Token | � |
Token ID | 95 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
blurry | +0.068 |
nam | +0.064 |
wil | +0.062 |
lands | +0.061 |
prett | +0.060 |
Neg logit contributions | |
ocolate | -0.033 |
loe | -0.032 |
other | -0.030 |
kids | -0.029 |
ird | -0.029 |
Token | € |
Token ID | 26391 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
blurry | +0.142 |
nam | +0.130 |
wil | +0.123 |
prett | +0.122 |
lands | +0.122 |
Neg logit contributions | |
ocolate | -0.113 |
loe | -0.109 |
ird | -0.100 |
' | -0.100 |
uster | -0.100 |
Token | � |
Token ID | 447 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ocolate | +0.079 |
loe | +0.076 |
' | +0.070 |
ird | +0.069 |
tted | +0.067 |
Neg logit contributions | |
blurry | -0.124 |
nam | -0.117 |
wil | -0.110 |
lands | -0.108 |
ateful | -0.108 |
Token | � |
Token ID | 250 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ocolate | +0.134 |
loe | +0.128 |
' | +0.124 |
ird | +0.114 |
tted | +0.106 |
Neg logit contributions | |
blurry | -0.473 |
nam | -0.451 |
wil | -0.429 |
ateful | -0.425 |
lands | -0.422 |
Token | a |
Token ID | 257 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
blurry | +0.061 |
nam | +0.057 |
wil | +0.052 |
ateful | +0.051 |
prett | +0.051 |
Neg logit contributions | |
ocolate | -0.075 |
loe | -0.075 |
' | -0.071 |
ird | -0.070 |
uster | -0.067 |
Token | hut |
Token ID | 40812 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
ocolate | +0.040 |
loe | +0.040 |
' | +0.037 |
tted | +0.036 |
ird | +0.036 |
Neg logit contributions | |
blurry | -0.040 |
nam | -0.037 |
prett | -0.035 |
wil | -0.034 |
lands | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
loe | +0.048 |
ocolate | +0.047 |
uster | +0.042 |
ird | +0.042 |
tted | +0.041 |
Neg logit contributions | |
blurry | -0.063 |
nam | -0.058 |
wil | -0.056 |
prett | -0.056 |
lands | -0.056 |
Token | She |
Token ID | 1375 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
ocolate | +0.009 |
affle | +0.009 |
ve | +0.009 |
kids | +0.009 |
iest | +0.009 |
Neg logit contributions | |
nam | -0.009 |
rings | -0.008 |
Mars | -0.008 |
blurry | -0.008 |
prett | -0.008 |
Token | those |
Token ID | 883 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
ocolate | +0.003 |
loe | +0.003 |
ird | +0.003 |
' | +0.003 |
uster | +0.003 |
Neg logit contributions | |
blurry | -0.004 |
nam | -0.004 |
ateful | -0.003 |
lands | -0.003 |
wil | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
blurry | +0.032 |
nam | +0.030 |
wil | +0.028 |
ateful | +0.027 |
lands | +0.027 |
Neg logit contributions | |
ocolate | -0.027 |
loe | -0.026 |
' | -0.025 |
ird | -0.025 |
tted | -0.024 |
Token | need |
Token ID | 761 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
ocolate | +0.002 |
loe | +0.002 |
' | +0.002 |
ird | +0.002 |
tted | +0.002 |
Neg logit contributions | |
blurry | -0.002 |
nam | -0.002 |
wil | -0.002 |
ateful | -0.002 |
lands | -0.002 |
Token | â |
Token ID | 22940 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ocolate | +0.026 |
loe | +0.026 |
tted | +0.025 |
ird | +0.024 |
uster | +0.024 |
Neg logit contributions | |
blurry | -0.021 |
nam | -0.020 |
lands | -0.018 |
wil | -0.018 |
prett | -0.017 |
Token | € |
Token ID | 26391 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ocolate | +0.018 |
ay | +0.018 |
uster | +0.018 |
loe | +0.018 |
ird | +0.017 |
Neg logit contributions | |
blurry | -0.021 |
ateful | -0.020 |
cks | -0.019 |
nam | -0.019 |
wil | -0.019 |
Token | � |
Token ID | 447 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ocolate | +0.078 |
loe | +0.071 |
uster | +0.065 |
tted | +0.063 |
' | +0.063 |
Neg logit contributions | |
blurry | -0.126 |
nam | -0.122 |
wil | -0.116 |
lands | -0.115 |
cks | -0.113 |
Token | � |
Token ID | 251 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ocolate | +0.244 |
loe | +0.243 |
' | +0.239 |
ird | +0.230 |
tted | +0.220 |
Neg logit contributions | |
blurry | -0.361 |
nam | -0.338 |
wil | -0.316 |
cks | -0.312 |
ateful | -0.312 |
Token | even |
Token ID | 10197 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
blurry | +0.134 |
nam | +0.129 |
wil | +0.119 |
ateful | +0.117 |
lands | +0.117 |
Neg logit contributions | |
ocolate | -0.099 |
loe | -0.094 |
tted | -0.088 |
' | -0.087 |
ird | -0.087 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
loe | +0.034 |
' | +0.033 |
ird | +0.033 |
ocolate | +0.032 |
of | +0.031 |
Neg logit contributions | |
blurry | -0.043 |
nam | -0.039 |
wil | -0.038 |
cks | -0.038 |
lands | -0.036 |
Token | One |
Token ID | 3198 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
blurry | +0.102 |
lands | +0.094 |
nam | +0.092 |
cks | +0.089 |
wil | +0.089 |
Neg logit contributions | |
ocolate | -0.117 |
loe | -0.111 |
ird | -0.108 |
uster | -0.107 |
' | -0.103 |
Token | day |
Token ID | 1110 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
blurry | +0.021 |
nam | +0.020 |
cks | +0.019 |
wil | +0.019 |
ateful | +0.019 |
Neg logit contributions | |
ocolate | -0.009 |
loe | -0.009 |
' | -0.009 |
ird | -0.008 |
of | -0.008 |
Token | didn |
Token ID | 1422 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
loe | +0.021 |
ocolate | +0.020 |
' | +0.020 |
ird | +0.020 |
tted | +0.019 |
Neg logit contributions | |
blurry | -0.023 |
nam | -0.021 |
ateful | -0.019 |
cks | -0.019 |
wil | -0.019 |
Token | 't |
Token ID | 470 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
ocolate | +0.024 |
ird | +0.023 |
loe | +0.023 |
kids | +0.022 |
uster | +0.022 |
Neg logit contributions | |
blurry | -0.055 |
nam | -0.050 |
lands | -0.049 |
wil | -0.048 |
cks | -0.048 |
Token | know |
Token ID | 760 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
ocolate | +0.045 |
' | +0.044 |
ird | +0.044 |
loe | +0.043 |
tted | +0.040 |
Neg logit contributions | |
blurry | -0.077 |
nam | -0.074 |
wil | -0.070 |
cks | -0.070 |
ateful | -0.068 |
Token | what |
Token ID | 644 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
blurry | +0.016 |
nam | +0.015 |
wil | +0.014 |
ateful | +0.013 |
lands | +0.013 |
Neg logit contributions | |
ocolate | -0.024 |
loe | -0.024 |
' | -0.023 |
ird | -0.023 |
uster | -0.022 |
Token | " |
Token ID | 366 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
blurry | +0.012 |
nam | +0.011 |
wil | +0.010 |
lands | +0.010 |
ateful | +0.010 |
Neg logit contributions | |
ocolate | -0.013 |
loe | -0.012 |
' | -0.012 |
ird | -0.012 |
tted | -0.011 |
Token | nos |
Token ID | 39369 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
blurry | +0.007 |
nam | +0.006 |
wil | +0.006 |
cks | +0.006 |
ateful | +0.006 |
Neg logit contributions | |
ocolate | -0.007 |
' | -0.007 |
loe | -0.007 |
ird | -0.007 |
tted | -0.006 |
Token | y |
Token ID | 88 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ocolate | +0.375 |
loe | +0.367 |
' | +0.355 |
ird | +0.353 |
tted | +0.347 |
Neg logit contributions | |
blurry | -0.220 |
nam | -0.195 |
ateful | -0.181 |
wil | -0.179 |
lands | -0.173 |
Token | " |
Token ID | 1 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
blurry | +0.095 |
lands | +0.094 |
wil | +0.091 |
flies | +0.090 |
ateful | +0.090 |
Neg logit contributions | |
loe | -0.062 |
ocolate | -0.060 |
tted | -0.056 |
uster | -0.055 |
ird | -0.053 |
Token | meant |
Token ID | 4001 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
blurry | +0.016 |
nam | +0.015 |
wil | +0.014 |
cks | +0.013 |
ateful | +0.013 |
Neg logit contributions | |
ocolate | -0.014 |
loe | -0.013 |
' | -0.013 |
ird | -0.013 |
tted | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
tted | +0.023 |
loe | +0.022 |
ocolate | +0.022 |
affle | +0.021 |
uster | +0.021 |
Neg logit contributions | |
blurry | -0.022 |
nam | -0.020 |
flashes | -0.017 |
wil | -0.017 |
rings | -0.017 |
Token | so |
Token ID | 523 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ocolate | +0.008 |
loe | +0.008 |
' | +0.008 |
ird | +0.008 |
tted | +0.007 |
Neg logit contributions | |
blurry | -0.014 |
nam | -0.013 |
wil | -0.012 |
ateful | -0.012 |
lands | -0.012 |
Token | something |
Token ID | 1223 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
blurry | +0.069 |
nam | +0.063 |
cks | +0.062 |
ateful | +0.060 |
wil | +0.059 |
Neg logit contributions | |
ocolate | -0.066 |
' | -0.065 |
loe | -0.063 |
ird | -0.061 |
of | -0.061 |
Token | was |
Token ID | 373 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
nam | +0.027 |
blurry | +0.027 |
ateful | +0.026 |
cks | +0.026 |
ric | +0.024 |
Neg logit contributions | |
' | -0.026 |
of | -0.025 |
ocolate | -0.023 |
loe | -0.023 |
ird | -0.023 |
Token | wrong |
Token ID | 2642 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
ocolate | +0.047 |
' | +0.046 |
loe | +0.045 |
of | +0.044 |
ird | +0.042 |
Neg logit contributions | |
nam | -0.049 |
blurry | -0.049 |
ateful | -0.045 |
lands | -0.044 |
cks | -0.044 |
Token | â |
Token ID | 22940 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
blurry | +0.068 |
nam | +0.065 |
wil | +0.060 |
ateful | +0.059 |
prett | +0.059 |
Neg logit contributions | |
ocolate | -0.048 |
loe | -0.047 |
' | -0.045 |
ird | -0.044 |
tted | -0.042 |
Token | € |
Token ID | 26391 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ocolate | +0.011 |
loe | +0.010 |
ird | +0.010 |
uster | +0.010 |
ay | +0.010 |
Neg logit contributions | |
blurry | -0.013 |
nam | -0.012 |
wil | -0.012 |
cks | -0.012 |
ateful | -0.011 |
Token | � |
Token ID | 447 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
ocolate | +0.081 |
loe | +0.079 |
' | +0.074 |
ird | +0.073 |
uster | +0.070 |
Neg logit contributions | |
blurry | -0.110 |
nam | -0.103 |
wil | -0.098 |
lands | -0.095 |
ateful | -0.095 |
Token | � |
Token ID | 251 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
ocolate | +0.076 |
loe | +0.072 |
' | +0.066 |
ird | +0.057 |
tted | +0.049 |
Neg logit contributions | |
blurry | -0.526 |
nam | -0.506 |
wil | -0.483 |
ateful | -0.479 |
lands | -0.475 |
Token | all |
Token ID | 439 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
blurry | +0.146 |
nam | +0.140 |
wil | +0.130 |
lands | +0.128 |
ateful | +0.127 |
Neg logit contributions | |
ocolate | -0.109 |
loe | -0.104 |
ird | -0.097 |
' | -0.097 |
tted | -0.097 |
Token | the |
Token ID | 262 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
ocolate | +0.093 |
loe | +0.089 |
ird | +0.084 |
' | +0.084 |
tted | +0.082 |
Neg logit contributions | |
blurry | -0.089 |
nam | -0.083 |
wil | -0.077 |
ateful | -0.075 |
lands | -0.075 |
Token | water |
Token ID | 1660 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
ocolate | +0.005 |
loe | +0.005 |
' | +0.005 |
ird | +0.004 |
tted | +0.004 |
Neg logit contributions | |
blurry | -0.006 |
nam | -0.006 |
wil | -0.005 |
ateful | -0.005 |
lands | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
blurry | +0.031 |
nam | +0.030 |
ateful | +0.027 |
cks | +0.026 |
wil | +0.026 |
Neg logit contributions | |
ocolate | -0.030 |
loe | -0.030 |
' | -0.030 |
ird | -0.028 |
tted | -0.028 |
Token | looked |
Token ID | 3114 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
nam | +0.009 |
blurry | +0.009 |
ateful | +0.008 |
cks | +0.008 |
prett | +0.008 |
Neg logit contributions | |
' | -0.008 |
loe | -0.008 |
ocolate | -0.008 |
ird | -0.007 |
tted | -0.007 |
Token | lovely |
Token ID | 14081 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
nam | +0.005 |
blurry | +0.005 |
ateful | +0.004 |
cks | +0.004 |
lands | +0.004 |
Neg logit contributions | |
' | -0.004 |
ocolate | -0.004 |
of | -0.004 |
loe | -0.004 |
tted | -0.004 |
Token | � |
Token ID | 6184 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
blurry | +0.005 |
nam | +0.005 |
wil | +0.005 |
prett | +0.005 |
lands | +0.005 |
Neg logit contributions | |
ocolate | -0.003 |
loe | -0.003 |
ird | -0.003 |
' | -0.003 |
tted | -0.003 |
Token | � |
Token ID | 95 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
blurry | +0.057 |
nam | +0.051 |
prett | +0.050 |
wil | +0.050 |
lands | +0.050 |
Neg logit contributions | |
ocolate | -0.035 |
loe | -0.033 |
adult | -0.032 |
other | -0.032 |
kids | -0.032 |
Token | € |
Token ID | 26391 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
blurry | +0.135 |
prett | +0.119 |
lands | +0.119 |
nam | +0.119 |
cks | +0.117 |
Neg logit contributions | |
ocolate | -0.103 |
loe | -0.095 |
uster | -0.092 |
of | -0.091 |
adult | -0.091 |
Token | � |
Token ID | 447 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ocolate | +0.084 |
loe | +0.080 |
' | +0.075 |
ird | +0.074 |
uster | +0.072 |
Neg logit contributions | |
blurry | -0.119 |
nam | -0.111 |
wil | -0.105 |
lands | -0.105 |
cks | -0.104 |
Token | � |
Token ID | 250 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ocolate | +0.107 |
loe | +0.101 |
' | +0.093 |
ird | +0.086 |
tted | +0.077 |
Neg logit contributions | |
blurry | -0.494 |
nam | -0.473 |
wil | -0.451 |
ateful | -0.447 |
lands | -0.444 |
Token | it |
Token ID | 340 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
blurry | +0.064 |
nam | +0.060 |
wil | +0.055 |
ateful | +0.054 |
lands | +0.054 |
Neg logit contributions | |
ocolate | -0.066 |
loe | -0.064 |
' | -0.062 |
ird | -0.061 |
tted | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
ocolate | +0.047 |
loe | +0.046 |
' | +0.043 |
ird | +0.043 |
tted | +0.041 |
Neg logit contributions | |
blurry | -0.060 |
nam | -0.056 |
wil | -0.053 |
lands | -0.052 |
ateful | -0.052 |
Token | bright |
Token ID | 6016 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
ocolate | +0.040 |
loe | +0.040 |
' | +0.038 |
ird | +0.037 |
tted | +0.036 |
Neg logit contributions | |
blurry | -0.044 |
nam | -0.041 |
wil | -0.038 |
lands | -0.037 |
prett | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
blurry | +0.007 |
nam | +0.006 |
wil | +0.006 |
prett | +0.006 |
lands | +0.006 |
Neg logit contributions | |
ocolate | -0.005 |
loe | -0.005 |
ird | -0.004 |
tted | -0.004 |
' | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
' | +0.023 |
ird | +0.022 |
loe | +0.022 |
of | +0.022 |
ocolate | +0.022 |
Neg logit contributions | |
blurry | -0.023 |
nam | -0.021 |
ateful | -0.020 |
cks | -0.020 |
wil | -0.020 |
Token | peace |
Token ID | 4167 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
blurry | +0.021 |
nam | +0.020 |
ateful | +0.019 |
wil | +0.018 |
cks | +0.018 |
Neg logit contributions | |
ocolate | -0.018 |
loe | -0.018 |
' | -0.018 |
ird | -0.018 |
tted | -0.017 |
Token | � |
Token ID | 6184 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
' | +0.018 |
loe | +0.018 |
ocolate | +0.018 |
ird | +0.017 |
tted | +0.016 |
Neg logit contributions | |
blurry | -0.026 |
nam | -0.026 |
ateful | -0.023 |
cks | -0.023 |
wil | -0.022 |
Token | � |
Token ID | 95 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
blurry | +0.061 |
nam | +0.058 |
ateful | +0.055 |
wil | +0.054 |
prett | +0.054 |
Neg logit contributions | |
ocolate | -0.040 |
loe | -0.037 |
' | -0.036 |
ird | -0.035 |
ay | -0.034 |
Token | € |
Token ID | 26391 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
blurry | +0.143 |
nam | +0.131 |
prett | +0.126 |
ateful | +0.125 |
lands | +0.125 |
Neg logit contributions | |
ocolate | -0.105 |
loe | -0.095 |
' | -0.090 |
ird | -0.089 |
uster | -0.088 |
Token | � |
Token ID | 447 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ocolate | +0.081 |
loe | +0.076 |
' | +0.071 |
ird | +0.069 |
uster | +0.068 |
Neg logit contributions | |
blurry | -0.128 |
nam | -0.121 |
wil | -0.115 |
lands | -0.113 |
cks | -0.112 |
Token | � |
Token ID | 250 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
ocolate | +0.231 |
' | +0.228 |
loe | +0.227 |
ird | +0.218 |
tted | +0.207 |
Neg logit contributions | |
blurry | -0.375 |
nam | -0.350 |
wil | -0.330 |
ateful | -0.325 |
cks | -0.324 |
Token | she |
Token ID | 673 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
blurry | +0.063 |
nam | +0.058 |
wil | +0.054 |
lands | +0.053 |
cks | +0.053 |
Neg logit contributions | |
ocolate | -0.062 |
loe | -0.061 |
' | -0.059 |
ird | -0.058 |
tted | -0.056 |
Token | just |
Token ID | 655 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
blurry | +0.033 |
nam | +0.031 |
wil | +0.029 |
ateful | +0.028 |
lands | +0.028 |
Neg logit contributions | |
ocolate | -0.027 |
loe | -0.027 |
' | -0.026 |
ird | -0.025 |
tted | -0.024 |
Token | needs |
Token ID | 2476 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
ocolate | +0.022 |
loe | +0.022 |
' | +0.021 |
ird | +0.021 |
tted | +0.020 |
Neg logit contributions | |
blurry | -0.029 |
nam | -0.027 |
wil | -0.025 |
ateful | -0.025 |
lands | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
blurry | +0.006 |
nam | +0.005 |
lands | +0.005 |
wil | +0.005 |
prett | +0.005 |
Neg logit contributions | |
ocolate | -0.007 |
loe | -0.007 |
tted | -0.006 |
ird | -0.006 |
' | -0.006 |
Token | t |
Token ID | 83 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
blurry | +0.131 |
nam | +0.127 |
wil | +0.119 |
rings | +0.117 |
ety | +0.115 |
Neg logit contributions | |
ocolate | -0.054 |
loe | -0.051 |
basis | -0.048 |
adult | -0.047 |
affle | -0.045 |
Token | help |
Token ID | 1037 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
blurry | +0.017 |
nam | +0.015 |
wil | +0.014 |
lands | +0.013 |
ateful | +0.013 |
Neg logit contributions | |
ocolate | -0.018 |
loe | -0.018 |
ay | -0.016 |
' | -0.016 |
ird | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
ocolate | +0.103 |
tted | +0.099 |
loe | +0.098 |
umbs | +0.091 |
ird | +0.091 |
Neg logit contributions | |
blurry | -0.113 |
nam | -0.106 |
lands | -0.097 |
cks | -0.096 |
ateful | -0.093 |
Token | â |
Token ID | 22940 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
ocolate | +0.042 |
loe | +0.041 |
ird | +0.038 |
uster | +0.037 |
' | +0.036 |
Neg logit contributions | |
blurry | -0.053 |
nam | -0.048 |
lands | -0.046 |
wil | -0.045 |
cks | -0.045 |
Token | € |
Token ID | 26391 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ocolate | +0.004 |
loe | +0.004 |
of | +0.004 |
ird | +0.004 |
uster | +0.004 |
Neg logit contributions | |
blurry | -0.004 |
nam | -0.004 |
cks | -0.004 |
ateful | -0.003 |
lands | -0.003 |
Token | � |
Token ID | 447 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
ocolate | +0.086 |
loe | +0.083 |
uster | +0.076 |
adult | +0.075 |
' | +0.074 |
Neg logit contributions | |
blurry | -0.107 |
nam | -0.102 |
cks | -0.096 |
lands | -0.095 |
wil | -0.095 |
Token | � |
Token ID | 251 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
ocolate | +0.098 |
loe | +0.093 |
' | +0.076 |
ird | +0.075 |
uster | +0.067 |
Neg logit contributions | |
blurry | -0.489 |
nam | -0.471 |
wil | -0.449 |
lands | -0.444 |
ateful | -0.444 |
Token | he |
Token ID | 258 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
blurry | +0.137 |
nam | +0.134 |
lands | +0.124 |
wil | +0.122 |
prett | +0.120 |
Neg logit contributions | |
ocolate | -0.112 |
loe | -0.107 |
tted | -0.099 |
ird | -0.098 |
' | -0.096 |
Token | reached |
Token ID | 4251 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ocolate | +0.039 |
loe | +0.037 |
tted | +0.036 |
uster | +0.036 |
ird | +0.036 |
Neg logit contributions | |
blurry | -0.036 |
nam | -0.034 |
wil | -0.032 |
ateful | -0.031 |
lands | -0.031 |
Token | out |
Token ID | 503 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
blurry | +0.017 |
nam | +0.015 |
lands | +0.014 |
wil | +0.014 |
prett | +0.014 |
Neg logit contributions | |
ocolate | -0.020 |
loe | -0.019 |
ird | -0.018 |
' | -0.018 |
tted | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ocolate | +0.003 |
loe | +0.003 |
ird | +0.003 |
' | +0.003 |
tted | +0.003 |
Neg logit contributions | |
blurry | -0.002 |
nam | -0.002 |
wil | -0.002 |
lands | -0.002 |
flashes | -0.002 |
Token | important |
Token ID | 1593 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ocolate | +0.025 |
loe | +0.025 |
' | +0.024 |
ird | +0.023 |
tted | +0.022 |
Neg logit contributions | |
blurry | -0.031 |
nam | -0.029 |
wil | -0.027 |
ateful | -0.027 |
lands | -0.027 |
Token | thing |
Token ID | 1517 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
ocolate | +0.088 |
loe | +0.086 |
' | +0.081 |
ird | +0.080 |
tted | +0.078 |
Neg logit contributions | |
blurry | -0.117 |
nam | -0.108 |
lands | -0.103 |
wil | -0.103 |
ateful | -0.101 |
Token | � |
Token ID | 6184 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
blurry | +0.030 |
nam | +0.028 |
wil | +0.025 |
ateful | +0.025 |
cks | +0.025 |
Neg logit contributions | |
ocolate | -0.031 |
loe | -0.030 |
' | -0.030 |
ird | -0.029 |
tted | -0.027 |
Token | � |
Token ID | 95 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
blurry | +0.067 |
nam | +0.062 |
wil | +0.061 |
ateful | +0.060 |
cks | +0.059 |
Neg logit contributions | |
ocolate | -0.025 |
loe | -0.025 |
ird | -0.023 |
other | -0.023 |
uster | -0.022 |
Token | € |
Token ID | 26391 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
blurry | +0.136 |
prett | +0.119 |
lands | +0.119 |
nam | +0.118 |
wil | +0.118 |
Neg logit contributions | |
ocolate | -0.105 |
loe | -0.100 |
uster | -0.095 |
ird | -0.095 |
of | -0.093 |
Token | � |
Token ID | 447 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
ocolate | +0.087 |
loe | +0.083 |
' | +0.076 |
uster | +0.076 |
ird | +0.076 |
Neg logit contributions | |
blurry | -0.113 |
nam | -0.106 |
wil | -0.101 |
lands | -0.100 |
cks | -0.099 |
Token | � |
Token ID | 250 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ocolate | +0.174 |
loe | +0.168 |
' | +0.163 |
ird | +0.154 |
tted | +0.145 |
Neg logit contributions | |
blurry | -0.424 |
nam | -0.404 |
wil | -0.381 |
ateful | -0.376 |
lands | -0.373 |
Token | his |
Token ID | 465 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
blurry | +0.069 |
nam | +0.064 |
wil | +0.059 |
lands | +0.058 |
cks | +0.058 |
Neg logit contributions | |
ocolate | -0.069 |
loe | -0.067 |
' | -0.065 |
ird | -0.064 |
tted | -0.063 |
Token | leash |
Token ID | 40529 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
blurry | +0.031 |
nam | +0.029 |
wil | +0.027 |
ateful | +0.026 |
lands | +0.026 |
Neg logit contributions | |
ocolate | -0.027 |
loe | -0.027 |
' | -0.025 |
ird | -0.025 |
tted | -0.024 |
Token | ! |
Token ID | 0 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ocolate | +0.064 |
loe | +0.063 |
ird | +0.059 |
' | +0.058 |
uster | +0.056 |
Neg logit contributions | |
blurry | -0.077 |
nam | -0.071 |
wil | -0.068 |
lands | -0.067 |
prett | -0.066 |
Token | She |
Token ID | 1375 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
nam | +0.007 |
blurry | +0.007 |
rings | +0.007 |
ateful | +0.007 |
Mars | +0.007 |
Neg logit contributions | |
ocolate | -0.005 |
ve | -0.005 |
loe | -0.005 |
kids | -0.005 |
' | -0.005 |
Token | also |
Token ID | 635 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
blurry | +0.003 |
nam | +0.003 |
wil | +0.002 |
ateful | +0.002 |
lands | +0.002 |
Neg logit contributions | |
ocolate | -0.003 |
loe | -0.003 |
' | -0.002 |
ird | -0.002 |
tted | -0.002 |
Token | very |
Token ID | 845 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
blurry | +0.079 |
nam | +0.073 |
lands | +0.067 |
ateful | +0.067 |
wil | +0.067 |
Neg logit contributions | |
ocolate | -0.073 |
' | -0.072 |
loe | -0.071 |
ird | -0.070 |
tted | -0.067 |
Token | persistent |
Token ID | 16218 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
' | +0.010 |
ocolate | +0.010 |
ird | +0.009 |
loe | +0.009 |
of | +0.009 |
Neg logit contributions | |
blurry | -0.011 |
nam | -0.010 |
cks | -0.010 |
lands | -0.010 |
flashes | -0.010 |
Token | â |
Token ID | 22940 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ocolate | +0.036 |
loe | +0.035 |
ird | +0.033 |
' | +0.033 |
tted | +0.033 |
Neg logit contributions | |
blurry | -0.037 |
nam | -0.034 |
wil | -0.032 |
lands | -0.031 |
ateful | -0.031 |
Token | € |
Token ID | 26391 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ocolate | +0.012 |
loe | +0.011 |
ird | +0.011 |
ay | +0.011 |
uster | +0.011 |
Neg logit contributions | |
blurry | -0.014 |
nam | -0.013 |
ateful | -0.012 |
wil | -0.012 |
cks | -0.012 |
Token | � |
Token ID | 447 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
ocolate | +0.085 |
loe | +0.080 |
' | +0.074 |
ird | +0.073 |
uster | +0.072 |
Neg logit contributions | |
blurry | -0.109 |
nam | -0.103 |
wil | -0.097 |
lands | -0.095 |
cks | -0.095 |
Token | � |
Token ID | 251 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ocolate | +0.065 |
loe | +0.061 |
' | +0.059 |
ird | +0.049 |
tted | +0.041 |
Neg logit contributions | |
blurry | -0.527 |
nam | -0.502 |
wil | -0.482 |
ateful | -0.478 |
lands | -0.476 |
Token | so |
Token ID | 568 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
blurry | +0.145 |
nam | +0.139 |
wil | +0.129 |
ateful | +0.127 |
lands | +0.127 |
Neg logit contributions | |
ocolate | -0.102 |
loe | -0.099 |
' | -0.092 |
ird | -0.092 |
tted | -0.090 |
Token | they |
Token ID | 484 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
blurry | +0.062 |
nam | +0.058 |
wil | +0.054 |
ateful | +0.053 |
lands | +0.052 |
Neg logit contributions | |
ocolate | -0.057 |
loe | -0.056 |
' | -0.053 |
ird | -0.053 |
tted | -0.051 |
Token | gathered |
Token ID | 9272 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
blurry | +0.010 |
nam | +0.009 |
wil | +0.009 |
ateful | +0.008 |
lands | +0.008 |
Neg logit contributions | |
ocolate | -0.011 |
loe | -0.011 |
' | -0.010 |
ird | -0.010 |
tted | -0.010 |
Token | around |
Token ID | 1088 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
ocolate | +0.028 |
loe | +0.027 |
' | +0.027 |
ird | +0.026 |
tted | +0.025 |
Neg logit contributions | |
blurry | -0.023 |
nam | -0.021 |
wil | -0.019 |
cks | -0.019 |
ateful | -0.019 |
Token | They |
Token ID | 2990 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
ocolate | +0.010 |
loe | +0.009 |
ird | +0.009 |
' | +0.009 |
uster | +0.008 |
Neg logit contributions | |
blurry | -0.009 |
nam | -0.008 |
wil | -0.008 |
ateful | -0.008 |
lands | -0.008 |
Token | chase |
Token ID | 15505 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
blurry | +0.053 |
nam | +0.051 |
wil | +0.049 |
ateful | +0.048 |
cks | +0.047 |
Neg logit contributions | |
' | -0.039 |
loe | -0.038 |
ocolate | -0.038 |
ird | -0.037 |
tted | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
blurry | +0.010 |
nam | +0.009 |
wil | +0.008 |
lands | +0.008 |
ateful | +0.008 |
Neg logit contributions | |
ocolate | -0.013 |
loe | -0.013 |
' | -0.013 |
ird | -0.013 |
tted | -0.012 |
Token | car |
Token ID | 1097 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
blurry | +0.007 |
nam | +0.006 |
lands | +0.006 |
prett | +0.006 |
wil | +0.006 |
Neg logit contributions | |
ocolate | -0.008 |
loe | -0.008 |
' | -0.007 |
ird | -0.007 |
tted | -0.007 |
Token | - |
Token ID | 12 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
nam | +0.048 |
blurry | +0.045 |
ateful | +0.045 |
wil | +0.044 |
ric | +0.041 |
Neg logit contributions | |
of | -0.023 |
' | -0.023 |
tted | -0.020 |
ay | -0.019 |
ocolate | -0.018 |
Token | nos |
Token ID | 39369 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
blurry | +0.044 |
nam | +0.042 |
wil | +0.040 |
ateful | +0.039 |
prett | +0.039 |
Neg logit contributions | |
ocolate | -0.026 |
loe | -0.025 |
' | -0.024 |
tted | -0.024 |
ird | -0.023 |
Token | aur |
Token ID | 2899 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ocolate | +0.250 |
loe | +0.240 |
' | +0.239 |
ird | +0.229 |
tted | +0.217 |
Neg logit contributions | |
blurry | -0.336 |
nam | -0.299 |
ateful | -0.294 |
wil | -0.292 |
lands | -0.288 |
Token | around |
Token ID | 1088 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
ocolate | +0.137 |
loe | +0.133 |
ird | +0.128 |
' | +0.127 |
tted | +0.124 |
Neg logit contributions | |
blurry | -0.138 |
nam | -0.126 |
wil | -0.119 |
lands | -0.118 |
cks | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
blurry | +0.028 |
nam | +0.026 |
wil | +0.024 |
ateful | +0.023 |
lands | +0.023 |
Neg logit contributions | |
ocolate | -0.037 |
loe | -0.037 |
ird | -0.035 |
' | -0.035 |
tted | -0.034 |
Token | room |
Token ID | 2119 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
blurry | +0.008 |
nam | +0.008 |
wil | +0.007 |
ateful | +0.007 |
lands | +0.007 |
Neg logit contributions | |
ocolate | -0.008 |
loe | -0.008 |
' | -0.007 |
ird | -0.007 |
tted | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
blurry | +0.009 |
nam | +0.009 |
wil | +0.008 |
ateful | +0.008 |
prett | +0.008 |
Neg logit contributions | |
' | -0.006 |
ocolate | -0.006 |
loe | -0.006 |
ird | -0.006 |
of | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
ocolate | +0.053 |
loe | +0.052 |
tted | +0.047 |
ird | +0.047 |
uster | +0.046 |
Neg logit contributions | |
blurry | -0.057 |
nam | -0.054 |
wil | -0.050 |
lands | -0.049 |
prett | -0.048 |
Token | school |
Token ID | 1524 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
ocolate | +0.053 |
loe | +0.051 |
' | +0.049 |
ird | +0.048 |
ay | +0.046 |
Neg logit contributions | |
blurry | -0.043 |
nam | -0.039 |
wil | -0.036 |
ateful | -0.036 |
lands | -0.035 |
Token | � |
Token ID | 6184 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
blurry | +0.041 |
nam | +0.039 |
wil | +0.036 |
lands | +0.035 |
ateful | +0.035 |
Neg logit contributions | |
ocolate | -0.038 |
loe | -0.037 |
' | -0.035 |
ird | -0.034 |
tted | -0.033 |
Token | � |
Token ID | 95 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
blurry | +0.051 |
nam | +0.049 |
wil | +0.045 |
ateful | +0.045 |
lands | +0.044 |
Neg logit contributions | |
ocolate | -0.037 |
loe | -0.035 |
uster | -0.033 |
ird | -0.033 |
' | -0.033 |
Token | € |
Token ID | 26391 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
blurry | +0.136 |
nam | +0.126 |
prett | +0.118 |
ateful | +0.118 |
wil | +0.117 |
Neg logit contributions | |
ocolate | -0.105 |
loe | -0.099 |
uster | -0.095 |
of | -0.092 |
' | -0.092 |
Token | � |
Token ID | 447 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
ocolate | +0.087 |
loe | +0.082 |
' | +0.077 |
ird | +0.076 |
tted | +0.074 |
Neg logit contributions | |
blurry | -0.116 |
nam | -0.109 |
wil | -0.102 |
lands | -0.101 |
ateful | -0.100 |
Token | � |
Token ID | 250 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ocolate | +0.098 |
loe | +0.093 |
' | +0.084 |
ird | +0.078 |
tted | +0.068 |
Neg logit contributions | |
blurry | -0.487 |
nam | -0.466 |
wil | -0.446 |
ateful | -0.441 |
lands | -0.439 |
Token | it |
Token ID | 340 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
blurry | +0.066 |
nam | +0.062 |
wil | +0.056 |
ateful | +0.055 |
prett | +0.055 |
Neg logit contributions | |
ocolate | -0.074 |
loe | -0.073 |
' | -0.070 |
ird | -0.069 |
tted | -0.066 |
Token | was |
Token ID | 373 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
ocolate | +0.039 |
loe | +0.038 |
' | +0.036 |
ird | +0.035 |
tted | +0.033 |
Neg logit contributions | |
blurry | -0.072 |
nam | -0.068 |
wil | -0.064 |
lands | -0.063 |
ateful | -0.063 |
Token | an |
Token ID | 281 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ocolate | +0.039 |
loe | +0.038 |
' | +0.037 |
ird | +0.036 |
tted | +0.035 |
Neg logit contributions | |
blurry | -0.042 |
nam | -0.039 |
wil | -0.036 |
prett | -0.035 |
lands | -0.035 |
Token | important |
Token ID | 1593 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
loe | +0.161 |
tted | +0.158 |
ocolate | +0.154 |
umbs | +0.154 |
� | +0.153 |
Neg logit contributions | |
blurry | -0.102 |
prett | -0.094 |
nam | -0.092 |
ateful | -0.082 |
wil | -0.079 |
Token | far |
Token ID | 1290 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ocolate | +0.006 |
loe | +0.006 |
' | +0.006 |
ird | +0.006 |
tted | +0.005 |
Neg logit contributions | |
blurry | -0.005 |
nam | -0.005 |
ateful | -0.004 |
cks | -0.004 |
wil | -0.004 |
Token | away |
Token ID | 1497 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
blurry | +0.065 |
nam | +0.063 |
wil | +0.057 |
ateful | +0.057 |
cks | +0.055 |
Neg logit contributions | |
ocolate | -0.061 |
' | -0.061 |
loe | -0.060 |
ird | -0.057 |
tted | -0.056 |
Token | � |
Token ID | 6184 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
ocolate | +0.034 |
loe | +0.033 |
' | +0.033 |
ird | +0.031 |
tted | +0.030 |
Neg logit contributions | |
blurry | -0.041 |
nam | -0.039 |
wil | -0.036 |
ateful | -0.036 |
prett | -0.035 |
Token | � |
Token ID | 95 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
blurry | +0.052 |
wil | +0.049 |
nam | +0.049 |
lands | +0.049 |
cks | +0.048 |
Neg logit contributions | |
ocolate | -0.032 |
loe | -0.031 |
kids | -0.030 |
ird | -0.030 |
other | -0.030 |
Token | € |
Token ID | 26391 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
blurry | +0.131 |
cks | +0.117 |
lands | +0.116 |
wil | +0.115 |
prett | +0.114 |
Neg logit contributions | |
ocolate | -0.098 |
loe | -0.091 |
of | -0.088 |
uster | -0.086 |
ird | -0.086 |
Token | � |
Token ID | 447 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
ocolate | +0.076 |
loe | +0.071 |
uster | +0.065 |
ird | +0.064 |
' | +0.064 |
Neg logit contributions | |
blurry | -0.112 |
nam | -0.106 |
lands | -0.102 |
wil | -0.101 |
cks | -0.101 |
Token | � |
Token ID | 250 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ocolate | +0.196 |
loe | +0.191 |
' | +0.187 |
ird | +0.178 |
tted | +0.171 |
Neg logit contributions | |
blurry | -0.389 |
nam | -0.368 |
wil | -0.346 |
ateful | -0.342 |
lands | -0.339 |
Token | it |
Token ID | 340 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
blurry | +0.061 |
nam | +0.058 |
wil | +0.052 |
ateful | +0.052 |
prett | +0.051 |
Neg logit contributions | |
ocolate | -0.068 |
loe | -0.067 |
' | -0.064 |
ird | -0.063 |
tted | -0.060 |
Token | is |
Token ID | 318 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
ocolate | +0.043 |
loe | +0.040 |
ird | +0.036 |
uster | +0.036 |
' | +0.034 |
Neg logit contributions | |
blurry | -0.062 |
nam | -0.056 |
wil | -0.056 |
lands | -0.055 |
prett | -0.055 |
Token | distant |
Token ID | 12899 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
blurry | +0.044 |
nam | +0.040 |
wil | +0.038 |
prett | +0.038 |
lands | +0.037 |
Neg logit contributions | |
ocolate | -0.046 |
loe | -0.045 |
ird | -0.042 |
' | -0.042 |
tted | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
blurry | +0.024 |
nam | +0.022 |
lands | +0.021 |
wil | +0.021 |
prett | +0.021 |
Neg logit contributions | |
ocolate | -0.017 |
loe | -0.016 |
ird | -0.015 |
' | -0.015 |
tted | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
blurry | +0.047 |
nam | +0.044 |
wil | +0.041 |
ateful | +0.040 |
lands | +0.040 |
Neg logit contributions | |
ocolate | -0.046 |
loe | -0.045 |
' | -0.043 |
ird | -0.043 |
tted | -0.041 |
Token | " |
Token ID | 366 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
blurry | +0.014 |
nam | +0.013 |
flashes | +0.013 |
lands | +0.012 |
wil | +0.012 |
Neg logit contributions | |
ocolate | -0.012 |
loe | -0.012 |
ird | -0.012 |
' | -0.011 |
uster | -0.011 |
Token | A |
Token ID | 32 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
blurry | +0.008 |
nam | +0.008 |
wil | +0.007 |
ateful | +0.007 |
lands | +0.007 |
Neg logit contributions | |
' | -0.008 |
ocolate | -0.008 |
tted | -0.007 |
loe | -0.007 |
ird | -0.007 |
Token | car |
Token ID | 1097 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
blurry | +0.014 |
lands | +0.012 |
nam | +0.012 |
prett | +0.012 |
flashes | +0.011 |
Neg logit contributions | |
ocolate | -0.018 |
loe | -0.017 |
' | -0.016 |
tted | -0.015 |
oning | -0.015 |
Token | - |
Token ID | 12 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
nam | +0.042 |
blurry | +0.042 |
wil | +0.038 |
ateful | +0.037 |
cks | +0.035 |
Neg logit contributions | |
' | -0.029 |
ocolate | -0.028 |
loe | -0.027 |
ird | -0.027 |
ay | -0.027 |
Token | nos |
Token ID | 39369 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
blurry | +0.041 |
nam | +0.038 |
wil | +0.037 |
ateful | +0.035 |
prett | +0.035 |
Neg logit contributions | |
ocolate | -0.029 |
loe | -0.028 |
' | -0.027 |
ird | -0.026 |
ay | -0.026 |
Token | aur |
Token ID | 2899 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ocolate | +0.256 |
loe | +0.248 |
' | +0.241 |
ird | +0.231 |
tted | +0.226 |
Neg logit contributions | |
blurry | -0.322 |
nam | -0.286 |
ateful | -0.283 |
lands | -0.276 |
wil | -0.274 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ocolate | +0.121 |
loe | +0.117 |
tted | +0.112 |
ird | +0.111 |
' | +0.109 |
Neg logit contributions | |
blurry | -0.150 |
nam | -0.136 |
cks | -0.135 |
lands | -0.134 |
wil | -0.131 |
Token |
|
Token ID | 198 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
' | +0.007 |
ird | +0.007 |
tted | +0.006 |
Neg logit contributions | |
blurry | -0.012 |
nam | -0.011 |
wil | -0.010 |
lands | -0.010 |
ateful | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
ird | +0.007 |
' | +0.007 |
tted | +0.006 |
Neg logit contributions | |
blurry | -0.012 |
nam | -0.011 |
wil | -0.010 |
lands | -0.010 |
cks | -0.010 |
Token | They |
Token ID | 2990 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
ocolate | +0.010 |
loe | +0.009 |
ird | +0.009 |
' | +0.009 |
uster | +0.008 |
Neg logit contributions | |
blurry | -0.009 |
nam | -0.008 |
wil | -0.008 |
ateful | -0.008 |
lands | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
ocolate | +0.061 |
' | +0.060 |
loe | +0.059 |
ird | +0.057 |
tted | +0.054 |
Neg logit contributions | |
blurry | -0.082 |
nam | -0.078 |
wil | -0.073 |
ateful | -0.072 |
cks | -0.072 |
Token | they |
Token ID | 484 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
of | +0.004 |
ird | +0.004 |
loe | +0.004 |
' | +0.004 |
ocolate | +0.004 |
Neg logit contributions | |
blurry | -0.005 |
cks | -0.005 |
wil | -0.005 |
nam | -0.005 |
ateful | -0.004 |
Token | played |
Token ID | 2826 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
blurry | +0.010 |
cks | +0.009 |
nam | +0.009 |
ateful | +0.009 |
lands | +0.009 |
Neg logit contributions | |
' | -0.007 |
ird | -0.006 |
of | -0.006 |
loe | -0.006 |
ocolate | -0.006 |
Token | make |
Token ID | 787 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ocolate | +0.039 |
loe | +0.039 |
' | +0.037 |
ird | +0.037 |
uster | +0.035 |
Neg logit contributions | |
blurry | -0.032 |
nam | -0.029 |
wil | -0.026 |
prett | -0.026 |
lands | -0.026 |
Token | - |
Token ID | 12 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
blurry | +0.040 |
nam | +0.038 |
wil | +0.035 |
ateful | +0.034 |
cks | +0.033 |
Neg logit contributions | |
ocolate | -0.037 |
loe | -0.036 |
' | -0.035 |
ird | -0.034 |
tted | -0.033 |
Token | bel |
Token ID | 6667 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
blurry | +0.017 |
nam | +0.014 |
cks | +0.013 |
wil | +0.013 |
lands | +0.013 |
Neg logit contributions | |
ocolate | -0.052 |
' | -0.051 |
tted | -0.051 |
of | -0.051 |
ird | -0.051 |
Token | ieve |
Token ID | 12311 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
blurry | +0.310 |
nam | +0.290 |
wil | +0.263 |
ateful | +0.261 |
lands | +0.258 |
Neg logit contributions | |
ocolate | -0.337 |
loe | -0.331 |
' | -0.319 |
ird | -0.313 |
tted | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
blurry | +0.057 |
nam | +0.054 |
wil | +0.051 |
ateful | +0.049 |
cks | +0.049 |
Neg logit contributions | |
' | -0.046 |
ocolate | -0.046 |
loe | -0.046 |
ird | -0.043 |
of | -0.042 |
Token | Finally |
Token ID | 9461 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
ocolate | +0.004 |
loe | +0.004 |
' | +0.004 |
ird | +0.004 |
ay | +0.004 |
Neg logit contributions | |
blurry | -0.004 |
nam | -0.004 |
wil | -0.004 |
ateful | -0.004 |
cks | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
ocolate | +0.024 |
loe | +0.023 |
tted | +0.021 |
ird | +0.021 |
uster | +0.021 |
Neg logit contributions | |
blurry | -0.052 |
nam | -0.049 |
lands | -0.046 |
wil | -0.046 |
ateful | -0.046 |
Token | they |
Token ID | 484 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
' | +0.006 |
ocolate | +0.005 |
of | +0.005 |
loe | +0.005 |
ird | +0.004 |
Neg logit contributions | |
blurry | -0.007 |
nam | -0.007 |
wil | -0.007 |
cks | -0.006 |
endant | -0.006 |
Token | red |
Token ID | 2266 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
blurry | +0.037 |
nam | +0.034 |
wil | +0.032 |
ateful | +0.031 |
lands | +0.031 |
Neg logit contributions | |
ocolate | -0.039 |
loe | -0.039 |
' | -0.037 |
ird | -0.037 |
tted | -0.035 |
Token | cape |
Token ID | 36023 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
blurry | +0.011 |
nam | +0.010 |
wil | +0.009 |
ateful | +0.009 |
cks | +0.009 |
Neg logit contributions | |
ocolate | -0.011 |
loe | -0.010 |
' | -0.010 |
ird | -0.010 |
ay | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
blurry | +0.046 |
nam | +0.043 |
wil | +0.041 |
ateful | +0.040 |
cks | +0.040 |
Neg logit contributions | |
ocolate | -0.028 |
loe | -0.028 |
' | -0.027 |
ird | -0.026 |
tted | -0.025 |
Token | make |
Token ID | 787 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
ird | +0.003 |
' | +0.003 |
of | +0.003 |
ocolate | +0.003 |
loe | +0.003 |
Neg logit contributions | |
blurry | -0.004 |
ateful | -0.004 |
wil | -0.004 |
cks | -0.004 |
nam | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
blurry | +0.050 |
nam | +0.049 |
wil | +0.047 |
ateful | +0.045 |
cks | +0.043 |
Neg logit contributions | |
loe | -0.027 |
' | -0.026 |
ocolate | -0.026 |
of | -0.026 |
ay | -0.025 |
Token | bel |
Token ID | 6667 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
blurry | +0.021 |
nam | +0.017 |
wil | +0.017 |
cks | +0.016 |
ateful | +0.015 |
Neg logit contributions | |
' | -0.048 |
of | -0.047 |
ird | -0.047 |
tted | -0.047 |
ocolate | -0.046 |
Token | ieve |
Token ID | 12311 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
blurry | +0.323 |
nam | +0.301 |
wil | +0.279 |
ateful | +0.272 |
lands | +0.270 |
Neg logit contributions | |
ocolate | -0.325 |
loe | -0.320 |
' | -0.308 |
ird | -0.302 |
tted | -0.291 |
Token | he |
Token ID | 339 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
blurry | +0.059 |
nam | +0.056 |
wil | +0.054 |
ateful | +0.052 |
prett | +0.051 |
Neg logit contributions | |
of | -0.039 |
' | -0.039 |
loe | -0.038 |
ocolate | -0.038 |
ay | -0.036 |
Token | had |
Token ID | 550 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
blurry | +0.050 |
nam | +0.050 |
ateful | +0.045 |
wil | +0.045 |
cks | +0.043 |
Neg logit contributions | |
' | -0.036 |
ird | -0.035 |
of | -0.034 |
loe | -0.034 |
tted | -0.033 |
Token | super |
Token ID | 2208 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ocolate | +0.017 |
loe | +0.017 |
' | +0.017 |
ird | +0.017 |
of | +0.016 |
Neg logit contributions | |
blurry | -0.023 |
nam | -0.022 |
wil | -0.021 |
ateful | -0.020 |
cks | -0.019 |
Token | powers |
Token ID | 30132 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
blurry | +0.088 |
nam | +0.088 |
wil | +0.081 |
ateful | +0.080 |
cks | +0.079 |
Neg logit contributions | |
of | -0.065 |
' | -0.064 |
tted | -0.064 |
ird | -0.062 |
loe | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
blurry | +0.001 |
nam | +0.001 |
cks | +0.001 |
ateful | +0.000 |
wil | +0.000 |
Neg logit contributions | |
ocolate | -0.000 |
loe | -0.000 |
' | -0.000 |
ird | -0.000 |
of | -0.000 |
Token | world |
Token ID | 995 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
ocolate | +0.024 |
loe | +0.023 |
' | +0.023 |
ird | +0.022 |
tted | +0.021 |
Neg logit contributions | |
blurry | -0.025 |
nam | -0.023 |
ateful | -0.022 |
wil | -0.022 |
cks | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
ocolate | +0.006 |
loe | +0.005 |
' | +0.005 |
ird | +0.005 |
tted | +0.005 |
Neg logit contributions | |
blurry | -0.007 |
nam | -0.006 |
wil | -0.006 |
ateful | -0.006 |
cks | -0.006 |
Token | make |
Token ID | 787 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
ocolate | +0.035 |
loe | +0.033 |
' | +0.033 |
ird | +0.032 |
of | +0.031 |
Neg logit contributions | |
blurry | -0.036 |
nam | -0.032 |
ateful | -0.031 |
cks | -0.031 |
wil | -0.031 |
Token | - |
Token ID | 12 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
blurry | +0.039 |
nam | +0.038 |
ateful | +0.035 |
wil | +0.034 |
cks | +0.033 |
Neg logit contributions | |
loe | -0.037 |
ocolate | -0.037 |
' | -0.036 |
of | -0.035 |
ird | -0.035 |
Token | bel |
Token ID | 6667 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
blurry | +0.025 |
nam | +0.022 |
cks | +0.021 |
wil | +0.020 |
ateful | +0.020 |
Neg logit contributions | |
' | -0.043 |
of | -0.043 |
ocolate | -0.041 |
tted | -0.041 |
ird | -0.041 |
Token | ieve |
Token ID | 12311 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
blurry | +0.304 |
nam | +0.286 |
ateful | +0.259 |
cks | +0.257 |
wil | +0.257 |
Neg logit contributions | |
ocolate | -0.341 |
loe | -0.333 |
' | -0.320 |
ird | -0.314 |
uster | -0.307 |
Token | . |
Token ID | 13 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
blurry | +0.058 |
nam | +0.055 |
wil | +0.051 |
ateful | +0.050 |
cks | +0.049 |
Neg logit contributions | |
' | -0.046 |
loe | -0.046 |
ocolate | -0.045 |
ird | -0.043 |
of | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
ocolate | +0.005 |
loe | +0.005 |
' | +0.005 |
ird | +0.005 |
uster | +0.005 |
Neg logit contributions | |
nam | -0.004 |
blurry | -0.004 |
lands | -0.004 |
prett | -0.003 |
wil | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
ocolate | +0.022 |
uster | +0.021 |
ird | +0.021 |
loe | +0.020 |
tted | +0.019 |
Neg logit contributions | |
blurry | -0.017 |
lands | -0.016 |
nam | -0.015 |
cks | -0.015 |
wil | -0.015 |
Token | She |
Token ID | 3347 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
ocolate | +0.021 |
loe | +0.021 |
ird | +0.020 |
uster | +0.020 |
' | +0.019 |
Neg logit contributions | |
blurry | -0.019 |
nam | -0.018 |
wil | -0.016 |
ateful | -0.015 |
prett | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
blurry | +0.052 |
nam | +0.048 |
wil | +0.045 |
cks | +0.044 |
prett | +0.044 |
Neg logit contributions | |
ocolate | -0.053 |
loe | -0.052 |
' | -0.051 |
ird | -0.048 |
of | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
blurry | +0.042 |
nam | +0.039 |
wil | +0.035 |
ateful | +0.035 |
cks | +0.035 |
Neg logit contributions | |
ocolate | -0.040 |
loe | -0.040 |
' | -0.039 |
ird | -0.038 |
tted | -0.037 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ocolate | +0.026 |
loe | +0.026 |
' | +0.025 |
ird | +0.024 |
tted | +0.024 |
Neg logit contributions | |
blurry | -0.027 |
nam | -0.025 |
wil | -0.023 |
ateful | -0.023 |
lands | -0.023 |
Token | make |
Token ID | 787 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
loe | +0.091 |
ocolate | +0.091 |
ird | +0.085 |
uster | +0.084 |
' | +0.082 |
Neg logit contributions | |
blurry | -0.084 |
nam | -0.078 |
lands | -0.072 |
prett | -0.070 |
wil | -0.070 |
Token | - |
Token ID | 12 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
blurry | +0.043 |
nam | +0.040 |
lands | +0.037 |
prett | +0.036 |
wil | +0.036 |
Neg logit contributions | |
ocolate | -0.044 |
loe | -0.043 |
' | -0.041 |
ird | -0.041 |
tted | -0.040 |
Token | bel |
Token ID | 6667 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
blurry | +0.020 |
nam | +0.017 |
cks | +0.016 |
wil | +0.016 |
lands | +0.016 |
Neg logit contributions | |
' | -0.042 |
ocolate | -0.042 |
of | -0.041 |
tted | -0.041 |
ird | -0.041 |
Token | ieve |
Token ID | 12311 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
blurry | +0.312 |
nam | +0.293 |
wil | +0.265 |
ateful | +0.265 |
cks | +0.261 |
Neg logit contributions | |
ocolate | -0.333 |
loe | -0.327 |
' | -0.313 |
ird | -0.307 |
uster | -0.298 |
Token | at |
Token ID | 379 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
blurry | +0.052 |
nam | +0.048 |
wil | +0.045 |
ateful | +0.044 |
prett | +0.044 |
Neg logit contributions | |
ocolate | -0.043 |
loe | -0.042 |
' | -0.041 |
ird | -0.040 |
tted | -0.038 |
Token | home |
Token ID | 1363 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
blurry | +0.115 |
nam | +0.104 |
wil | +0.099 |
ateful | +0.096 |
cks | +0.094 |
Neg logit contributions | |
ocolate | -0.111 |
loe | -0.109 |
' | -0.103 |
ird | -0.102 |
other | -0.096 |
Token | , |
Token ID | 11 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ocolate | +0.147 |
loe | +0.144 |
' | +0.141 |
ird | +0.137 |
tted | +0.130 |
Neg logit contributions | |
blurry | -0.174 |
nam | -0.162 |
wil | -0.152 |
ateful | -0.148 |
cks | -0.147 |
Token | too |
Token ID | 1165 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ocolate | +0.009 |
loe | +0.009 |
' | +0.008 |
ird | +0.008 |
tted | +0.007 |
Neg logit contributions | |
blurry | -0.016 |
nam | -0.015 |
ateful | -0.014 |
wil | -0.014 |
cks | -0.014 |
Token | liked |
Token ID | 8288 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
ocolate | +0.006 |
loe | +0.006 |
' | +0.005 |
ird | +0.005 |
tted | +0.005 |
Neg logit contributions | |
blurry | -0.007 |
cks | -0.007 |
nam | -0.007 |
lands | -0.006 |
ateful | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
ocolate | +0.022 |
' | +0.021 |
loe | +0.021 |
of | +0.019 |
ird | +0.019 |
Neg logit contributions | |
blurry | -0.033 |
nam | -0.030 |
cks | -0.030 |
ateful | -0.030 |
wil | -0.029 |
Token | play |
Token ID | 711 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
blurry | +0.028 |
nam | +0.027 |
wil | +0.024 |
ateful | +0.024 |
lands | +0.024 |
Neg logit contributions | |
ocolate | -0.029 |
loe | -0.029 |
' | -0.028 |
ird | -0.027 |
tted | -0.027 |
Token | make |
Token ID | 787 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
blurry | +0.016 |
nam | +0.015 |
lands | +0.014 |
prett | +0.014 |
wil | +0.014 |
Neg logit contributions | |
ocolate | -0.016 |
loe | -0.016 |
ird | -0.015 |
' | -0.014 |
uster | -0.014 |
Token | - |
Token ID | 12 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
blurry | +0.037 |
nam | +0.034 |
wil | +0.031 |
ateful | +0.031 |
lands | +0.030 |
Neg logit contributions | |
ocolate | -0.045 |
loe | -0.044 |
' | -0.042 |
ird | -0.042 |
tted | -0.040 |
Token | bel |
Token ID | 6667 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
blurry | +0.021 |
nam | +0.018 |
wil | +0.017 |
cks | +0.017 |
lands | +0.016 |
Neg logit contributions | |
tted | -0.045 |
' | -0.045 |
ocolate | -0.044 |
of | -0.044 |
ird | -0.044 |
Token | ieve |
Token ID | 12311 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
blurry | +0.305 |
nam | +0.285 |
wil | +0.258 |
ateful | +0.257 |
lands | +0.254 |
Neg logit contributions | |
ocolate | -0.335 |
loe | -0.329 |
' | -0.316 |
ird | -0.311 |
tted | -0.301 |
Token | . |
Token ID | 13 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
blurry | +0.056 |
nam | +0.053 |
wil | +0.050 |
cks | +0.049 |
ateful | +0.049 |
Neg logit contributions | |
' | -0.040 |
loe | -0.040 |
ocolate | -0.039 |
of | -0.038 |
ird | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ocolate | +0.004 |
loe | +0.004 |
tted | +0.004 |
ird | +0.004 |
uster | +0.004 |
Neg logit contributions | |
blurry | -0.005 |
nam | -0.005 |
prett | -0.005 |
lands | -0.005 |
wil | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ocolate | +0.019 |
loe | +0.018 |
uster | +0.018 |
ird | +0.018 |
tted | +0.017 |
Neg logit contributions | |
blurry | -0.020 |
nam | -0.019 |
lands | -0.018 |
wil | -0.017 |
cks | -0.017 |
Token | One |
Token ID | 3198 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
ocolate | +0.023 |
loe | +0.022 |
uster | +0.022 |
ird | +0.021 |
tted | +0.021 |
Neg logit contributions | |
blurry | -0.017 |
nam | -0.016 |
prett | -0.014 |
wil | -0.014 |
ateful | -0.013 |
Token | Finally |
Token ID | 9461 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
blurry | +0.004 |
nam | +0.004 |
lands | +0.004 |
wil | +0.004 |
prett | +0.004 |
Neg logit contributions | |
ocolate | -0.003 |
loe | -0.003 |
' | -0.003 |
ird | -0.003 |
uster | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ocolate | +0.024 |
loe | +0.023 |
tted | +0.022 |
uster | +0.022 |
' | +0.021 |
Neg logit contributions | |
blurry | -0.047 |
nam | -0.044 |
wil | -0.043 |
lands | -0.042 |
ateful | -0.041 |
Token | her |
Token ID | 607 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
ocolate | +0.007 |
' | +0.007 |
loe | +0.007 |
ird | +0.007 |
of | +0.006 |
Neg logit contributions | |
blurry | -0.006 |
cks | -0.005 |
nam | -0.005 |
ateful | -0.005 |
wil | -0.005 |
Token | make |
Token ID | 787 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
blurry | +0.024 |
nam | +0.022 |
wil | +0.021 |
lands | +0.021 |
prett | +0.021 |
Neg logit contributions | |
ocolate | -0.022 |
loe | -0.022 |
' | -0.021 |
ird | -0.020 |
tted | -0.020 |
Token | - |
Token ID | 12 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
blurry | +0.048 |
nam | +0.048 |
ateful | +0.043 |
wil | +0.042 |
cks | +0.041 |
Neg logit contributions | |
loe | -0.042 |
ocolate | -0.041 |
' | -0.041 |
ird | -0.040 |
of | -0.038 |
Token | bel |
Token ID | 6667 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
blurry | +0.026 |
nam | +0.024 |
wil | +0.022 |
cks | +0.021 |
ateful | +0.021 |
Neg logit contributions | |
ocolate | -0.032 |
' | -0.031 |
loe | -0.031 |
ird | -0.030 |
tted | -0.030 |
Token | ieve |
Token ID | 12311 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
blurry | +0.279 |
nam | +0.267 |
ateful | +0.242 |
cks | +0.242 |
prett | +0.235 |
Neg logit contributions | |
ocolate | -0.349 |
loe | -0.341 |
' | -0.327 |
uster | -0.322 |
ird | -0.319 |
Token | adventures |
Token ID | 17545 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
blurry | +0.050 |
nam | +0.047 |
wil | +0.044 |
ateful | +0.043 |
lands | +0.043 |
Neg logit contributions | |
ocolate | -0.040 |
loe | -0.039 |
' | -0.037 |
ird | -0.037 |
tted | -0.035 |
Token | were |
Token ID | 547 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
blurry | +0.042 |
nam | +0.040 |
wil | +0.037 |
ateful | +0.037 |
cks | +0.037 |
Neg logit contributions | |
ocolate | -0.027 |
loe | -0.026 |
' | -0.025 |
ird | -0.025 |
tted | -0.024 |
Token | recorded |
Token ID | 6264 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
ocolate | +0.009 |
' | +0.009 |
loe | +0.009 |
ird | +0.009 |
of | +0.008 |
Neg logit contributions | |
blurry | -0.011 |
nam | -0.010 |
ateful | -0.010 |
wil | -0.009 |
cks | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
blurry | +0.029 |
nam | +0.028 |
wil | +0.026 |
ateful | +0.025 |
cks | +0.025 |
Neg logit contributions | |
ocolate | -0.022 |
loe | -0.022 |
' | -0.021 |
ird | -0.020 |
tted | -0.019 |
Token | - |
Token ID | 12 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
blurry | +0.061 |
nam | +0.058 |
wil | +0.055 |
ateful | +0.055 |
cks | +0.053 |
Neg logit contributions | |
ocolate | -0.031 |
loe | -0.030 |
' | -0.030 |
ird | -0.028 |
ay | -0.027 |
Token | up |
Token ID | 929 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
blurry | +0.035 |
nam | +0.032 |
wil | +0.031 |
ateful | +0.031 |
cks | +0.030 |
Neg logit contributions | |
ocolate | -0.027 |
loe | -0.026 |
ird | -0.026 |
' | -0.026 |
tted | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
blurry | +0.033 |
nam | +0.031 |
wil | +0.029 |
ateful | +0.029 |
cks | +0.028 |
Neg logit contributions | |
ocolate | -0.022 |
' | -0.022 |
loe | -0.022 |
ird | -0.021 |
tted | -0.020 |
Token | make |
Token ID | 787 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
ird | +0.007 |
' | +0.007 |
of | +0.007 |
ocolate | +0.007 |
loe | +0.007 |
Neg logit contributions | |
blurry | -0.010 |
cks | -0.009 |
ateful | -0.009 |
wil | -0.009 |
lands | -0.009 |
Token | - |
Token ID | 12 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
fly | +0.041 |
blurry | +0.040 |
wil | +0.040 |
nam | +0.040 |
flies | +0.039 |
Neg logit contributions | |
of | -0.035 |
' | -0.032 |
ird | -0.032 |
ay | -0.032 |
loe | -0.031 |
Token | bel |
Token ID | 6667 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
blurry | +0.029 |
cks | +0.025 |
nam | +0.025 |
wil | +0.025 |
ateful | +0.024 |
Neg logit contributions | |
ird | -0.033 |
of | -0.032 |
tted | -0.032 |
' | -0.032 |
ocolate | -0.031 |
Token | ieve |
Token ID | 12311 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
blurry | +0.302 |
nam | +0.281 |
wil | +0.259 |
ateful | +0.252 |
lands | +0.251 |
Neg logit contributions | |
ocolate | -0.332 |
loe | -0.327 |
' | -0.315 |
ird | -0.310 |
tted | -0.300 |
Token | . |
Token ID | 13 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
blurry | +0.054 |
nam | +0.050 |
wil | +0.050 |
cks | +0.049 |
ric | +0.049 |
Neg logit contributions | |
of | -0.034 |
' | -0.032 |
loe | -0.030 |
ay | -0.030 |
ird | -0.030 |
Token | One |
Token ID | 1881 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
ocolate | +0.002 |
loe | +0.002 |
tted | +0.002 |
' | +0.002 |
ird | +0.002 |
Neg logit contributions | |
blurry | -0.003 |
nam | -0.003 |
prett | -0.003 |
lands | -0.003 |
wil | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
ocolate | +0.037 |
loe | +0.037 |
ird | +0.035 |
' | +0.034 |
tted | +0.033 |
Neg logit contributions | |
blurry | -0.052 |
nam | -0.048 |
wil | -0.046 |
prett | -0.045 |
ateful | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ocolate | +0.043 |
tted | +0.043 |
loe | +0.042 |
uster | +0.040 |
kids | +0.039 |
Neg logit contributions | |
blurry | -0.060 |
nam | -0.058 |
lands | -0.054 |
wil | -0.052 |
ateful | -0.051 |
Token | " |
Token ID | 366 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
ird | +0.006 |
tted | +0.006 |
' | +0.006 |
Neg logit contributions | |
blurry | -0.010 |
nam | -0.009 |
wil | -0.009 |
prett | -0.008 |
lands | -0.008 |
Token | Please |
Token ID | 5492 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
blurry | +0.009 |
nam | +0.008 |
wil | +0.007 |
ateful | +0.007 |
lands | +0.007 |
Neg logit contributions | |
ocolate | -0.009 |
loe | -0.009 |
' | -0.009 |
ird | -0.009 |
tted | -0.008 |
Token | keep |
Token ID | 1394 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
blurry | +0.011 |
lands | +0.010 |
nam | +0.010 |
wil | +0.010 |
prett | +0.009 |
Neg logit contributions | |
ocolate | -0.011 |
loe | -0.011 |
uster | -0.010 |
other | -0.010 |
kids | -0.010 |
Token | your |
Token ID | 534 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
ocolate | +0.009 |
loe | +0.009 |
' | +0.009 |
ird | +0.009 |
tted | +0.009 |
Neg logit contributions | |
blurry | -0.009 |
nam | -0.008 |
wil | -0.007 |
lands | -0.007 |
ateful | -0.007 |
Token | seat |
Token ID | 5852 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ocolate | +0.051 |
loe | +0.051 |
' | +0.051 |
ird | +0.049 |
tted | +0.047 |
Neg logit contributions | |
blurry | -0.055 |
nam | -0.052 |
ateful | -0.048 |
wil | -0.048 |
cks | -0.047 |
Token | bel |
Token ID | 6667 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
blurry | +0.021 |
nam | +0.020 |
wil | +0.019 |
prett | +0.019 |
lands | +0.018 |
Neg logit contributions | |
ocolate | -0.018 |
loe | -0.017 |
' | -0.016 |
ird | -0.016 |
tted | -0.015 |
Token | ts |
Token ID | 912 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
nam | +0.234 |
blurry | +0.226 |
cks | +0.226 |
ateful | +0.218 |
prett | +0.197 |
Neg logit contributions | |
ocolate | -0.350 |
uster | -0.348 |
loe | -0.347 |
uddy | -0.337 |
obby | -0.334 |
Token | on |
Token ID | 319 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
blurry | +0.008 |
nam | +0.008 |
wil | +0.007 |
lands | +0.007 |
prett | +0.007 |
Neg logit contributions | |
ocolate | -0.007 |
loe | -0.007 |
ird | -0.006 |
' | -0.006 |
tted | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
blurry | +0.014 |
nam | +0.013 |
lands | +0.012 |
wil | +0.012 |
cks | +0.011 |
Neg logit contributions | |
ocolate | -0.018 |
loe | -0.018 |
ird | -0.018 |
tted | -0.017 |
' | -0.017 |
Token | We |
Token ID | 775 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
nam | +0.003 |
blurry | +0.003 |
flashes | +0.003 |
prett | +0.003 |
Mars | +0.003 |
Neg logit contributions | |
ocolate | -0.004 |
loe | -0.004 |
ve | -0.004 |
' | -0.004 |
kids | -0.004 |
Token | will |
Token ID | 481 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
blurry | +0.093 |
nam | +0.085 |
wil | +0.082 |
lands | +0.079 |
prett | +0.079 |
Neg logit contributions | |
ocolate | -0.087 |
loe | -0.084 |
' | -0.075 |
ird | -0.074 |
uster | -0.074 |
Token | John |
Token ID | 1757 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
blurry | +0.001 |
nam | +0.001 |
flashes | +0.001 |
ateful | +0.001 |
lands | +0.001 |
Neg logit contributions | |
ocolate | -0.001 |
loe | -0.001 |
ird | -0.001 |
' | -0.001 |
tted | -0.001 |
Token | began |
Token ID | 2540 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
ocolate | +0.088 |
loe | +0.085 |
ird | +0.080 |
' | +0.078 |
uster | +0.078 |
Neg logit contributions | |
blurry | -0.077 |
nam | -0.071 |
wil | -0.068 |
lands | -0.067 |
prett | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
blurry | +0.046 |
nam | +0.043 |
ateful | +0.041 |
wil | +0.040 |
cks | +0.039 |
Neg logit contributions | |
ocolate | -0.032 |
' | -0.032 |
loe | -0.032 |
ird | -0.029 |
of | -0.029 |
Token | make |
Token ID | 787 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
blurry | +0.028 |
nam | +0.026 |
wil | +0.024 |
ateful | +0.024 |
cks | +0.024 |
Neg logit contributions | |
ocolate | -0.027 |
loe | -0.026 |
' | -0.026 |
ird | -0.025 |
tted | -0.024 |
Token | - |
Token ID | 12 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
blurry | +0.046 |
nam | +0.043 |
wil | +0.041 |
ateful | +0.040 |
cks | +0.038 |
Neg logit contributions | |
ocolate | -0.041 |
loe | -0.041 |
' | -0.039 |
ird | -0.038 |
tted | -0.037 |
Token | bel |
Token ID | 6667 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
blurry | +0.020 |
nam | +0.017 |
wil | +0.016 |
cks | +0.015 |
ateful | +0.015 |
Neg logit contributions | |
ocolate | -0.039 |
' | -0.038 |
loe | -0.038 |
ird | -0.038 |
tted | -0.037 |
Token | ieve |
Token ID | 12311 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
blurry | +0.288 |
nam | +0.273 |
ateful | +0.246 |
cks | +0.244 |
prett | +0.241 |
Neg logit contributions | |
ocolate | -0.334 |
loe | -0.328 |
' | -0.314 |
ird | -0.310 |
uster | -0.303 |
Token | he |
Token ID | 339 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
blurry | +0.052 |
nam | +0.049 |
wil | +0.046 |
ateful | +0.045 |
prett | +0.044 |
Neg logit contributions | |
ocolate | -0.036 |
loe | -0.036 |
' | -0.035 |
ird | -0.033 |
tted | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
blurry | +0.045 |
nam | +0.042 |
ateful | +0.039 |
wil | +0.039 |
cks | +0.038 |
Neg logit contributions | |
' | -0.034 |
ocolate | -0.034 |
loe | -0.034 |
ird | -0.033 |
tted | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
' | +0.021 |
ocolate | +0.021 |
loe | +0.020 |
ird | +0.020 |
tted | +0.019 |
Neg logit contributions | |
blurry | -0.027 |
nam | -0.025 |
wil | -0.024 |
ateful | -0.024 |
cks | -0.023 |
Token | hero |
Token ID | 4293 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
ocolate | +0.023 |
loe | +0.022 |
' | +0.022 |
ird | +0.021 |
tted | +0.020 |
Neg logit contributions | |
blurry | -0.030 |
nam | -0.029 |
wil | -0.027 |
ateful | -0.027 |
cks | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ocolate | +0.023 |
loe | +0.023 |
' | +0.022 |
ird | +0.021 |
tted | +0.020 |
Neg logit contributions | |
blurry | -0.028 |
nam | -0.027 |
wil | -0.024 |
ateful | -0.024 |
prett | -0.024 |
Token | ready |
Token ID | 3492 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ocolate | +0.031 |
loe | +0.031 |
' | +0.030 |
ird | +0.030 |
tted | +0.028 |
Neg logit contributions | |
blurry | -0.034 |
nam | -0.032 |
ateful | -0.030 |
wil | -0.029 |
lands | -0.029 |
Token | for |
Token ID | 329 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
loe | +0.076 |
ocolate | +0.076 |
ird | +0.071 |
tted | +0.069 |
' | +0.069 |
Neg logit contributions | |
blurry | -0.080 |
nam | -0.072 |
wil | -0.068 |
lands | -0.067 |
prett | -0.067 |
Token | make |
Token ID | 787 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
ocolate | +0.080 |
loe | +0.079 |
' | +0.077 |
tted | +0.077 |
ird | +0.076 |
Neg logit contributions | |
blurry | -0.069 |
nam | -0.065 |
lands | -0.059 |
cks | -0.058 |
wil | -0.058 |
Token | - |
Token ID | 12 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
blurry | +0.048 |
nam | +0.045 |
wil | +0.042 |
ateful | +0.041 |
lands | +0.041 |
Neg logit contributions | |
ocolate | -0.048 |
loe | -0.047 |
' | -0.045 |
ird | -0.044 |
tted | -0.043 |
Token | bel |
Token ID | 6667 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
blurry | +0.023 |
nam | +0.021 |
wil | +0.020 |
lands | +0.019 |
cks | +0.019 |
Neg logit contributions | |
ocolate | -0.023 |
loe | -0.023 |
' | -0.023 |
ird | -0.022 |
tted | -0.022 |
Token | ieve |
Token ID | 12311 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
blurry | +0.281 |
nam | +0.269 |
ateful | +0.245 |
cks | +0.243 |
prett | +0.236 |
Neg logit contributions | |
ocolate | -0.331 |
loe | -0.325 |
' | -0.309 |
uster | -0.305 |
ird | -0.303 |
Token | fun |
Token ID | 1257 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
blurry | +0.044 |
nam | +0.042 |
wil | +0.039 |
ateful | +0.038 |
lands | +0.038 |
Neg logit contributions | |
ocolate | -0.034 |
loe | -0.034 |
' | -0.032 |
ird | -0.032 |
tted | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
blurry | +0.055 |
nam | +0.052 |
wil | +0.049 |
ateful | +0.048 |
prett | +0.047 |
Neg logit contributions | |
ocolate | -0.043 |
loe | -0.042 |
' | -0.041 |
ird | -0.039 |
tted | -0.038 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ocolate | +0.002 |
loe | +0.002 |
ird | +0.002 |
uster | +0.002 |
' | +0.002 |
Neg logit contributions | |
blurry | -0.003 |
nam | -0.003 |
lands | -0.003 |
ateful | -0.003 |
cks | -0.003 |
Token | Once |
Token ID | 7454 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
lands | +0.086 |
blurry | +0.084 |
cks | +0.075 |
flashes | +0.074 |
nam | +0.072 |
Neg logit contributions | |
ocolate | -0.136 |
uster | -0.132 |
loe | -0.127 |
ird | -0.127 |
adult | -0.126 |
Token | to |
Token ID | 284 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
loe | +0.032 |
ocolate | +0.032 |
' | +0.030 |
ird | +0.029 |
tted | +0.029 |
Neg logit contributions | |
blurry | -0.022 |
nam | -0.020 |
lands | -0.018 |
prett | -0.018 |
wil | -0.017 |
Token | prevent |
Token ID | 2948 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
blurry | +0.027 |
nam | +0.025 |
wil | +0.023 |
lands | +0.023 |
prett | +0.023 |
Neg logit contributions | |
ocolate | -0.024 |
loe | -0.024 |
' | -0.023 |
ird | -0.022 |
tted | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ocolate | +0.068 |
loe | +0.067 |
' | +0.064 |
ird | +0.062 |
of | +0.061 |
Neg logit contributions | |
blurry | -0.084 |
nam | -0.078 |
wil | -0.074 |
prett | -0.071 |
ateful | -0.070 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ocolate | +0.001 |
loe | +0.001 |
' | +0.001 |
ird | +0.001 |
tted | +0.001 |
Neg logit contributions | |
blurry | -0.001 |
nam | -0.001 |
wil | -0.001 |
lands | -0.001 |
prett | -0.001 |
Token | guys |
Token ID | 3730 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
blurry | +0.011 |
nam | +0.010 |
wil | +0.009 |
ateful | +0.009 |
lands | +0.009 |
Neg logit contributions | |
ocolate | -0.010 |
loe | -0.010 |
' | -0.009 |
ird | -0.009 |
tted | -0.009 |
Token | ( |
Token ID | 357 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
ocolate | +0.039 |
loe | +0.038 |
' | +0.037 |
ird | +0.036 |
tted | +0.035 |
Neg logit contributions | |
blurry | -0.045 |
nam | -0.043 |
wil | -0.040 |
ateful | -0.039 |
prett | -0.038 |
Token | the |
Token ID | 1169 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
blurry | +0.346 |
nam | +0.333 |
ateful | +0.306 |
wil | +0.304 |
cks | +0.298 |
Neg logit contributions | |
ocolate | -0.268 |
loe | -0.264 |
' | -0.249 |
ird | -0.243 |
uster | -0.232 |
Token | toys |
Token ID | 14958 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ocolate | +0.021 |
loe | +0.020 |
' | +0.019 |
ird | +0.019 |
tted | +0.018 |
Neg logit contributions | |
blurry | -0.021 |
lands | -0.018 |
nam | -0.018 |
wil | -0.018 |
prett | -0.017 |
Token | on |
Token ID | 319 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ocolate | +0.067 |
loe | +0.066 |
ird | +0.059 |
' | +0.058 |
uster | +0.057 |
Neg logit contributions | |
blurry | -0.074 |
nam | -0.068 |
wil | -0.064 |
lands | -0.062 |
ateful | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | -9.64e-03 |
Pos logit contributions | |
blurry | +0.013 |
nam | +0.012 |
lands | +0.011 |
ateful | +0.011 |
wil | +0.011 |
Neg logit contributions | |
ocolate | -0.019 |
loe | -0.019 |
ird | -0.019 |
tted | -0.018 |
uster | -0.018 |
Token | floor |
Token ID | 4314 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
blurry | +0.001 |
nam | +0.001 |
wil | +0.001 |
prett | +0.001 |
lands | +0.001 |
Neg logit contributions | |
ocolate | -0.001 |
loe | -0.001 |
ird | -0.001 |
' | -0.001 |
tted | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
ocolate | +0.009 |
loe | +0.009 |
' | +0.009 |
ird | +0.009 |
uster | +0.009 |
Neg logit contributions | |
blurry | -0.012 |
nam | -0.012 |
ateful | -0.011 |
flashes | -0.010 |
wil | -0.010 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
loe | +0.017 |
' | +0.017 |
ocolate | +0.016 |
ird | +0.016 |
tted | +0.015 |
Neg logit contributions | |
blurry | -0.026 |
nam | -0.025 |
cks | -0.023 |
ateful | -0.023 |
prett | -0.023 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ocolate | +0.012 |
' | +0.012 |
loe | +0.011 |
of | +0.011 |
adult | +0.011 |
Neg logit contributions | |
blurry | -0.020 |
cks | -0.018 |
nam | -0.018 |
wil | -0.018 |
ateful | -0.018 |
Token | make |
Token ID | 787 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
loe | +0.093 |
ocolate | +0.093 |
ird | +0.086 |
uster | +0.084 |
tted | +0.083 |
Neg logit contributions | |
blurry | -0.088 |
nam | -0.084 |
prett | -0.076 |
lands | -0.076 |
ateful | -0.072 |
Token | - |
Token ID | 12 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
blurry | +0.045 |
nam | +0.041 |
wil | +0.038 |
lands | +0.037 |
ateful | +0.037 |
Neg logit contributions | |
ocolate | -0.051 |
loe | -0.051 |
' | -0.049 |
ird | -0.048 |
tted | -0.046 |
Token | bel |
Token ID | 6667 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
blurry | +0.017 |
nam | +0.014 |
wil | +0.014 |
cks | +0.013 |
lands | +0.013 |
Neg logit contributions | |
ocolate | -0.033 |
' | -0.033 |
tted | -0.032 |
loe | -0.032 |
ird | -0.032 |
Token | ieve |
Token ID | 12311 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
blurry | +0.289 |
nam | +0.275 |
ateful | +0.248 |
cks | +0.244 |
prett | +0.243 |
Neg logit contributions | |
ocolate | -0.328 |
loe | -0.322 |
' | -0.308 |
ird | -0.302 |
uster | -0.296 |
Token | with |
Token ID | 351 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
blurry | +0.046 |
nam | +0.043 |
wil | +0.040 |
ateful | +0.039 |
cks | +0.039 |
Neg logit contributions | |
ocolate | -0.037 |
loe | -0.037 |
' | -0.036 |
ird | -0.035 |
tted | -0.033 |
Token | his |
Token ID | 465 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
blurry | +0.005 |
nam | +0.004 |
wil | +0.004 |
ateful | +0.004 |
cks | +0.004 |
Neg logit contributions | |
ocolate | -0.005 |
loe | -0.005 |
ird | -0.005 |
' | -0.005 |
uster | -0.005 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
blurry | +0.038 |
nam | +0.036 |
wil | +0.033 |
prett | +0.033 |
lands | +0.033 |
Neg logit contributions | |
ocolate | -0.031 |
loe | -0.031 |
' | -0.029 |
ird | -0.029 |
tted | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ocolate | +0.065 |
loe | +0.064 |
' | +0.063 |
ird | +0.061 |
tted | +0.058 |
Neg logit contributions | |
blurry | -0.075 |
nam | -0.070 |
wil | -0.065 |
ateful | -0.064 |
lands | -0.063 |
Token | big |
Token ID | 1263 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
ocolate | +0.028 |
loe | +0.028 |
' | +0.027 |
ird | +0.027 |
tted | +0.026 |
Neg logit contributions | |
blurry | -0.027 |
nam | -0.025 |
wil | -0.023 |
ateful | -0.023 |
lands | -0.023 |
Token | smile |
Token ID | 8212 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
loe | +0.070 |
ocolate | +0.070 |
ird | +0.067 |
tted | +0.066 |
' | +0.064 |
Neg logit contributions | |
blurry | -0.047 |
wil | -0.040 |
nam | -0.038 |
lands | -0.038 |
flashes | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +9.54e-02 |
Pos logit contributions | |
blurry | +0.104 |
nam | +0.097 |
wil | +0.092 |
lands | +0.090 |
ateful | +0.089 |
Neg logit contributions | |
ocolate | -0.074 |
loe | -0.073 |
' | -0.067 |
ird | -0.067 |
tted | -0.065 |
Token | making |
Token ID | 1642 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
' | +0.004 |
ocolate | +0.004 |
of | +0.004 |
tted | +0.004 |
loe | +0.004 |
Neg logit contributions | |
blurry | -0.007 |
ateful | -0.007 |
nam | -0.007 |
lands | -0.007 |
cks | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
ocolate | +0.043 |
of | +0.043 |
loe | +0.042 |
' | +0.040 |
other | +0.040 |
Neg logit contributions | |
nam | -0.065 |
blurry | -0.065 |
ateful | -0.058 |
wil | -0.057 |
cks | -0.055 |
Token | ( |
Token ID | 357 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
' | +0.021 |
ocolate | +0.020 |
of | +0.020 |
ay | +0.019 |
tted | +0.019 |
Neg logit contributions | |
nam | -0.031 |
ateful | -0.029 |
cks | -0.028 |
blurry | -0.028 |
rings | -0.027 |
Token | p |
Token ID | 79 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
blurry | +0.343 |
nam | +0.321 |
wil | +0.299 |
ateful | +0.293 |
lands | +0.292 |
Neg logit contributions | |
ocolate | -0.274 |
loe | -0.267 |
' | -0.257 |
ird | -0.252 |
tted | -0.245 |
Token | onding |
Token ID | 42703 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
ocolate | +0.012 |
loe | +0.012 |
' | +0.011 |
ird | +0.011 |
tted | +0.010 |
Neg logit contributions | |
blurry | -0.015 |
nam | -0.015 |
wil | -0.013 |
ateful | -0.013 |
prett | -0.013 |
Token | ) |
Token ID | 8 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ocolate | +0.031 |
loe | +0.030 |
ird | +0.029 |
kids | +0.029 |
innie | +0.026 |
Neg logit contributions | |
blurry | -0.044 |
wil | -0.041 |
lands | -0.038 |
ateful | -0.037 |
cks | -0.037 |
Token | noise |
Token ID | 7838 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
blurry | +0.133 |
nam | +0.126 |
wil | +0.117 |
ateful | +0.116 |
lands | +0.115 |
Neg logit contributions | |
ocolate | -0.084 |
loe | -0.081 |
' | -0.079 |
ird | -0.076 |
tted | -0.073 |
Token | of |
Token ID | 286 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
blurry | +0.142 |
nam | +0.135 |
wil | +0.126 |
ateful | +0.124 |
lands | +0.123 |
Neg logit contributions | |
ocolate | -0.092 |
loe | -0.090 |
' | -0.086 |
ird | -0.084 |
tted | -0.080 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
loe | +0.028 |
' | +0.028 |
ocolate | +0.027 |
ird | +0.026 |
tted | +0.024 |
Neg logit contributions | |
blurry | -0.041 |
nam | -0.039 |
ateful | -0.036 |
wil | -0.036 |
cks | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ocolate | +0.017 |
loe | +0.015 |
' | +0.015 |
of | +0.014 |
ird | +0.014 |
Neg logit contributions | |
blurry | -0.025 |
nam | -0.023 |
cks | -0.022 |
ateful | -0.022 |
wil | -0.022 |
Token | play |
Token ID | 711 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
blurry | +0.016 |
nam | +0.015 |
wil | +0.014 |
ateful | +0.014 |
lands | +0.014 |
Neg logit contributions | |
ocolate | -0.016 |
loe | -0.016 |
' | -0.015 |
ird | -0.015 |
tted | -0.014 |
Token | make |
Token ID | 787 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
blurry | +0.013 |
nam | +0.012 |
wil | +0.011 |
lands | +0.011 |
prett | +0.011 |
Neg logit contributions | |
ocolate | -0.012 |
loe | -0.011 |
' | -0.011 |
ird | -0.011 |
tted | -0.010 |
Token | - |
Token ID | 12 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
blurry | +0.041 |
nam | +0.039 |
wil | +0.036 |
ateful | +0.035 |
cks | +0.034 |
Neg logit contributions | |
ocolate | -0.047 |
loe | -0.046 |
' | -0.045 |
ird | -0.044 |
ay | -0.042 |
Token | bel |
Token ID | 6667 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
blurry | +0.011 |
nam | +0.010 |
wil | +0.009 |
ateful | +0.009 |
cks | +0.009 |
Neg logit contributions | |
ocolate | -0.015 |
' | -0.015 |
loe | -0.015 |
ird | -0.015 |
tted | -0.015 |
Token | ieve |
Token ID | 12311 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
blurry | +0.303 |
nam | +0.283 |
wil | +0.260 |
ateful | +0.255 |
lands | +0.253 |
Neg logit contributions | |
ocolate | -0.308 |
loe | -0.303 |
' | -0.292 |
ird | -0.287 |
tted | -0.277 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
blurry | +0.039 |
nam | +0.037 |
wil | +0.035 |
cks | +0.035 |
ateful | +0.034 |
Neg logit contributions | |
' | -0.027 |
loe | -0.026 |
ocolate | -0.026 |
of | -0.026 |
ird | -0.025 |
Token | Today |
Token ID | 6288 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ocolate | +0.013 |
loe | +0.012 |
' | +0.012 |
ird | +0.011 |
tted | +0.011 |
Neg logit contributions | |
blurry | -0.019 |
nam | -0.018 |
wil | -0.016 |
prett | -0.016 |
ateful | -0.016 |
Token | she |
Token ID | 673 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
ocolate | +0.076 |
loe | +0.075 |
' | +0.071 |
ird | +0.069 |
tted | +0.065 |
Neg logit contributions | |
blurry | -0.142 |
nam | -0.135 |
wil | -0.127 |
ateful | -0.126 |
cks | -0.125 |
Token | was |
Token ID | 373 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
blurry | +0.035 |
nam | +0.033 |
wil | +0.031 |
ateful | +0.030 |
lands | +0.030 |
Neg logit contributions | |
ocolate | -0.033 |
loe | -0.032 |
' | -0.031 |
ird | -0.030 |
tted | -0.029 |
Token | canned |
Token ID | 32530 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
' | +0.007 |
ird | +0.007 |
of | +0.006 |
Neg logit contributions | |
blurry | -0.008 |
nam | -0.008 |
ateful | -0.007 |
cks | -0.007 |
wil | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
loe | +0.080 |
ocolate | +0.079 |
ird | +0.072 |
uster | +0.070 |
tted | +0.070 |
Neg logit contributions | |
blurry | -0.070 |
nam | -0.064 |
lands | -0.063 |
prett | -0.060 |
wil | -0.060 |
Token | jar |
Token ID | 17379 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
' | +0.007 |
ird | +0.007 |
tted | +0.007 |
Neg logit contributions | |
blurry | -0.009 |
nam | -0.008 |
ateful | -0.008 |
wil | -0.008 |
cks | -0.008 |
Token | red |
Token ID | 445 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
blurry | +0.002 |
nam | +0.002 |
wil | +0.002 |
prett | +0.002 |
lands | +0.002 |
Neg logit contributions | |
ocolate | -0.002 |
loe | -0.002 |
ird | -0.002 |
' | -0.002 |
uster | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
blurry | +0.022 |
nam | +0.020 |
wil | +0.019 |
ateful | +0.018 |
lands | +0.018 |
Neg logit contributions | |
ocolate | -0.020 |
loe | -0.020 |
' | -0.019 |
ird | -0.019 |
tted | -0.018 |
Token | bottled |
Token ID | 34123 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
' | +0.007 |
ird | +0.007 |
tted | +0.006 |
Neg logit contributions | |
blurry | -0.009 |
nam | -0.008 |
ateful | -0.007 |
cks | -0.007 |
wil | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
blurry | +0.295 |
nam | +0.275 |
ateful | +0.254 |
wil | +0.254 |
prett | +0.242 |
Neg logit contributions | |
ocolate | -0.304 |
loe | -0.299 |
' | -0.296 |
ird | -0.279 |
ay | -0.271 |
Token | vacuum |
Token ID | 17076 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
' | +0.007 |
ird | +0.007 |
tted | +0.006 |
Neg logit contributions | |
blurry | -0.008 |
nam | -0.007 |
ateful | -0.007 |
wil | -0.007 |
cks | -0.007 |
Token | - |
Token ID | 12 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
ocolate | +0.085 |
loe | +0.082 |
' | +0.078 |
ird | +0.077 |
tted | +0.072 |
Neg logit contributions | |
blurry | -0.124 |
nam | -0.116 |
wil | -0.109 |
lands | -0.108 |
ateful | -0.107 |
Token | se |
Token ID | 325 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
blurry | +0.027 |
nam | +0.025 |
wil | +0.023 |
lands | +0.023 |
ateful | +0.023 |
Neg logit contributions | |
ocolate | -0.028 |
loe | -0.027 |
' | -0.026 |
ird | -0.026 |
uster | -0.024 |
Token | aled |
Token ID | 3021 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
blurry | +0.031 |
nam | +0.028 |
wil | +0.028 |
lands | +0.028 |
cks | +0.027 |
Neg logit contributions | |
ocolate | -0.027 |
loe | -0.026 |
ird | -0.023 |
' | -0.023 |
ay | -0.023 |
Token | He |
Token ID | 679 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ocolate | +0.009 |
loe | +0.009 |
' | +0.009 |
ird | +0.008 |
tted | +0.008 |
Neg logit contributions | |
nam | -0.010 |
blurry | -0.010 |
prett | -0.008 |
lands | -0.008 |
ateful | -0.008 |
Token | would |
Token ID | 561 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
loe | +0.021 |
ocolate | +0.021 |
' | +0.020 |
ird | +0.020 |
tted | +0.019 |
Neg logit contributions | |
blurry | -0.023 |
nam | -0.022 |
wil | -0.020 |
ateful | -0.020 |
cks | -0.019 |
Token | race |
Token ID | 3234 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ocolate | +0.030 |
loe | +0.029 |
' | +0.029 |
ird | +0.027 |
tted | +0.026 |
Neg logit contributions | |
blurry | -0.036 |
nam | -0.034 |
ateful | -0.032 |
wil | -0.032 |
cks | -0.031 |
Token | make |
Token ID | 787 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
blurry | +0.012 |
nam | +0.012 |
wil | +0.011 |
ateful | +0.011 |
cks | +0.011 |
Neg logit contributions | |
ocolate | -0.010 |
loe | -0.010 |
' | -0.010 |
tted | -0.009 |
of | -0.009 |
Token | - |
Token ID | 12 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
blurry | +0.048 |
nam | +0.045 |
wil | +0.042 |
ateful | +0.041 |
cks | +0.040 |
Neg logit contributions | |
ocolate | -0.051 |
loe | -0.051 |
' | -0.049 |
ird | -0.048 |
tted | -0.047 |
Token | bel |
Token ID | 6667 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
blurry | +0.014 |
nam | +0.012 |
wil | +0.011 |
ateful | +0.011 |
cks | +0.011 |
Neg logit contributions | |
ocolate | -0.020 |
' | -0.020 |
loe | -0.019 |
tted | -0.019 |
ird | -0.019 |
Token | ieve |
Token ID | 12311 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
blurry | +0.273 |
nam | +0.259 |
ateful | +0.234 |
cks | +0.233 |
lands | +0.228 |
Neg logit contributions | |
ocolate | -0.322 |
loe | -0.315 |
' | -0.302 |
ird | -0.294 |
uster | -0.292 |
Token | cars |
Token ID | 5006 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
blurry | +0.042 |
nam | +0.040 |
wil | +0.037 |
lands | +0.037 |
ateful | +0.036 |
Neg logit contributions | |
ocolate | -0.033 |
loe | -0.032 |
' | -0.030 |
ird | -0.030 |
tted | -0.029 |
Token | around |
Token ID | 1088 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
blurry | +0.016 |
nam | +0.015 |
wil | +0.014 |
lands | +0.014 |
ateful | +0.014 |
Neg logit contributions | |
ocolate | -0.010 |
loe | -0.010 |
' | -0.009 |
ird | -0.009 |
tted | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
blurry | +0.026 |
nam | +0.024 |
lands | +0.022 |
wil | +0.022 |
ateful | +0.021 |
Neg logit contributions | |
ocolate | -0.032 |
loe | -0.032 |
ird | -0.031 |
' | -0.030 |
tted | -0.029 |
Token | track |
Token ID | 2610 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
blurry | +0.001 |
nam | +0.001 |
lands | +0.001 |
prett | +0.001 |
wil | +0.001 |
Neg logit contributions | |
ocolate | -0.001 |
loe | -0.001 |
ird | -0.001 |
uster | -0.001 |
' | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
blurry | +0.065 |
nam | +0.059 |
wil | +0.055 |
cks | +0.055 |
ateful | +0.054 |
Neg logit contributions | |
ocolate | -0.068 |
loe | -0.067 |
' | -0.066 |
ird | -0.064 |
of | -0.060 |
Token | baseball |
Token ID | 9283 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ocolate | +0.001 |
loe | +0.001 |
' | +0.001 |
ird | +0.001 |
tted | +0.001 |
Neg logit contributions | |
blurry | -0.001 |
nam | -0.001 |
wil | -0.001 |
ateful | -0.001 |
lands | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
blurry | +0.018 |
nam | +0.017 |
wil | +0.016 |
ateful | +0.015 |
lands | +0.015 |
Neg logit contributions | |
ocolate | -0.014 |
loe | -0.014 |
' | -0.013 |
ird | -0.013 |
tted | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.006 |
' | +0.006 |
ird | +0.006 |
tted | +0.006 |
Neg logit contributions | |
blurry | -0.008 |
nam | -0.007 |
wil | -0.007 |
ateful | -0.007 |
lands | -0.007 |
Token | pitcher |
Token ID | 18086 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
blurry | +0.003 |
nam | +0.002 |
prett | +0.002 |
lands | +0.002 |
wil | +0.002 |
Neg logit contributions | |
loe | -0.002 |
ocolate | -0.002 |
ird | -0.002 |
' | -0.002 |
uster | -0.002 |
Token | ( |
Token ID | 357 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
ocolate | +0.037 |
loe | +0.037 |
ird | +0.034 |
uster | +0.033 |
' | +0.032 |
Neg logit contributions | |
blurry | -0.046 |
nam | -0.041 |
wil | -0.041 |
lands | -0.040 |
prett | -0.039 |
Token | who |
Token ID | 8727 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
blurry | +0.330 |
nam | +0.309 |
wil | +0.289 |
ateful | +0.283 |
lands | +0.282 |
Neg logit contributions | |
ocolate | -0.256 |
loe | -0.251 |
' | -0.240 |
ird | -0.235 |
tted | -0.227 |
Token | was |
Token ID | 373 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
blurry | +0.140 |
nam | +0.129 |
wil | +0.123 |
ateful | +0.121 |
lands | +0.120 |
Neg logit contributions | |
ocolate | -0.141 |
loe | -0.138 |
uster | -0.125 |
' | -0.124 |
ird | -0.122 |
Token | throwing |
Token ID | 9644 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ocolate | +0.020 |
' | +0.019 |
loe | +0.019 |
ird | +0.018 |
tted | +0.018 |
Neg logit contributions | |
blurry | -0.021 |
nam | -0.019 |
wil | -0.018 |
ateful | -0.018 |
prett | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
ocolate | +0.028 |
loe | +0.027 |
' | +0.027 |
ird | +0.026 |
tted | +0.025 |
Neg logit contributions | |
blurry | -0.025 |
nam | -0.023 |
wil | -0.022 |
ateful | -0.021 |
cks | -0.021 |
Token | ball |
Token ID | 2613 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
blurry | +0.003 |
prett | +0.002 |
nam | +0.002 |
lands | +0.002 |
wil | +0.002 |
Neg logit contributions | |
loe | -0.003 |
ocolate | -0.003 |
ird | -0.003 |
innie | -0.003 |
kids | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
ocolate | +0.020 |
loe | +0.018 |
ird | +0.017 |
tted | +0.015 |
' | +0.014 |
Neg logit contributions | |
blurry | -0.047 |
nam | -0.043 |
lands | -0.042 |
ateful | -0.042 |
wil | -0.042 |
Token | how |
Token ID | 703 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
ocolate | +0.037 |
loe | +0.037 |
' | +0.036 |
ird | +0.035 |
tted | +0.034 |
Neg logit contributions | |
blurry | -0.030 |
nam | -0.027 |
wil | -0.025 |
ateful | -0.024 |
lands | -0.024 |
Token | our |
Token ID | 674 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
blurry | +0.002 |
nam | +0.002 |
cks | +0.002 |
wil | +0.002 |
prett | +0.002 |
Neg logit contributions | |
' | -0.002 |
of | -0.002 |
loe | -0.002 |
ocolate | -0.002 |
tted | -0.002 |
Token | decisions |
Token ID | 5370 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
' | +0.093 |
ocolate | +0.086 |
loe | +0.084 |
other | +0.081 |
adult | +0.080 |
Neg logit contributions | |
blurry | -0.106 |
nam | -0.098 |
cks | -0.090 |
wil | -0.089 |
ateful | -0.088 |
Token | might |
Token ID | 1244 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
blurry | +0.047 |
nam | +0.044 |
wil | +0.041 |
lands | +0.040 |
ateful | +0.040 |
Neg logit contributions | |
ocolate | -0.040 |
loe | -0.040 |
ird | -0.037 |
' | -0.037 |
tted | -0.035 |
Token | affect |
Token ID | 2689 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
ocolate | +0.022 |
' | +0.021 |
loe | +0.021 |
ird | +0.020 |
tted | +0.019 |
Neg logit contributions | |
blurry | -0.025 |
nam | -0.024 |
ateful | -0.022 |
wil | -0.022 |
cks | -0.021 |
Token | them |
Token ID | 606 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
blurry | +0.296 |
nam | +0.276 |
wil | +0.256 |
ateful | +0.246 |
prett | +0.245 |
Neg logit contributions | |
ocolate | -0.281 |
loe | -0.280 |
' | -0.278 |
ird | -0.262 |
tted | -0.250 |
Token | . |
Token ID | 13 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
' | +0.078 |
ocolate | +0.077 |
loe | +0.074 |
ird | +0.072 |
tted | +0.069 |
Neg logit contributions | |
blurry | -0.102 |
nam | -0.096 |
wil | -0.090 |
ateful | -0.088 |
cks | -0.088 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
nam | +0.002 |
blurry | +0.002 |
ateful | +0.002 |
ric | +0.002 |
cks | +0.002 |
Neg logit contributions | |
ocolate | -0.002 |
loe | -0.002 |
tted | -0.002 |
ird | -0.002 |
affle | -0.002 |
Token | Once |
Token ID | 7454 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
lands | +0.067 |
blurry | +0.061 |
flashes | +0.053 |
cks | +0.051 |
nam | +0.051 |
Neg logit contributions | |
ocolate | -0.137 |
uster | -0.131 |
ird | -0.128 |
loe | -0.126 |
adult | -0.126 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
blurry | +0.020 |
nam | +0.018 |
wil | +0.017 |
ateful | +0.017 |
lands | +0.017 |
Neg logit contributions | |
ocolate | -0.020 |
loe | -0.020 |
' | -0.019 |
ird | -0.019 |
tted | -0.018 |
Token | before |
Token ID | 878 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
ocolate | +0.212 |
loe | +0.211 |
ird | +0.197 |
tted | +0.195 |
uster | +0.187 |
Neg logit contributions | |
blurry | -0.213 |
nam | -0.205 |
ateful | -0.185 |
lands | -0.180 |
prett | -0.179 |
Token | doing |
Token ID | 1804 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
ocolate | +0.041 |
loe | +0.040 |
' | +0.040 |
ird | +0.038 |
tted | +0.035 |
Neg logit contributions | |
blurry | -0.046 |
nam | -0.043 |
wil | -0.039 |
prett | -0.039 |
ateful | -0.039 |
Token | something |
Token ID | 1223 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
' | +0.032 |
ocolate | +0.031 |
loe | +0.029 |
of | +0.029 |
ird | +0.029 |
Neg logit contributions | |
blurry | -0.032 |
wil | -0.032 |
nam | -0.032 |
cks | -0.028 |
fly | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
blurry | +0.033 |
nam | +0.033 |
ateful | +0.030 |
wil | +0.030 |
cks | +0.030 |
Neg logit contributions | |
' | -0.026 |
of | -0.025 |
ocolate | -0.023 |
loe | -0.023 |
ird | -0.023 |
Token | might |
Token ID | 1244 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
blurry | +0.073 |
nam | +0.071 |
cks | +0.064 |
ateful | +0.064 |
wil | +0.063 |
Neg logit contributions | |
' | -0.060 |
of | -0.057 |
ocolate | -0.055 |
ird | -0.053 |
loe | -0.052 |
Token | affect |
Token ID | 2689 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
' | +0.019 |
ocolate | +0.019 |
of | +0.018 |
ird | +0.017 |
loe | +0.017 |
Neg logit contributions | |
nam | -0.026 |
blurry | -0.026 |
ateful | -0.024 |
cks | -0.024 |
lands | -0.023 |
Token | others |
Token ID | 1854 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
blurry | +0.309 |
nam | +0.294 |
wil | +0.272 |
ateful | +0.260 |
prett | +0.259 |
Neg logit contributions | |
' | -0.264 |
loe | -0.261 |
ocolate | -0.257 |
ird | -0.242 |
of | -0.238 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
blurry | +0.054 |
nam | +0.051 |
wil | +0.048 |
ateful | +0.046 |
prett | +0.046 |
Neg logit contributions | |
' | -0.041 |
ocolate | -0.041 |
loe | -0.040 |
ird | -0.038 |
tted | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
blurry | +0.011 |
nam | +0.010 |
wil | +0.009 |
cks | +0.009 |
ateful | +0.009 |
Neg logit contributions | |
loe | -0.005 |
ocolate | -0.005 |
' | -0.004 |
ird | -0.004 |
ay | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ocolate | +0.009 |
loe | +0.008 |
ird | +0.008 |
' | +0.008 |
tted | +0.008 |
Neg logit contributions | |
blurry | -0.012 |
nam | -0.011 |
wil | -0.010 |
lands | -0.010 |
ateful | -0.010 |
Token | From |
Token ID | 4863 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ocolate | +0.011 |
loe | +0.011 |
ird | +0.010 |
' | +0.010 |
uster | +0.010 |
Neg logit contributions | |
blurry | -0.010 |
nam | -0.009 |
wil | -0.008 |
ateful | -0.008 |
prett | -0.008 |
Token | think |
Token ID | 892 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
blurry | +0.006 |
nam | +0.006 |
wil | +0.005 |
lands | +0.005 |
ateful | +0.005 |
Neg logit contributions | |
ocolate | -0.005 |
loe | -0.005 |
' | -0.005 |
ird | -0.005 |
tted | -0.005 |
Token | about |
Token ID | 546 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
ocolate | +0.015 |
loe | +0.014 |
tted | +0.013 |
ird | +0.013 |
' | +0.013 |
Neg logit contributions | |
blurry | -0.018 |
nam | -0.017 |
lands | -0.015 |
prett | -0.015 |
wil | -0.015 |
Token | how |
Token ID | 703 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
blurry | +0.002 |
nam | +0.002 |
wil | +0.002 |
ateful | +0.002 |
prett | +0.002 |
Neg logit contributions | |
ocolate | -0.002 |
loe | -0.002 |
' | -0.002 |
ird | -0.002 |
of | -0.002 |
Token | my |
Token ID | 616 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
blurry | +0.003 |
nam | +0.003 |
wil | +0.003 |
cks | +0.003 |
prett | +0.003 |
Neg logit contributions | |
' | -0.003 |
ocolate | -0.003 |
loe | -0.003 |
of | -0.002 |
ird | -0.002 |
Token | decisions |
Token ID | 5370 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
ocolate | +0.047 |
' | +0.046 |
loe | +0.046 |
ird | +0.044 |
tted | +0.042 |
Neg logit contributions | |
blurry | -0.057 |
nam | -0.053 |
wil | -0.049 |
cks | -0.049 |
ateful | -0.049 |
Token | affect |
Token ID | 2689 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
blurry | +0.045 |
nam | +0.041 |
wil | +0.039 |
lands | +0.038 |
ateful | +0.038 |
Neg logit contributions | |
ocolate | -0.039 |
loe | -0.039 |
' | -0.036 |
ird | -0.036 |
uster | -0.035 |
Token | our |
Token ID | 674 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
blurry | +0.251 |
nam | +0.234 |
lands | +0.212 |
wil | +0.211 |
ateful | +0.211 |
Neg logit contributions | |
ocolate | -0.323 |
loe | -0.315 |
ird | -0.303 |
' | -0.297 |
tted | -0.297 |
Token | nation |
Token ID | 3277 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
' | +0.098 |
ocolate | +0.094 |
loe | +0.093 |
other | +0.088 |
ay | +0.087 |
Neg logit contributions | |
blurry | -0.099 |
nam | -0.096 |
cks | -0.084 |
wil | -0.082 |
prett | -0.081 |
Token | ." |
Token ID | 526 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
blurry | +0.069 |
nam | +0.065 |
wil | +0.060 |
ateful | +0.059 |
lands | +0.059 |
Neg logit contributions | |
ocolate | -0.050 |
loe | -0.049 |
' | -0.046 |
ird | -0.045 |
tted | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ocolate | +0.044 |
loe | +0.043 |
ird | +0.040 |
' | +0.040 |
tted | +0.038 |
Neg logit contributions | |
nam | -0.058 |
blurry | -0.058 |
lands | -0.053 |
prett | -0.052 |
cks | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ocolate | +0.014 |
loe | +0.013 |
ird | +0.013 |
uster | +0.013 |
' | +0.012 |
Neg logit contributions | |
blurry | -0.013 |
nam | -0.012 |
lands | -0.012 |
cks | -0.012 |
wil | -0.012 |
Token | ? |
Token ID | 30 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ocolate | +0.122 |
loe | +0.121 |
' | +0.112 |
tted | +0.112 |
ird | +0.111 |
Neg logit contributions | |
blurry | -0.118 |
nam | -0.111 |
lands | -0.101 |
wil | -0.100 |
ateful | -0.100 |
Token | You |
Token ID | 921 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
nam | +0.080 |
blurry | +0.076 |
ateful | +0.069 |
cks | +0.068 |
rings | +0.067 |
Neg logit contributions | |
ocolate | -0.074 |
loe | -0.072 |
tted | -0.067 |
uster | -0.067 |
' | -0.067 |
Token | can |
Token ID | 460 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
ocolate | +0.065 |
loe | +0.062 |
uster | +0.056 |
rd | +0.055 |
kids | +0.054 |
Neg logit contributions | |
blurry | -0.060 |
nam | -0.057 |
prett | -0.052 |
lands | -0.051 |
wil | -0.051 |
Token | be |
Token ID | 307 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
blurry | +0.039 |
nam | +0.036 |
lands | +0.034 |
prett | +0.033 |
cks | +0.033 |
Neg logit contributions | |
ocolate | -0.039 |
loe | -0.038 |
uster | -0.036 |
tted | -0.035 |
ird | -0.035 |
Token | my |
Token ID | 616 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
blurry | +0.017 |
wil | +0.015 |
nam | +0.015 |
ateful | +0.015 |
flashes | +0.014 |
Neg logit contributions | |
' | -0.012 |
ird | -0.012 |
ocolate | -0.012 |
loe | -0.012 |
of | -0.011 |
Token | helpers |
Token ID | 49385 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ocolate | +0.041 |
loe | +0.041 |
' | +0.039 |
ird | +0.038 |
tted | +0.036 |
Neg logit contributions | |
blurry | -0.066 |
nam | -0.063 |
wil | -0.059 |
ateful | -0.058 |
lands | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
ocolate | +0.160 |
loe | +0.157 |
tted | +0.144 |
uster | +0.141 |
ird | +0.140 |
Neg logit contributions | |
blurry | -0.182 |
nam | -0.172 |
ateful | -0.158 |
prett | -0.158 |
lands | -0.156 |
Token | You |
Token ID | 921 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
nam | +0.011 |
blurry | +0.010 |
ateful | +0.009 |
prett | +0.009 |
flashes | +0.009 |
Neg logit contributions | |
ocolate | -0.010 |
loe | -0.010 |
ve | -0.010 |
tted | -0.010 |
' | -0.010 |
Token | can |
Token ID | 460 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
ocolate | +0.066 |
loe | +0.063 |
uster | +0.057 |
rd | +0.056 |
' | +0.055 |
Neg logit contributions | |
blurry | -0.058 |
nam | -0.056 |
prett | -0.051 |
lands | -0.049 |
wil | -0.049 |
Token | say |
Token ID | 910 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
blurry | +0.039 |
nam | +0.036 |
lands | +0.033 |
prett | +0.033 |
wil | +0.033 |
Neg logit contributions | |
ocolate | -0.038 |
loe | -0.037 |
uster | -0.034 |
' | -0.034 |
ird | -0.034 |
Token | hello |
Token ID | 23748 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ocolate | +0.018 |
loe | +0.018 |
' | +0.017 |
ird | +0.017 |
tted | +0.016 |
Neg logit contributions | |
blurry | -0.020 |
nam | -0.019 |
wil | -0.017 |
ateful | -0.017 |
lands | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ocolate | +0.056 |
loe | +0.055 |
uster | +0.051 |
tted | +0.050 |
ird | +0.049 |
Neg logit contributions | |
blurry | -0.053 |
nam | -0.048 |
lands | -0.046 |
wil | -0.045 |
ateful | -0.045 |
Token | Go |
Token ID | 1514 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
blurry | +0.010 |
nam | +0.010 |
ateful | +0.009 |
cks | +0.009 |
flashes | +0.009 |
Neg logit contributions | |
ocolate | -0.009 |
' | -0.008 |
loe | -0.008 |
ird | -0.008 |
tted | -0.008 |
Token | away |
Token ID | 1497 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
ocolate | +0.117 |
loe | +0.115 |
ird | +0.109 |
' | +0.105 |
uster | +0.104 |
Neg logit contributions | |
blurry | -0.055 |
nam | -0.047 |
lands | -0.045 |
wil | -0.043 |
ateful | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
ocolate | +0.020 |
loe | +0.020 |
' | +0.018 |
ird | +0.018 |
tted | +0.017 |
Neg logit contributions | |
blurry | -0.038 |
nam | -0.036 |
lands | -0.034 |
wil | -0.034 |
ateful | -0.034 |
Token | leave |
Token ID | 2666 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
blurry | +0.002 |
nam | +0.002 |
cks | +0.002 |
ateful | +0.002 |
wil | +0.002 |
Neg logit contributions | |
' | -0.001 |
loe | -0.001 |
ird | -0.001 |
ocolate | -0.001 |
of | -0.001 |
Token | us |
Token ID | 514 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ocolate | +0.086 |
loe | +0.083 |
ird | +0.082 |
' | +0.080 |
tted | +0.079 |
Neg logit contributions | |
blurry | -0.076 |
nam | -0.071 |
lands | -0.068 |
cks | -0.064 |
wil | -0.063 |
Token | alone |
Token ID | 3436 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
ocolate | +0.215 |
loe | +0.212 |
' | +0.205 |
ird | +0.202 |
tted | +0.196 |
Neg logit contributions | |
blurry | -0.155 |
nam | -0.143 |
wil | -0.130 |
ateful | -0.127 |
lands | -0.125 |
Token | ." |
Token ID | 526 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
blurry | +0.029 |
nam | +0.025 |
lands | +0.025 |
ateful | +0.024 |
wil | +0.024 |
Neg logit contributions | |
ocolate | -0.031 |
loe | -0.031 |
ird | -0.028 |
uster | -0.028 |
tted | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
loe | +0.038 |
ocolate | +0.038 |
' | +0.035 |
ird | +0.033 |
ay | +0.031 |
Neg logit contributions | |
blurry | -0.081 |
nam | -0.076 |
wil | -0.074 |
prett | -0.071 |
ateful | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
' | +0.007 |
ird | +0.007 |
tted | +0.006 |
Neg logit contributions | |
blurry | -0.013 |
nam | -0.012 |
wil | -0.011 |
ateful | -0.011 |
lands | -0.011 |
Token | Mark |
Token ID | 9704 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
loe | +0.007 |
' | +0.007 |
ocolate | +0.007 |
tted | +0.006 |
ird | +0.006 |
Neg logit contributions | |
blurry | -0.013 |
nam | -0.013 |
wil | -0.012 |
prett | -0.012 |
ateful | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
blurry | +0.041 |
nam | +0.038 |
cks | +0.037 |
ateful | +0.036 |
wil | +0.036 |
Neg logit contributions | |
ocolate | -0.029 |
loe | -0.029 |
' | -0.029 |
ird | -0.028 |
ay | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
blurry | +0.019 |
nam | +0.018 |
wil | +0.016 |
prett | +0.016 |
lands | +0.016 |
Neg logit contributions | |
ocolate | -0.018 |
loe | -0.018 |
' | -0.017 |
ird | -0.016 |
tted | -0.016 |
Token | He |
Token ID | 679 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
blurry | +0.002 |
nam | +0.002 |
ateful | +0.001 |
wil | +0.001 |
prett | +0.001 |
Neg logit contributions | |
ocolate | -0.001 |
loe | -0.001 |
' | -0.001 |
ird | -0.001 |
tted | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ocolate | +0.016 |
loe | +0.016 |
' | +0.015 |
ird | +0.015 |
tted | +0.014 |
Neg logit contributions | |
blurry | -0.015 |
nam | -0.014 |
wil | -0.013 |
lands | -0.012 |
prett | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
ocolate | +0.037 |
loe | +0.035 |
' | +0.034 |
of | +0.034 |
ird | +0.034 |
Neg logit contributions | |
blurry | -0.039 |
nam | -0.035 |
cks | -0.034 |
wil | -0.033 |
ateful | -0.033 |
Token | sitting |
Token ID | 5586 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
blurry | +0.024 |
nam | +0.023 |
cks | +0.022 |
ateful | +0.022 |
wil | +0.021 |
Neg logit contributions | |
ocolate | -0.016 |
' | -0.016 |
loe | -0.016 |
ird | -0.015 |
of | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
ocolate | +0.172 |
loe | +0.169 |
' | +0.161 |
ird | +0.160 |
tted | +0.153 |
Neg logit contributions | |
blurry | -0.181 |
nam | -0.170 |
wil | -0.157 |
ateful | -0.154 |
lands | -0.153 |
Token | the |
Token ID | 262 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
blurry | +0.003 |
nam | +0.002 |
ateful | +0.002 |
cks | +0.002 |
wil | +0.002 |
Neg logit contributions | |
ocolate | -0.003 |
loe | -0.003 |
' | -0.002 |
ird | -0.002 |
of | -0.002 |
Token | park |
Token ID | 3952 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
blurry | +0.005 |
nam | +0.005 |
cks | +0.005 |
ateful | +0.005 |
wil | +0.004 |
Neg logit contributions | |
ocolate | -0.004 |
loe | -0.004 |
' | -0.004 |
tted | -0.004 |
ird | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
blurry | +0.097 |
nam | +0.093 |
wil | +0.087 |
ateful | +0.087 |
cks | +0.086 |
Neg logit contributions | |
ocolate | -0.047 |
loe | -0.045 |
' | -0.044 |
ird | -0.042 |
tted | -0.039 |
Token | looking |
Token ID | 2045 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
' | +0.002 |
ocolate | +0.002 |
of | +0.002 |
loe | +0.002 |
ird | +0.002 |
Neg logit contributions | |
blurry | -0.003 |
ateful | -0.003 |
cks | -0.003 |
nam | -0.003 |
lands | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
blurry | +0.013 |
nam | +0.012 |
wil | +0.011 |
ateful | +0.011 |
lands | +0.011 |
Neg logit contributions | |
ocolate | -0.017 |
loe | -0.017 |
' | -0.016 |
ird | -0.016 |
tted | -0.016 |
Token | screen |
Token ID | 3159 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
blurry | +0.007 |
nam | +0.006 |
lands | +0.006 |
wil | +0.006 |
prett | +0.006 |
Neg logit contributions | |
ocolate | -0.005 |
loe | -0.005 |
ird | -0.005 |
tted | -0.005 |
' | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
blurry | +0.021 |
nam | +0.021 |
wil | +0.019 |
ateful | +0.019 |
prett | +0.019 |
Neg logit contributions | |
ocolate | -0.010 |
' | -0.010 |
loe | -0.010 |
ird | -0.009 |
tted | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
blurry | +0.018 |
nam | +0.017 |
wil | +0.015 |
prett | +0.015 |
ateful | +0.015 |
Neg logit contributions | |
ocolate | -0.013 |
loe | -0.013 |
' | -0.012 |
ird | -0.011 |
ay | -0.011 |
Token | is |
Token ID | 318 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
' | +0.008 |
loe | +0.007 |
of | +0.007 |
ocolate | +0.007 |
ird | +0.006 |
Neg logit contributions | |
nam | -0.010 |
blurry | -0.010 |
ateful | -0.009 |
bel | -0.009 |
prett | -0.008 |
Token | wearing |
Token ID | 5762 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
blurry | +0.053 |
nam | +0.052 |
ateful | +0.051 |
rings | +0.049 |
lands | +0.049 |
Neg logit contributions | |
of | -0.051 |
ocolate | -0.048 |
' | -0.046 |
loe | -0.046 |
ird | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
ocolate | +0.159 |
loe | +0.154 |
' | +0.148 |
ay | +0.146 |
ird | +0.143 |
Neg logit contributions | |
blurry | -0.201 |
ateful | -0.191 |
nam | -0.188 |
cks | -0.184 |
wil | -0.183 |
Token | pretty |
Token ID | 2495 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
' | +0.024 |
ocolate | +0.024 |
loe | +0.023 |
ird | +0.023 |
ay | +0.023 |
Neg logit contributions | |
blurry | -0.023 |
nam | -0.023 |
ateful | -0.022 |
cks | -0.020 |
wil | -0.020 |
Token | dress |
Token ID | 6576 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
blurry | +0.058 |
nam | +0.056 |
ateful | +0.054 |
wil | +0.051 |
cks | +0.051 |
Neg logit contributions | |
ocolate | -0.052 |
loe | -0.051 |
' | -0.051 |
ird | -0.049 |
ay | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
blurry | +0.062 |
nam | +0.059 |
ateful | +0.055 |
wil | +0.055 |
cks | +0.054 |
Neg logit contributions | |
ocolate | -0.039 |
loe | -0.039 |
' | -0.039 |
ird | -0.037 |
tted | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
ird | +0.004 |
ocolate | +0.004 |
of | +0.004 |
loe | +0.004 |
' | +0.004 |
Neg logit contributions | |
blurry | -0.008 |
ateful | -0.008 |
nam | -0.008 |
wil | -0.007 |
cks | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ocolate | +0.052 |
loe | +0.051 |
' | +0.048 |
ird | +0.047 |
tted | +0.046 |
Neg logit contributions | |
blurry | -0.061 |
nam | -0.058 |
wil | -0.054 |
lands | -0.053 |
ateful | -0.052 |
Token | Go |
Token ID | 1514 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
nam | +0.009 |
blurry | +0.009 |
ateful | +0.008 |
flashes | +0.008 |
cks | +0.008 |
Neg logit contributions | |
ocolate | -0.008 |
' | -0.008 |
loe | -0.008 |
tted | -0.008 |
ve | -0.008 |
Token | away |
Token ID | 1497 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
ocolate | +0.120 |
loe | +0.119 |
ird | +0.112 |
' | +0.109 |
uster | +0.108 |
Neg logit contributions | |
blurry | -0.057 |
nam | -0.048 |
lands | -0.047 |
wil | -0.045 |
ateful | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
ocolate | +0.017 |
' | +0.016 |
loe | +0.016 |
ird | +0.015 |
tted | +0.014 |
Neg logit contributions | |
blurry | -0.040 |
nam | -0.039 |
wil | -0.036 |
prett | -0.036 |
cks | -0.036 |
Token | leave |
Token ID | 2666 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
blurry | +0.002 |
ateful | +0.002 |
cks | +0.002 |
nam | +0.002 |
flashes | +0.002 |
Neg logit contributions | |
' | -0.001 |
of | -0.001 |
ocolate | -0.001 |
help | -0.001 |
ird | -0.001 |
Token | us |
Token ID | 514 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
ocolate | +0.093 |
loe | +0.093 |
ird | +0.089 |
' | +0.087 |
tted | +0.087 |
Neg logit contributions | |
blurry | -0.077 |
nam | -0.073 |
lands | -0.068 |
wil | -0.067 |
cks | -0.065 |
Token | alone |
Token ID | 3436 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
ocolate | +0.215 |
loe | +0.211 |
' | +0.208 |
ird | +0.203 |
tted | +0.197 |
Neg logit contributions | |
blurry | -0.154 |
nam | -0.141 |
wil | -0.128 |
ateful | -0.126 |
lands | -0.123 |
Token | ," |
Token ID | 553 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
blurry | +0.033 |
nam | +0.031 |
lands | +0.029 |
wil | +0.029 |
ateful | +0.028 |
Neg logit contributions | |
ocolate | -0.028 |
loe | -0.028 |
ird | -0.025 |
uster | -0.025 |
tted | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
blurry | +0.054 |
ric | +0.049 |
flies | +0.048 |
wil | +0.048 |
cks | +0.047 |
Neg logit contributions | |
' | -0.024 |
of | -0.023 |
ocolate | -0.023 |
loe | -0.019 |
ird | -0.019 |
Token | bird |
Token ID | 6512 |
Feature activation | +3.43e-03 |
Pos logit contributions | |
blurry | +0.010 |
nam | +0.010 |
ateful | +0.009 |
cks | +0.009 |
lands | +0.009 |
Neg logit contributions | |
' | -0.006 |
ocolate | -0.006 |
loe | -0.006 |
ird | -0.006 |
adult | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
' | +0.000 |
of | +0.000 |
ird | +0.000 |
loe | +0.000 |
tted | +0.000 |
Neg logit contributions | |
blurry | -0.000 |
nam | -0.000 |
ateful | -0.000 |
prett | -0.000 |
ric | -0.000 |
Token | gifts |
Token ID | 13201 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ocolate | +0.057 |
loe | +0.056 |
' | +0.053 |
ird | +0.052 |
uster | +0.051 |
Neg logit contributions | |
blurry | -0.056 |
nam | -0.052 |
prett | -0.048 |
lands | -0.047 |
ateful | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ocolate | +0.115 |
loe | +0.113 |
' | +0.107 |
ird | +0.105 |
tted | +0.101 |
Neg logit contributions | |
blurry | -0.148 |
nam | -0.140 |
wil | -0.130 |
ateful | -0.128 |
lands | -0.127 |
Token | Love |
Token ID | 5896 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
blurry | +0.014 |
nam | +0.014 |
prett | +0.012 |
ateful | +0.012 |
flashes | +0.012 |
Neg logit contributions | |
ocolate | -0.014 |
loe | -0.014 |
' | -0.013 |
tted | -0.013 |
ird | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
blurry | +0.040 |
nam | +0.038 |
lands | +0.036 |
wil | +0.036 |
ateful | +0.036 |
Neg logit contributions | |
ocolate | -0.022 |
loe | -0.021 |
tted | -0.019 |
ird | -0.019 |
uster | -0.019 |
Token | Grand |
Token ID | 5675 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ocolate | +0.004 |
loe | +0.004 |
' | +0.004 |
ird | +0.004 |
tted | +0.004 |
Neg logit contributions | |
blurry | -0.004 |
nam | -0.004 |
wil | -0.004 |
lands | -0.004 |
cks | -0.004 |
Token | ma |
Token ID | 2611 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ocolate | +0.006 |
loe | +0.006 |
tted | +0.006 |
uster | +0.005 |
' | +0.005 |
Neg logit contributions | |
blurry | -0.010 |
nam | -0.010 |
ateful | -0.009 |
wil | -0.009 |
cks | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ocolate | +0.097 |
loe | +0.095 |
tted | +0.087 |
' | +0.086 |
ird | +0.086 |
Neg logit contributions | |
blurry | -0.127 |
nam | -0.118 |
wil | -0.112 |
lands | -0.111 |
prett | -0.110 |
Token | Grand |
Token ID | 5675 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ocolate | +0.001 |
' | +0.001 |
loe | +0.001 |
ird | +0.001 |
ay | +0.001 |
Neg logit contributions | |
blurry | -0.001 |
nam | -0.001 |
wil | -0.001 |
cks | -0.001 |
ateful | -0.001 |
Token | pa |
Token ID | 8957 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
ocolate | +0.008 |
tted | +0.007 |
loe | +0.007 |
uster | +0.007 |
' | +0.007 |
Neg logit contributions | |
blurry | -0.009 |
nam | -0.009 |
ateful | -0.008 |
cks | -0.008 |
wil | -0.008 |
Token | ." |
Token ID | 526 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
ocolate | +0.046 |
loe | +0.046 |
' | +0.042 |
ird | +0.042 |
tted | +0.042 |
Neg logit contributions | |
blurry | -0.058 |
nam | -0.055 |
wil | -0.051 |
lands | -0.050 |
ateful | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
' | +0.041 |
of | +0.040 |
ocolate | +0.039 |
loe | +0.039 |
ird | +0.036 |
Neg logit contributions | |
blurry | -0.067 |
cks | -0.063 |
wil | -0.062 |
nam | -0.062 |
ric | -0.059 |
Token | for |
Token ID | 329 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
blurry | +0.050 |
nam | +0.046 |
lands | +0.044 |
prett | +0.042 |
wil | +0.041 |
Neg logit contributions | |
ocolate | -0.064 |
loe | -0.064 |
ird | -0.061 |
' | -0.058 |
tted | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
ocolate | +0.090 |
loe | +0.090 |
' | +0.088 |
ird | +0.085 |
tted | +0.083 |
Neg logit contributions | |
blurry | -0.072 |
nam | -0.067 |
wil | -0.059 |
prett | -0.058 |
lands | -0.058 |
Token | walk |
Token ID | 2513 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ocolate | +0.022 |
loe | +0.022 |
' | +0.021 |
ird | +0.021 |
tted | +0.020 |
Neg logit contributions | |
blurry | -0.027 |
nam | -0.025 |
ateful | -0.024 |
wil | -0.024 |
cks | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
blurry | +0.013 |
nam | +0.012 |
wil | +0.011 |
ateful | +0.011 |
lands | +0.011 |
Neg logit contributions | |
ocolate | -0.012 |
loe | -0.011 |
' | -0.011 |
ird | -0.011 |
tted | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
loe | +0.006 |
ird | +0.005 |
' | +0.005 |
ve | +0.005 |
uster | +0.005 |
Neg logit contributions | |
blurry | -0.004 |
flashes | -0.004 |
nam | -0.004 |
lands | -0.003 |
sideways | -0.003 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
' | +0.013 |
loe | +0.013 |
ird | +0.012 |
tted | +0.012 |
ocolate | +0.012 |
Neg logit contributions | |
blurry | -0.016 |
nam | -0.015 |
ateful | -0.015 |
cks | -0.015 |
wil | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ocolate | +0.027 |
of | +0.026 |
' | +0.025 |
loe | +0.024 |
ird | +0.023 |
Neg logit contributions | |
blurry | -0.045 |
nam | -0.042 |
cks | -0.041 |
wil | -0.040 |
ateful | -0.040 |
Token | big |
Token ID | 1263 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
' | +0.020 |
ocolate | +0.019 |
ird | +0.018 |
ay | +0.018 |
loe | +0.018 |
Neg logit contributions | |
blurry | -0.026 |
cks | -0.026 |
nam | -0.025 |
ateful | -0.025 |
wil | -0.024 |
Token | tree |
Token ID | 5509 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
ocolate | +0.050 |
loe | +0.048 |
' | +0.047 |
ird | +0.046 |
ay | +0.043 |
Neg logit contributions | |
blurry | -0.067 |
nam | -0.064 |
wil | -0.059 |
ateful | -0.059 |
cks | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
blurry | +0.053 |
nam | +0.051 |
ateful | +0.049 |
prett | +0.046 |
wil | +0.046 |
Neg logit contributions | |
' | -0.032 |
of | -0.030 |
ocolate | -0.028 |
loe | -0.026 |
tted | -0.026 |
Token | decided |
Token ID | 3066 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
of | +0.002 |
' | +0.002 |
ird | +0.002 |
ocolate | +0.002 |
days | +0.002 |
Neg logit contributions | |
blurry | -0.004 |
cks | -0.004 |
ateful | -0.004 |
ric | -0.004 |
wil | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
ocolate | +0.005 |
loe | +0.005 |
ird | +0.005 |
' | +0.005 |
tted | +0.005 |
Neg logit contributions | |
blurry | -0.007 |
nam | -0.007 |
lands | -0.006 |
wil | -0.006 |
prett | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
ocolate | +0.016 |
ird | +0.016 |
uster | +0.015 |
loe | +0.015 |
tted | +0.014 |
Neg logit contributions | |
blurry | -0.015 |
cks | -0.014 |
nam | -0.014 |
wil | -0.014 |
lands | -0.014 |
Token | The |
Token ID | 464 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ocolate | +0.015 |
loe | +0.015 |
ird | +0.015 |
uster | +0.014 |
' | +0.014 |
Neg logit contributions | |
blurry | -0.017 |
nam | -0.015 |
wil | -0.015 |
ateful | -0.014 |
prett | -0.014 |
Token | bees |
Token ID | 17002 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
blurry | +0.013 |
prett | +0.012 |
wil | +0.012 |
nam | +0.012 |
lands | +0.012 |
Neg logit contributions | |
ocolate | -0.012 |
loe | -0.012 |
uster | -0.012 |
ird | -0.011 |
tted | -0.011 |
Token | kept |
Token ID | 4030 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ocolate | +0.046 |
loe | +0.045 |
ird | +0.042 |
uster | +0.042 |
tted | +0.041 |
Neg logit contributions | |
blurry | -0.044 |
nam | -0.041 |
wil | -0.039 |
lands | -0.037 |
prett | -0.037 |
Token | asking |
Token ID | 4737 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ocolate | +0.013 |
loe | +0.013 |
' | +0.012 |
ird | +0.012 |
tted | +0.011 |
Neg logit contributions | |
blurry | -0.015 |
nam | -0.014 |
wil | -0.013 |
ateful | -0.013 |
lands | -0.012 |
Token | M |
Token ID | 337 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ocolate | +0.116 |
loe | +0.112 |
ird | +0.110 |
tted | +0.106 |
' | +0.105 |
Neg logit contributions | |
blurry | -0.117 |
nam | -0.109 |
wil | -0.102 |
prett | -0.101 |
lands | -0.100 |
Token | andy |
Token ID | 10757 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
ocolate | +0.024 |
tted | +0.024 |
ird | +0.024 |
loe | +0.024 |
' | +0.023 |
Neg logit contributions | |
blurry | -0.017 |
wil | -0.015 |
ateful | -0.014 |
lands | -0.014 |
prett | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
blurry | +0.048 |
nam | +0.045 |
wil | +0.042 |
ateful | +0.041 |
cks | +0.041 |
Neg logit contributions | |
ocolate | -0.041 |
loe | -0.041 |
' | -0.040 |
ird | -0.038 |
tted | -0.037 |
Token | make |
Token ID | 787 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
blurry | +0.028 |
nam | +0.026 |
wil | +0.024 |
ateful | +0.023 |
prett | +0.023 |
Neg logit contributions | |
ocolate | -0.025 |
loe | -0.025 |
' | -0.023 |
ird | -0.023 |
tted | -0.023 |
Token | more |
Token ID | 517 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
blurry | +0.046 |
nam | +0.044 |
wil | +0.041 |
ateful | +0.040 |
cks | +0.039 |
Neg logit contributions | |
ocolate | -0.028 |
loe | -0.027 |
' | -0.026 |
ird | -0.025 |
tted | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
blurry | +0.023 |
nam | +0.021 |
lands | +0.020 |
ateful | +0.019 |
prett | +0.019 |
Neg logit contributions | |
loe | -0.030 |
ocolate | -0.028 |
tted | -0.028 |
uster | -0.027 |
ird | -0.027 |
Token | I |
Token ID | 314 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
blurry | +0.013 |
nam | +0.012 |
wil | +0.011 |
ateful | +0.011 |
lands | +0.011 |
Neg logit contributions | |
ocolate | -0.009 |
loe | -0.009 |
' | -0.009 |
ird | -0.008 |
tted | -0.008 |
Token | can |
Token ID | 460 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
blurry | +0.013 |
nam | +0.012 |
wil | +0.011 |
ateful | +0.011 |
cks | +0.011 |
Neg logit contributions | |
ocolate | -0.010 |
' | -0.010 |
loe | -0.010 |
ird | -0.010 |
tted | -0.010 |
Token | 't |
Token ID | 470 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
blurry | +0.047 |
nam | +0.044 |
wil | +0.041 |
ateful | +0.040 |
lands | +0.040 |
Neg logit contributions | |
ocolate | -0.034 |
loe | -0.034 |
' | -0.032 |
ird | -0.031 |
tted | -0.030 |
Token | help |
Token ID | 1037 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ocolate | +0.064 |
loe | +0.064 |
uster | +0.058 |
ird | +0.058 |
' | +0.057 |
Neg logit contributions | |
blurry | -0.072 |
nam | -0.067 |
wil | -0.062 |
lands | -0.062 |
ateful | -0.061 |
Token | you |
Token ID | 345 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
ocolate | +0.111 |
loe | +0.109 |
ird | +0.104 |
' | +0.104 |
tted | +0.101 |
Neg logit contributions | |
blurry | -0.111 |
nam | -0.103 |
wil | -0.094 |
lands | -0.094 |
ateful | -0.094 |
Token | ." |
Token ID | 526 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
ocolate | +0.022 |
' | +0.021 |
loe | +0.021 |
ird | +0.020 |
tted | +0.019 |
Neg logit contributions | |
blurry | -0.031 |
nam | -0.029 |
wil | -0.028 |
ateful | -0.027 |
prett | -0.027 |
Token | Ben |
Token ID | 3932 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
' | +0.035 |
ocolate | +0.033 |
loe | +0.032 |
of | +0.031 |
tted | +0.030 |
Neg logit contributions | |
blurry | -0.089 |
nam | -0.088 |
wil | -0.083 |
cks | -0.079 |
prett | -0.078 |
Token | said |
Token ID | 531 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
blurry | +0.027 |
nam | +0.024 |
wil | +0.023 |
lands | +0.022 |
ateful | +0.022 |
Neg logit contributions | |
ocolate | -0.035 |
loe | -0.034 |
' | -0.032 |
ird | -0.032 |
uster | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
blurry | +0.010 |
nam | +0.009 |
lands | +0.009 |
wil | +0.008 |
ateful | +0.008 |
Neg logit contributions | |
ocolate | -0.005 |
loe | -0.005 |
ird | -0.005 |
uster | -0.004 |
tted | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
loe | +0.002 |
ocolate | +0.002 |
ird | +0.002 |
ay | +0.002 |
uster | +0.002 |
Neg logit contributions | |
blurry | -0.003 |
nam | -0.002 |
wil | -0.002 |
prett | -0.002 |
tilted | -0.002 |
Token | one |
Token ID | 530 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
blurry | +0.001 |
nam | +0.001 |
cks | +0.001 |
ateful | +0.001 |
wil | +0.001 |
Neg logit contributions | |
ocolate | -0.001 |
' | -0.001 |
of | -0.001 |
loe | -0.001 |
ird | -0.001 |
Token | morning |
Token ID | 3329 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
ocolate | +0.017 |
' | +0.016 |
of | +0.016 |
loe | +0.016 |
ay | +0.015 |
Neg logit contributions | |
blurry | -0.044 |
nam | -0.042 |
cks | -0.040 |
ateful | -0.040 |
wil | -0.039 |
Token | feeling |
Token ID | 4203 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ocolate | +0.031 |
loe | +0.030 |
' | +0.030 |
ird | +0.028 |
tted | +0.027 |
Neg logit contributions | |
blurry | -0.046 |
nam | -0.044 |
ateful | -0.041 |
wil | -0.041 |
cks | -0.040 |
Token | very |
Token ID | 845 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
' | +0.103 |
ocolate | +0.102 |
loe | +0.100 |
ird | +0.099 |
of | +0.099 |
Neg logit contributions | |
blurry | -0.087 |
nam | -0.083 |
cks | -0.080 |
ateful | -0.077 |
flies | -0.073 |
Token | sick |
Token ID | 6639 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
ocolate | +0.012 |
' | +0.012 |
loe | +0.012 |
ird | +0.012 |
of | +0.011 |
Neg logit contributions | |
blurry | -0.010 |
nam | -0.010 |
cks | -0.009 |
ateful | -0.009 |
flashes | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
loe | +0.050 |
ocolate | +0.049 |
tted | +0.048 |
ird | +0.045 |
' | +0.044 |
Neg logit contributions | |
blurry | -0.030 |
nam | -0.025 |
lands | -0.024 |
wil | -0.024 |
prett | -0.023 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ocolate | +0.011 |
loe | +0.010 |
' | +0.010 |
tted | +0.010 |
ird | +0.010 |
Neg logit contributions | |
blurry | -0.008 |
nam | -0.008 |
wil | -0.007 |
prett | -0.007 |
lands | -0.007 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
blurry | +0.011 |
nam | +0.010 |
wil | +0.010 |
lands | +0.009 |
prett | +0.009 |
Neg logit contributions | |
ocolate | -0.010 |
loe | -0.010 |
' | -0.009 |
ird | -0.009 |
tted | -0.009 |
Token | my |
Token ID | 1820 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
blurry | +0.011 |
wil | +0.010 |
nam | +0.009 |
prett | +0.009 |
ateful | +0.008 |
Neg logit contributions | |
ocolate | -0.014 |
loe | -0.013 |
tted | -0.012 |
uster | -0.012 |
ird | -0.012 |
Token | came |
Token ID | 1625 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ocolate | +0.069 |
loe | +0.064 |
tted | +0.061 |
uster | +0.059 |
ay | +0.059 |
Neg logit contributions | |
blurry | -0.037 |
wil | -0.034 |
sings | -0.028 |
nam | -0.027 |
tilted | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
blurry | +0.008 |
nam | +0.008 |
wil | +0.007 |
lands | +0.007 |
prett | +0.007 |
Neg logit contributions | |
ocolate | -0.009 |
loe | -0.009 |
ird | -0.009 |
tted | -0.008 |
' | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
nam | +0.150 |
blurry | +0.144 |
prett | +0.132 |
wil | +0.132 |
ateful | +0.132 |
Neg logit contributions | |
' | -0.091 |
ocolate | -0.086 |
of | -0.085 |
loe | -0.081 |
ird | -0.077 |
Token | felt |
Token ID | 2936 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
cks | +0.002 |
nam | +0.002 |
ric | +0.002 |
blurry | +0.002 |
ucker | +0.002 |
Neg logit contributions | |
of | -0.001 |
little | -0.001 |
' | -0.001 |
help | -0.001 |
tted | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
nam | +0.037 |
blurry | +0.037 |
ety | +0.035 |
rings | +0.035 |
ateful | +0.035 |
Neg logit contributions | |
of | -0.031 |
ocolate | -0.029 |
' | -0.029 |
tted | -0.027 |
loe | -0.027 |
Token | ground |
Token ID | 2323 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
blurry | +0.009 |
cks | +0.009 |
nam | +0.009 |
ateful | +0.009 |
wil | +0.008 |
Neg logit contributions | |
ocolate | -0.009 |
loe | -0.009 |
adult | -0.009 |
of | -0.008 |
' | -0.008 |
Token | shake |
Token ID | 13279 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
nam | +0.035 |
ateful | +0.032 |
blurry | +0.030 |
prett | +0.030 |
rings | +0.028 |
Neg logit contributions | |
of | -0.030 |
' | -0.029 |
loe | -0.027 |
tted | -0.027 |
ocolate | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
' | +0.001 |
ocolate | +0.001 |
loe | +0.001 |
of | +0.001 |
ay | +0.001 |
Neg logit contributions | |
nam | -0.001 |
blurry | -0.001 |
ateful | -0.001 |
wil | -0.001 |
prett | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
blurry | +0.006 |
nam | +0.006 |
wil | +0.006 |
ateful | +0.006 |
lands | +0.006 |
Neg logit contributions | |
ocolate | -0.004 |
loe | -0.004 |
' | -0.004 |
ird | -0.004 |
tted | -0.004 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
' | +0.023 |
ird | +0.022 |
loe | +0.022 |
ocolate | +0.021 |
of | +0.020 |
Neg logit contributions | |
blurry | -0.024 |
nam | -0.023 |
prett | -0.022 |
cks | -0.022 |
ateful | -0.021 |
Token | outside |
Token ID | 2354 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
ocolate | +0.055 |
loe | +0.054 |
' | +0.053 |
tted | +0.050 |
ird | +0.050 |
Neg logit contributions | |
blurry | -0.069 |
nam | -0.066 |
wil | -0.062 |
ateful | -0.061 |
cks | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
ocolate | +0.047 |
loe | +0.046 |
ird | +0.044 |
tted | +0.042 |
' | +0.042 |
Neg logit contributions | |
blurry | -0.065 |
nam | -0.060 |
lands | -0.058 |
wil | -0.057 |
ateful | -0.056 |
Token | saw |
Token ID | 2497 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
ateful | +0.002 |
blurry | +0.002 |
cks | +0.002 |
endant | +0.002 |
wil | +0.002 |
Neg logit contributions | |
' | -0.001 |
of | -0.001 |
ird | -0.001 |
tted | -0.001 |
other | -0.001 |
Token | named |
Token ID | 3706 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
' | +0.031 |
loe | +0.029 |
ocolate | +0.029 |
ird | +0.028 |
of | +0.027 |
Neg logit contributions | |
blurry | -0.063 |
nam | -0.059 |
prett | -0.056 |
ateful | -0.056 |
lands | -0.055 |
Token | Lily |
Token ID | 20037 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
blurry | +0.008 |
nam | +0.007 |
wil | +0.006 |
prett | +0.006 |
lands | +0.006 |
Neg logit contributions | |
ocolate | -0.013 |
loe | -0.013 |
uster | -0.012 |
' | -0.012 |
tted | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
blurry | +0.070 |
nam | +0.067 |
prett | +0.063 |
ateful | +0.062 |
lands | +0.062 |
Neg logit contributions | |
' | -0.042 |
of | -0.037 |
ird | -0.036 |
ocolate | -0.035 |
loe | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
' | +0.007 |
ird | +0.007 |
uster | +0.007 |
Neg logit contributions | |
blurry | -0.005 |
nam | -0.005 |
wil | -0.004 |
prett | -0.004 |
ateful | -0.004 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
' | +0.014 |
loe | +0.014 |
ocolate | +0.014 |
ird | +0.013 |
tted | +0.013 |
Neg logit contributions | |
blurry | -0.021 |
nam | -0.020 |
ateful | -0.019 |
cks | -0.019 |
prett | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
ocolate | +0.010 |
' | +0.009 |
of | +0.008 |
loe | +0.008 |
kids | +0.008 |
Neg logit contributions | |
blurry | -0.016 |
cks | -0.015 |
ateful | -0.014 |
nam | -0.014 |
wil | -0.014 |
Token | play |
Token ID | 711 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
blurry | +0.032 |
nam | +0.030 |
wil | +0.027 |
ateful | +0.027 |
lands | +0.027 |
Neg logit contributions | |
ocolate | -0.033 |
loe | -0.033 |
' | -0.032 |
ird | -0.031 |
tted | -0.030 |
Token | outside |
Token ID | 2354 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
blurry | +0.017 |
nam | +0.016 |
prett | +0.014 |
lands | +0.014 |
wil | +0.014 |
Neg logit contributions | |
ocolate | -0.016 |
loe | -0.016 |
ird | -0.015 |
' | -0.015 |
uster | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
ocolate | +0.048 |
loe | +0.047 |
' | +0.045 |
ird | +0.044 |
tted | +0.043 |
Neg logit contributions | |
blurry | -0.058 |
nam | -0.054 |
wil | -0.050 |
ateful | -0.049 |
lands | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
blurry | +0.002 |
nam | +0.002 |
wil | +0.002 |
ateful | +0.002 |
prett | +0.002 |
Neg logit contributions | |
ocolate | -0.002 |
loe | -0.002 |
' | -0.002 |
of | -0.002 |
ird | -0.002 |
Token | sunshine |
Token ID | 34488 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
nam | +0.003 |
blurry | +0.003 |
ateful | +0.003 |
cks | +0.003 |
wil | +0.003 |
Neg logit contributions | |
' | -0.002 |
ocolate | -0.002 |
loe | -0.002 |
ay | -0.002 |
other | -0.002 |
Token | warm |
Token ID | 5814 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
ocolate | +0.028 |
loe | +0.027 |
' | +0.027 |
ird | +0.026 |
tted | +0.025 |
Neg logit contributions | |
blurry | -0.029 |
nam | -0.028 |
cks | -0.026 |
ateful | -0.026 |
wil | -0.026 |
Token | day |
Token ID | 1110 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
ird | +0.041 |
loe | +0.041 |
ocolate | +0.041 |
tted | +0.041 |
oning | +0.038 |
Neg logit contributions | |
blurry | -0.041 |
lands | -0.035 |
flashes | -0.035 |
wil | -0.035 |
prett | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
loe | +0.056 |
ocolate | +0.054 |
tted | +0.050 |
uster | +0.049 |
affle | +0.049 |
Neg logit contributions | |
blurry | -0.049 |
nam | -0.043 |
wil | -0.041 |
prett | -0.040 |
flashes | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
loe | +0.013 |
ocolate | +0.013 |
ird | +0.013 |
' | +0.012 |
tted | +0.012 |
Neg logit contributions | |
blurry | -0.018 |
nam | -0.017 |
prett | -0.015 |
wil | -0.015 |
lands | -0.015 |
Token | all |
Token ID | 477 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ocolate | +0.013 |
loe | +0.013 |
' | +0.012 |
ird | +0.012 |
tted | +0.011 |
Neg logit contributions | |
blurry | -0.013 |
nam | -0.012 |
wil | -0.011 |
ateful | -0.011 |
cks | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
blurry | +0.094 |
nam | +0.089 |
wil | +0.081 |
ateful | +0.080 |
prett | +0.079 |
Neg logit contributions | |
loe | -0.089 |
ocolate | -0.089 |
' | -0.087 |
ird | -0.084 |
of | -0.082 |
Token | animals |
Token ID | 4695 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
blurry | +0.003 |
nam | +0.003 |
lands | +0.002 |
prett | +0.002 |
flashes | +0.002 |
Neg logit contributions | |
ocolate | -0.003 |
loe | -0.003 |
ird | -0.003 |
' | -0.003 |
tted | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ocolate | +0.066 |
loe | +0.065 |
ird | +0.059 |
uster | +0.059 |
ay | +0.058 |
Neg logit contributions | |
blurry | -0.060 |
nam | -0.056 |
wil | -0.053 |
lands | -0.050 |
ateful | -0.050 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ocolate | +0.011 |
loe | +0.011 |
' | +0.010 |
ird | +0.010 |
tted | +0.010 |
Neg logit contributions | |
blurry | -0.012 |
nam | -0.012 |
ateful | -0.011 |
wil | -0.011 |
lands | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
loe | +0.110 |
ocolate | +0.107 |
uster | +0.106 |
ird | +0.102 |
kids | +0.098 |
Neg logit contributions | |
blurry | -0.074 |
nam | -0.067 |
lands | -0.062 |
prett | -0.061 |
cks | -0.060 |
Token | Spot |
Token ID | 15899 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ocolate | +0.006 |
loe | +0.006 |
ird | +0.005 |
uster | +0.005 |
adult | +0.005 |
Neg logit contributions | |
blurry | -0.004 |
lands | -0.004 |
nam | -0.004 |
flashes | -0.004 |
cks | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
ocolate | +0.035 |
loe | +0.034 |
' | +0.032 |
ird | +0.032 |
tted | +0.031 |
Neg logit contributions | |
blurry | -0.039 |
nam | -0.037 |
wil | -0.034 |
lands | -0.034 |
prett | -0.033 |
Token | its |
Token ID | 663 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
blurry | +0.028 |
nam | +0.026 |
wil | +0.024 |
ateful | +0.023 |
prett | +0.023 |
Neg logit contributions | |
ocolate | -0.032 |
loe | -0.031 |
' | -0.030 |
ird | -0.029 |
tted | -0.028 |
Token | hole |
Token ID | 7604 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
blurry | +0.016 |
nam | +0.015 |
wil | +0.014 |
ateful | +0.014 |
lands | +0.014 |
Neg logit contributions | |
ocolate | -0.015 |
loe | -0.014 |
' | -0.014 |
ird | -0.014 |
tted | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
blurry | +0.128 |
nam | +0.120 |
wil | +0.111 |
ateful | +0.110 |
lands | +0.109 |
Neg logit contributions | |
ocolate | -0.110 |
loe | -0.108 |
' | -0.104 |
ird | -0.102 |
tted | -0.098 |
Token | The |
Token ID | 383 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
blurry | +0.002 |
nam | +0.002 |
lands | +0.002 |
wil | +0.002 |
ateful | +0.002 |
Neg logit contributions | |
ocolate | -0.002 |
loe | -0.002 |
ird | -0.002 |
' | -0.001 |
uster | -0.001 |
Token | little |
Token ID | 1310 |
Feature activation | +4.90e-03 |
Pos logit contributions | |
loe | +0.038 |
ocolate | +0.037 |
ird | +0.035 |
uster | +0.034 |
tted | +0.032 |
Neg logit contributions | |
blurry | -0.041 |
nam | -0.038 |
prett | -0.037 |
wil | -0.036 |
flashes | -0.034 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ocolate | +0.000 |
loe | +0.000 |
ird | +0.000 |
' | +0.000 |
tted | +0.000 |
Neg logit contributions | |
blurry | -0.000 |
nam | -0.000 |
wil | -0.000 |
prett | -0.000 |
lands | -0.000 |
Token | stayed |
Token ID | 9658 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ocolate | +0.018 |
loe | +0.017 |
uster | +0.016 |
oning | +0.016 |
ay | +0.016 |
Neg logit contributions | |
blurry | -0.011 |
wil | -0.011 |
lands | -0.011 |
tilted | -0.010 |
nam | -0.010 |
Token | asleep |
Token ID | 16039 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ocolate | +0.043 |
loe | +0.043 |
' | +0.042 |
ird | +0.040 |
tted | +0.039 |
Neg logit contributions | |
blurry | -0.052 |
nam | -0.049 |
ateful | -0.045 |
wil | -0.045 |
lands | -0.044 |
Token | until |
Token ID | 1566 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
blurry | +0.001 |
nam | +0.001 |
wil | +0.001 |
prett | +0.001 |
lands | +0.001 |
Neg logit contributions | |
ocolate | -0.001 |
loe | -0.001 |
ird | -0.001 |
uster | -0.001 |
ay | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
ocolate | +0.012 |
loe | +0.012 |
' | +0.012 |
ird | +0.011 |
tted | +0.011 |
Neg logit contributions | |
blurry | -0.013 |
nam | -0.012 |
ateful | -0.011 |
cks | -0.011 |
wil | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ocolate | +0.027 |
loe | +0.026 |
tted | +0.023 |
ird | +0.023 |
uster | +0.022 |
Neg logit contributions | |
blurry | -0.052 |
nam | -0.048 |
wil | -0.047 |
lands | -0.046 |
ateful | -0.046 |
Token | I |
Token ID | 314 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
loe | +0.008 |
ocolate | +0.008 |
tted | +0.007 |
ird | +0.007 |
umbs | +0.007 |
Neg logit contributions | |
blurry | -0.006 |
nam | -0.006 |
prett | -0.005 |
wil | -0.005 |
ateful | -0.005 |
Token | permit |
Token ID | 8749 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
blurry | +0.017 |
wil | +0.015 |
nam | +0.014 |
ateful | +0.014 |
lands | +0.014 |
Neg logit contributions | |
ocolate | -0.016 |
loe | -0.015 |
uster | -0.014 |
oning | -0.014 |
ay | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
ocolate | +0.045 |
loe | +0.045 |
ird | +0.044 |
tted | +0.044 |
uster | +0.043 |
Neg logit contributions | |
blurry | -0.032 |
nam | -0.031 |
lands | -0.028 |
wil | -0.027 |
prett | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
loe | +0.031 |
ocolate | +0.030 |
ird | +0.028 |
uster | +0.027 |
kids | +0.027 |
Neg logit contributions | |
blurry | -0.018 |
nam | -0.017 |
prett | -0.015 |
lands | -0.015 |
rings | -0.014 |
Token | play |
Token ID | 711 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
blurry | +0.031 |
nam | +0.027 |
lands | +0.026 |
prett | +0.026 |
ateful | +0.025 |
Neg logit contributions | |
loe | -0.035 |
ocolate | -0.034 |
uster | -0.031 |
ird | -0.030 |
kids | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
blurry | +0.016 |
nam | +0.014 |
prett | +0.013 |
lands | +0.013 |
cks | +0.012 |
Neg logit contributions | |
loe | -0.023 |
ocolate | -0.022 |
uster | -0.021 |
umbs | -0.021 |
kids | -0.021 |
Token | your |
Token ID | 534 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
blurry | +0.009 |
nam | +0.009 |
lands | +0.008 |
wil | +0.008 |
ateful | +0.007 |
Neg logit contributions | |
ocolate | -0.014 |
loe | -0.014 |
' | -0.014 |
tted | -0.014 |
ird | -0.014 |
Token | toys |
Token ID | 14958 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ocolate | +0.059 |
loe | +0.058 |
' | +0.054 |
ird | +0.053 |
uster | +0.052 |
Neg logit contributions | |
blurry | -0.056 |
nam | -0.053 |
prett | -0.049 |
lands | -0.046 |
wil | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
loe | +0.063 |
ocolate | +0.061 |
tted | +0.055 |
uster | +0.055 |
ird | +0.055 |
Neg logit contributions | |
blurry | -0.075 |
nam | -0.071 |
prett | -0.065 |
wil | -0.063 |
lands | -0.063 |
Token | but |
Token ID | 475 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
loe | +0.006 |
ocolate | +0.006 |
tted | +0.006 |
' | +0.006 |
ird | +0.006 |
Neg logit contributions | |
blurry | -0.008 |
nam | -0.008 |
prett | -0.007 |
wil | -0.007 |
ateful | -0.007 |
Token | � |
Token ID | 241 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
blurry | +0.056 |
nam | +0.052 |
wil | +0.050 |
lands | +0.049 |
cks | +0.049 |
Neg logit contributions | |
ocolate | -0.041 |
loe | -0.040 |
ird | -0.039 |
' | -0.038 |
tted | -0.036 |
Token | It |
Token ID | 1026 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
blurry | +0.012 |
nam | +0.011 |
wil | +0.010 |
cks | +0.010 |
ateful | +0.010 |
Neg logit contributions | |
ocolate | -0.011 |
loe | -0.010 |
' | -0.010 |
ird | -0.010 |
tted | -0.010 |
Token | â |
Token ID | 22940 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
blurry | +0.013 |
nam | +0.012 |
wil | +0.011 |
ateful | +0.011 |
lands | +0.011 |
Neg logit contributions | |
ocolate | -0.010 |
loe | -0.010 |
' | -0.009 |
ird | -0.009 |
tted | -0.009 |
Token | € |
Token ID | 26391 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
loe | +0.019 |
ocolate | +0.019 |
uster | +0.018 |
adult | +0.017 |
ird | +0.017 |
Neg logit contributions | |
blurry | -0.023 |
prett | -0.021 |
cks | -0.021 |
lands | -0.021 |
nam | -0.021 |
Token | ™ |
Token ID | 8151 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ocolate | +0.080 |
loe | +0.076 |
uster | +0.072 |
adult | +0.071 |
other | +0.069 |
Neg logit contributions | |
blurry | -0.092 |
nam | -0.087 |
lands | -0.086 |
cks | -0.081 |
wil | -0.080 |
Token | s |
Token ID | 82 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
blurry | +0.134 |
nam | +0.123 |
ateful | +0.117 |
wil | +0.117 |
lands | +0.114 |
Neg logit contributions | |
ocolate | -0.108 |
uster | -0.103 |
loe | -0.102 |
basis | -0.100 |
kids | -0.098 |
Token | chocolate |
Token ID | 11311 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
blurry | +0.224 |
nam | +0.210 |
wil | +0.195 |
ateful | +0.191 |
lands | +0.190 |
Neg logit contributions | |
ocolate | -0.195 |
loe | -0.192 |
' | -0.184 |
ird | -0.180 |
tted | -0.174 |
Token | ! |
Token ID | 0 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
ocolate | +0.091 |
loe | +0.090 |
' | +0.085 |
ird | +0.083 |
tted | +0.080 |
Neg logit contributions | |
blurry | -0.131 |
nam | -0.123 |
wil | -0.115 |
lands | -0.113 |
ateful | -0.113 |
Token | â |
Token ID | 22940 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
nam | +0.002 |
blurry | +0.002 |
prett | +0.002 |
rings | +0.002 |
ateful | +0.002 |
Neg logit contributions | |
ocolate | -0.002 |
loe | -0.002 |
' | -0.002 |
affle | -0.002 |
kids | -0.002 |
Token | € |
Token ID | 26391 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ocolate | +0.020 |
loe | +0.019 |
uster | +0.018 |
ird | +0.018 |
' | +0.017 |
Neg logit contributions | |
blurry | -0.024 |
nam | -0.022 |
prett | -0.021 |
cks | -0.021 |
lands | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ocolate | +0.076 |
loe | +0.072 |
uster | +0.067 |
adult | +0.066 |
tted | +0.065 |
Neg logit contributions | |
blurry | -0.097 |
nam | -0.093 |
lands | -0.091 |
cks | -0.087 |
wil | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
blurry | +0.042 |
lands | +0.038 |
nam | +0.038 |
cks | +0.037 |
wil | +0.037 |
Neg logit contributions | |
ocolate | -0.022 |
loe | -0.022 |
tted | -0.019 |
uster | -0.019 |
ird | -0.019 |
Token | my |
Token ID | 616 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
' | +0.006 |
ird | +0.006 |
tted | +0.006 |
Neg logit contributions | |
blurry | -0.007 |
nam | -0.006 |
wil | -0.006 |
ateful | -0.005 |
lands | -0.005 |
Token | car |
Token ID | 1097 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ocolate | +0.048 |
loe | +0.047 |
' | +0.046 |
ird | +0.045 |
tted | +0.043 |
Neg logit contributions | |
blurry | -0.055 |
nam | -0.052 |
wil | -0.048 |
ateful | -0.048 |
cks | -0.047 |
Token | is |
Token ID | 318 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
nam | +0.048 |
blurry | +0.048 |
ateful | +0.044 |
wil | +0.043 |
cks | +0.041 |
Neg logit contributions | |
' | -0.030 |
ocolate | -0.029 |
ird | -0.028 |
ay | -0.028 |
loe | -0.028 |
Token | faster |
Token ID | 5443 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
nam | +0.054 |
blurry | +0.054 |
ateful | +0.053 |
wil | +0.051 |
cks | +0.048 |
Neg logit contributions | |
ocolate | -0.049 |
of | -0.048 |
' | -0.048 |
loe | -0.048 |
ird | -0.048 |
Token | than |
Token ID | 621 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
blurry | +0.014 |
nam | +0.014 |
wil | +0.013 |
ateful | +0.013 |
prett | +0.013 |
Neg logit contributions | |
ocolate | -0.009 |
loe | -0.008 |
' | -0.008 |
ird | -0.008 |
tted | -0.007 |
Token | yours |
Token ID | 12431 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
blurry | +0.155 |
nam | +0.145 |
wil | +0.132 |
ateful | +0.130 |
lands | +0.129 |
Neg logit contributions | |
ocolate | -0.173 |
loe | -0.171 |
' | -0.165 |
ird | -0.162 |
tted | -0.157 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ocolate | +0.069 |
loe | +0.067 |
' | +0.063 |
ird | +0.061 |
tted | +0.058 |
Neg logit contributions | |
blurry | -0.151 |
nam | -0.143 |
wil | -0.135 |
ateful | -0.134 |
lands | -0.132 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ocolate | +0.007 |
loe | +0.007 |
' | +0.007 |
ird | +0.006 |
of | +0.006 |
Neg logit contributions | |
blurry | -0.008 |
nam | -0.007 |
wil | -0.007 |
cks | -0.007 |
ateful | -0.007 |
Token | says |
Token ID | 1139 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
loe | +0.015 |
ocolate | +0.015 |
' | +0.015 |
ird | +0.014 |
tted | +0.014 |
Neg logit contributions | |
blurry | -0.008 |
nam | -0.007 |
wil | -0.007 |
ateful | -0.006 |
prett | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
blurry | +0.048 |
nam | +0.045 |
wil | +0.040 |
ateful | +0.039 |
cks | +0.039 |
Neg logit contributions | |
ocolate | -0.049 |
loe | -0.048 |
ird | -0.044 |
' | -0.044 |
tted | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ocolate | +0.024 |
ird | +0.023 |
est | +0.022 |
loe | +0.022 |
ounces | +0.021 |
Neg logit contributions | |
lands | -0.009 |
blurry | -0.009 |
Mars | -0.009 |
bel | -0.008 |
cks | -0.008 |
Token | Billy |
Token ID | 49640 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
ocolate | +0.022 |
loe | +0.022 |
ird | +0.019 |
umbs | +0.018 |
est | +0.018 |
Neg logit contributions | |
blurry | -0.014 |
nam | -0.012 |
How | -0.011 |
shin | -0.011 |
Why | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
ocolate | +0.004 |
loe | +0.004 |
ird | +0.003 |
uster | +0.003 |
tted | +0.003 |
Neg logit contributions | |
blurry | -0.003 |
nam | -0.003 |
lands | -0.003 |
wil | -0.003 |
prett | -0.002 |
Token | € |
Token ID | 26391 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ocolate | +0.024 |
loe | +0.023 |
ird | +0.022 |
of | +0.022 |
uster | +0.022 |
Neg logit contributions | |
blurry | -0.025 |
nam | -0.023 |
cks | -0.022 |
prett | -0.022 |
ateful | -0.022 |
Token | ™ |
Token ID | 8151 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ocolate | +0.087 |
loe | +0.083 |
' | +0.077 |
ird | +0.076 |
uster | +0.075 |
Neg logit contributions | |
blurry | -0.095 |
nam | -0.090 |
lands | -0.085 |
cks | -0.082 |
wil | -0.081 |
Token | s |
Token ID | 82 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
blurry | +0.098 |
ric | +0.096 |
nam | +0.092 |
ety | +0.092 |
wil | +0.090 |
Neg logit contributions | |
uster | -0.124 |
ocolate | -0.121 |
basis | -0.120 |
affle | -0.119 |
oning | -0.119 |
Token | dad |
Token ID | 9955 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
blurry | +0.213 |
nam | +0.199 |
wil | +0.184 |
ateful | +0.181 |
lands | +0.180 |
Neg logit contributions | |
ocolate | -0.206 |
loe | -0.202 |
' | -0.194 |
ird | -0.191 |
tted | -0.185 |
Token | smiled |
Token ID | 13541 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
ocolate | +0.011 |
loe | +0.010 |
oning | +0.009 |
basis | +0.009 |
uster | +0.009 |
Neg logit contributions | |
blurry | -0.005 |
wil | -0.004 |
tilted | -0.004 |
nam | -0.004 |
lands | -0.003 |
Token | back |
Token ID | 736 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
blurry | +0.037 |
nam | +0.036 |
wil | +0.034 |
cks | +0.033 |
ateful | +0.033 |
Neg logit contributions | |
' | -0.017 |
ocolate | -0.017 |
loe | -0.016 |
ird | -0.015 |
uster | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ocolate | +0.036 |
loe | +0.035 |
ird | +0.033 |
tted | +0.032 |
' | +0.032 |
Neg logit contributions | |
blurry | -0.044 |
nam | -0.041 |
lands | -0.038 |
wil | -0.038 |
ateful | -0.038 |
Token | � |
Token ID | 6184 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
ocolate | +0.001 |
loe | +0.001 |
ird | +0.001 |
' | +0.001 |
ve | +0.001 |
Neg logit contributions | |
blurry | -0.001 |
nam | -0.000 |
flashes | -0.000 |
prett | -0.000 |
shin | -0.000 |
Token | their |
Token ID | 511 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
blurry | +0.060 |
nam | +0.053 |
wil | +0.047 |
ateful | +0.045 |
lands | +0.045 |
Neg logit contributions | |
ocolate | -0.126 |
loe | -0.125 |
' | -0.121 |
ird | -0.121 |
tted | -0.117 |
Token | faces |
Token ID | 6698 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
blurry | +0.001 |
nam | +0.001 |
ateful | +0.001 |
wil | +0.001 |
prett | +0.001 |
Neg logit contributions | |
ocolate | -0.001 |
' | -0.001 |
loe | -0.001 |
ay | -0.001 |
tted | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
blurry | +0.078 |
nam | +0.074 |
wil | +0.070 |
ateful | +0.069 |
lands | +0.069 |
Neg logit contributions | |
ocolate | -0.038 |
loe | -0.037 |
' | -0.035 |
ird | -0.034 |
tted | -0.032 |
Token | n |
Token ID | 299 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
blurry | +0.000 |
ateful | +0.000 |
nam | +0.000 |
ric | +0.000 |
rings | +0.000 |
Neg logit contributions | |
of | -0.000 |
days | -0.000 |
' | -0.000 |
ocolate | -0.000 |
hours | -0.000 |
Token | uzz |
Token ID | 4715 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ocolate | +0.038 |
loe | +0.037 |
' | +0.036 |
ird | +0.035 |
tted | +0.034 |
Neg logit contributions | |
blurry | -0.031 |
nam | -0.029 |
wil | -0.026 |
ateful | -0.025 |
lands | -0.025 |
Token | led |
Token ID | 992 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
nam | +0.032 |
blurry | +0.031 |
ateful | +0.027 |
prett | +0.027 |
wil | +0.026 |
Neg logit contributions | |
' | -0.028 |
loe | -0.027 |
ocolate | -0.027 |
ird | -0.026 |
of | -0.026 |
Token | their |
Token ID | 511 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
blurry | +0.174 |
nam | +0.173 |
ateful | +0.163 |
ric | +0.155 |
wil | +0.154 |
Neg logit contributions | |
of | -0.153 |
' | -0.148 |
est | -0.141 |
ocolate | -0.141 |
other | -0.135 |
Token | hair |
Token ID | 4190 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
blurry | +0.001 |
nam | +0.001 |
ateful | +0.001 |
wil | +0.001 |
prett | +0.001 |
Neg logit contributions | |
ocolate | -0.001 |
' | -0.001 |
loe | -0.001 |
tted | -0.001 |
ay | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
ocolate | +0.018 |
' | +0.018 |
loe | +0.017 |
ird | +0.017 |
tted | +0.016 |
Neg logit contributions | |
blurry | -0.025 |
nam | -0.024 |
ateful | -0.022 |
wil | -0.021 |
cks | -0.021 |
Token | It |
Token ID | 632 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
blurry | +0.006 |
nam | +0.006 |
wil | +0.006 |
ateful | +0.006 |
prett | +0.006 |
Neg logit contributions | |
ocolate | -0.003 |
loe | -0.003 |
' | -0.003 |
ird | -0.003 |
tted | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
' | +0.017 |
of | +0.016 |
tted | +0.015 |
ird | +0.015 |
loe | +0.014 |
Neg logit contributions | |
nam | -0.037 |
blurry | -0.035 |
ateful | -0.035 |
rings | -0.031 |
cks | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
blurry | +0.030 |
nam | +0.028 |
wil | +0.026 |
ateful | +0.025 |
lands | +0.025 |
Neg logit contributions | |
ocolate | -0.028 |
loe | -0.027 |
' | -0.027 |
ird | -0.026 |
tted | -0.025 |
Token | Bob |
Token ID | 5811 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
ird | +0.005 |
loe | +0.005 |
uster | +0.005 |
' | +0.005 |
ocolate | +0.005 |
Neg logit contributions | |
blurry | -0.003 |
cks | -0.003 |
flashes | -0.002 |
lands | -0.002 |
nam | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
ocolate | +0.030 |
loe | +0.029 |
' | +0.028 |
ird | +0.028 |
tted | +0.027 |
Neg logit contributions | |
blurry | -0.037 |
nam | -0.035 |
wil | -0.033 |
ateful | -0.032 |
lands | -0.032 |
Token | much |
Token ID | 881 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
ocolate | +0.023 |
loe | +0.023 |
' | +0.022 |
ird | +0.021 |
tted | +0.021 |
Neg logit contributions | |
blurry | -0.024 |
nam | -0.023 |
wil | -0.021 |
lands | -0.021 |
ateful | -0.021 |
Token | older |
Token ID | 4697 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
blurry | +0.036 |
nam | +0.035 |
cks | +0.035 |
wil | +0.034 |
lands | +0.033 |
Neg logit contributions | |
' | -0.032 |
ocolate | -0.031 |
of | -0.031 |
ird | -0.030 |
loe | -0.030 |
Token | than |
Token ID | 621 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
ocolate | +0.017 |
loe | +0.016 |
' | +0.015 |
ird | +0.015 |
tted | +0.015 |
Neg logit contributions | |
blurry | -0.025 |
nam | -0.023 |
wil | -0.022 |
ateful | -0.022 |
lands | -0.022 |
Token | Jack |
Token ID | 3619 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
blurry | +0.184 |
nam | +0.169 |
wil | +0.165 |
lands | +0.161 |
ateful | +0.159 |
Neg logit contributions | |
ocolate | -0.145 |
loe | -0.141 |
' | -0.132 |
ird | -0.128 |
uster | -0.122 |
Token | and |
Token ID | 290 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
blurry | +0.028 |
nam | +0.026 |
wil | +0.025 |
lands | +0.024 |
prett | +0.023 |
Neg logit contributions | |
ocolate | -0.028 |
loe | -0.028 |
uster | -0.026 |
tted | -0.025 |
ird | -0.025 |
Token | he |
Token ID | 339 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
ocolate | +0.003 |
loe | +0.003 |
' | +0.003 |
ird | +0.002 |
tted | +0.002 |
Neg logit contributions | |
blurry | -0.007 |
nam | -0.006 |
wil | -0.006 |
cks | -0.006 |
lands | -0.006 |
Token | always |
Token ID | 1464 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
blurry | +0.046 |
nam | +0.044 |
wil | +0.040 |
ateful | +0.040 |
cks | +0.039 |
Neg logit contributions | |
ocolate | -0.038 |
loe | -0.038 |
' | -0.037 |
ird | -0.035 |
tted | -0.035 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
blurry | +0.002 |
nam | +0.002 |
ateful | +0.002 |
cks | +0.002 |
wil | +0.002 |
Neg logit contributions | |
ocolate | -0.002 |
ird | -0.002 |
loe | -0.002 |
' | -0.002 |
tted | -0.002 |