Token | long |
Token ID | 890 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ister | +0.026 |
ths | +0.025 |
ww | +0.025 |
www | +0.025 |
avail | +0.024 |
Neg logit contributions | |
like | -0.015 |
everywhere | -0.010 |
favorite | -0.009 |
liked | -0.009 |
around | -0.009 |
Token | walks |
Token ID | 11114 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
like | +0.040 |
liked | +0.030 |
favorite | +0.030 |
everywhere | +0.029 |
back | +0.028 |
Neg logit contributions | |
ww | -0.037 |
ths | -0.036 |
ister | -0.036 |
service | -0.035 |
www | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
like | +0.004 |
pad | +0.002 |
favorite | +0.002 |
dolls | +0.002 |
liked | +0.002 |
Neg logit contributions | |
ister | -0.011 |
ww | -0.010 |
ths | -0.010 |
service | -0.010 |
www | -0.010 |
Token | Whenever |
Token ID | 21326 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
like | +0.001 |
everywhere | +0.001 |
favorite | +0.001 |
back | +0.001 |
dolls | +0.001 |
Neg logit contributions | |
ister | -0.002 |
ww | -0.002 |
www | -0.002 |
avail | -0.002 |
storm | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ths | +0.119 |
ww | +0.118 |
ister | +0.117 |
www | +0.116 |
rim | +0.113 |
Neg logit contributions | |
like | -0.060 |
liked | -0.038 |
favorite | -0.032 |
everywhere | -0.031 |
all | -0.031 |
Token | m |
Token ID | 285 |
Feature activation | +9.48e+00 |
Pos logit contributions | |
ister | +0.057 |
avail | +0.055 |
ths | +0.054 |
ww | +0.054 |
keys | +0.053 |
Neg logit contributions | |
like | -0.039 |
favorite | -0.029 |
liked | -0.028 |
back | -0.026 |
t | -0.026 |
Token | ule |
Token ID | 2261 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
avail | +0.146 |
ww | +0.126 |
storm | +0.118 |
www | +0.111 |
explosion | +0.111 |
Neg logit contributions | |
like | -0.298 |
favorite | -0.262 |
liked | -0.254 |
pad | -0.247 |
and | -0.245 |
Token | became |
Token ID | 2627 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
ww | +0.171 |
avail | +0.170 |
ister | +0.168 |
www | +0.167 |
ths | +0.163 |
Neg logit contributions | |
like | -0.096 |
liked | -0.069 |
favorite | -0.060 |
everywhere | -0.058 |
around | -0.055 |
Token | tired |
Token ID | 10032 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ister | +0.022 |
ww | +0.022 |
ths | +0.021 |
www | +0.021 |
service | +0.021 |
Neg logit contributions | |
like | -0.017 |
everywhere | -0.012 |
favorite | -0.012 |
liked | -0.012 |
around | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
ww | +0.085 |
www | +0.085 |
ths | +0.084 |
ister | +0.082 |
sermon | +0.081 |
Neg logit contributions | |
like | -0.027 |
everywhere | -0.010 |
but | -0.010 |
and | -0.010 |
all | -0.009 |
Token | she |
Token ID | 673 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
ww | +0.026 |
ister | +0.026 |
www | +0.026 |
ths | +0.025 |
vation | +0.025 |
Neg logit contributions | |
like | -0.012 |
liked | -0.006 |
all | -0.006 |
everywhere | -0.006 |
favorite | -0.006 |
Token | Red |
Token ID | 7738 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ister | +0.020 |
ww | +0.020 |
ths | +0.020 |
www | +0.019 |
service | +0.019 |
Neg logit contributions | |
like | -0.021 |
everywhere | -0.015 |
liked | -0.015 |
favorite | -0.015 |
around | -0.014 |
Token | thought |
Token ID | 1807 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
avail | +0.036 |
ister | +0.036 |
ww | +0.035 |
ths | +0.035 |
service | +0.035 |
Neg logit contributions | |
like | -0.023 |
liked | -0.017 |
favorite | -0.014 |
everywhere | -0.014 |
around | -0.014 |
Token | about |
Token ID | 546 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
ww | +0.021 |
ister | +0.021 |
ths | +0.021 |
www | +0.021 |
avail | +0.021 |
Neg logit contributions | |
like | -0.013 |
everywhere | -0.008 |
favorite | -0.008 |
liked | -0.008 |
around | -0.007 |
Token | what |
Token ID | 644 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
ister | +0.021 |
ww | +0.021 |
ths | +0.021 |
www | +0.020 |
avail | +0.020 |
Neg logit contributions | |
like | -0.013 |
everywhere | -0.008 |
liked | -0.008 |
favorite | -0.008 |
all | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
ister | +0.001 |
ths | +0.001 |
ww | +0.001 |
www | +0.001 |
avail | +0.001 |
Neg logit contributions | |
like | -0.001 |
liked | -0.000 |
favorite | -0.000 |
everywhere | -0.000 |
all | -0.000 |
Token | m |
Token ID | 285 |
Feature activation | +9.20e+00 |
Pos logit contributions | |
ister | +0.024 |
ww | +0.024 |
ths | +0.024 |
keys | +0.023 |
avail | +0.023 |
Neg logit contributions | |
like | -0.020 |
favorite | -0.014 |
liked | -0.014 |
everywhere | -0.013 |
dolls | -0.013 |
Token | op |
Token ID | 404 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
avail | +0.256 |
ww | +0.224 |
hawk | +0.218 |
ation | +0.215 |
storm | +0.213 |
Neg logit contributions | |
like | -0.185 |
favorite | -0.147 |
dolls | -0.141 |
aces | -0.136 |
liked | -0.133 |
Token | had |
Token ID | 550 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
avail | +0.105 |
ww | +0.104 |
ths | +0.102 |
ister | +0.100 |
www | +0.099 |
Neg logit contributions | |
like | -0.067 |
liked | -0.046 |
everywhere | -0.043 |
around | -0.042 |
favorite | -0.040 |
Token | said |
Token ID | 531 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
like | +0.046 |
favorite | +0.034 |
everywhere | +0.034 |
liked | +0.034 |
dolls | +0.032 |
Neg logit contributions | |
ister | -0.047 |
ww | -0.047 |
www | -0.046 |
ths | -0.046 |
service | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
like | +0.017 |
favorite | +0.010 |
everywhere | +0.010 |
liked | +0.009 |
dolls | +0.008 |
Neg logit contributions | |
ister | -0.043 |
service | -0.041 |
ths | -0.041 |
ww | -0.041 |
www | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
like | +0.052 |
everywhere | +0.025 |
favorite | +0.024 |
liked | +0.023 |
dolls | +0.018 |
Neg logit contributions | |
ister | -0.154 |
ww | -0.154 |
ths | -0.152 |
www | -0.151 |
service | -0.148 |
Token | day |
Token ID | 1110 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
ister | +0.017 |
ths | +0.017 |
avail | +0.017 |
ww | +0.017 |
www | +0.016 |
Neg logit contributions | |
like | -0.019 |
everywhere | -0.015 |
liked | -0.014 |
favorite | -0.014 |
around | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ister | +0.002 |
ww | +0.002 |
ths | +0.002 |
www | +0.002 |
avail | +0.002 |
Neg logit contributions | |
like | -0.001 |
everywhere | -0.000 |
liked | -0.000 |
favorite | -0.000 |
both | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
ister | +0.051 |
ww | +0.051 |
ths | +0.051 |
sermon | +0.051 |
www | +0.051 |
Neg logit contributions | |
like | -0.020 |
everywhere | -0.011 |
liked | -0.009 |
favorite | -0.009 |
around | -0.008 |
Token | whenever |
Token ID | 8797 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ww | +0.025 |
ths | +0.025 |
storm | +0.024 |
www | +0.023 |
body | +0.023 |
Neg logit contributions | |
like | -0.016 |
pad | -0.014 |
aces | -0.014 |
ti | -0.011 |
tie | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ister | +0.104 |
ww | +0.103 |
ths | +0.102 |
www | +0.101 |
sermon | +0.099 |
Neg logit contributions | |
like | -0.034 |
everywhere | -0.015 |
liked | -0.015 |
favorite | -0.015 |
dolls | -0.012 |
Token | m |
Token ID | 285 |
Feature activation | +9.17e+00 |
Pos logit contributions | |
ister | +0.046 |
ww | +0.046 |
ths | +0.045 |
www | +0.044 |
avail | +0.044 |
Neg logit contributions | |
like | -0.045 |
favorite | -0.033 |
liked | -0.033 |
everywhere | -0.032 |
dolls | -0.031 |
Token | op |
Token ID | 404 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
avail | +0.267 |
ww | +0.232 |
www | +0.219 |
storm | +0.215 |
hawk | +0.215 |
Neg logit contributions | |
like | -0.177 |
favorite | -0.145 |
dolls | -0.144 |
liked | -0.133 |
both | -0.133 |
Token | wasn |
Token ID | 2492 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
avail | +0.128 |
ww | +0.124 |
www | +0.119 |
ths | +0.115 |
izing | +0.114 |
Neg logit contributions | |
like | -0.082 |
liked | -0.062 |
around | -0.056 |
everywhere | -0.054 |
all | -0.053 |
Token | 't |
Token ID | 470 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
ww | +0.076 |
ths | +0.075 |
avail | +0.074 |
www | +0.074 |
service | +0.072 |
Neg logit contributions | |
like | -0.098 |
everywhere | -0.073 |
both | -0.073 |
all | -0.071 |
favorite | -0.070 |
Token | available |
Token ID | 1695 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ister | +0.027 |
ww | +0.027 |
ths | +0.026 |
www | +0.026 |
service | +0.025 |
Neg logit contributions | |
like | -0.021 |
everywhere | -0.014 |
liked | -0.014 |
favorite | -0.014 |
around | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
like | +0.004 |
liked | +0.003 |
favorite | +0.003 |
everywhere | +0.003 |
pad | +0.002 |
Neg logit contributions | |
ister | -0.008 |
ths | -0.008 |
ww | -0.008 |
service | -0.008 |
www | -0.008 |
Token | all |
Token ID | 477 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
like | +0.003 |
everywhere | +0.002 |
favorite | +0.002 |
liked | +0.002 |
pad | +0.002 |
Neg logit contributions | |
ister | -0.005 |
ths | -0.005 |
ww | -0.005 |
service | -0.005 |
www | -0.005 |
Token | clean |
Token ID | 3424 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ww | +0.005 |
ister | +0.005 |
ths | +0.004 |
www | +0.004 |
service | +0.004 |
Neg logit contributions | |
like | -0.003 |
favorite | -0.002 |
everywhere | -0.002 |
liked | -0.002 |
pad | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
like | +0.019 |
everywhere | +0.009 |
favorite | +0.009 |
liked | +0.009 |
pad | +0.007 |
Neg logit contributions | |
ister | -0.054 |
ww | -0.053 |
ths | -0.053 |
www | -0.052 |
service | -0.052 |
Token | After |
Token ID | 2293 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ister | +0.025 |
ww | +0.025 |
ths | +0.025 |
www | +0.025 |
service | +0.024 |
Neg logit contributions | |
like | -0.017 |
everywhere | -0.011 |
favorite | -0.011 |
liked | -0.011 |
dolls | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ister | +0.087 |
ww | +0.086 |
www | +0.086 |
avail | +0.084 |
asis | +0.082 |
Neg logit contributions | |
like | -0.032 |
all | -0.018 |
everywhere | -0.017 |
both | -0.016 |
liked | -0.014 |
Token | m |
Token ID | 285 |
Feature activation | +9.10e+00 |
Pos logit contributions | |
ister | +0.027 |
ww | +0.027 |
avail | +0.027 |
ths | +0.027 |
www | +0.026 |
Neg logit contributions | |
like | -0.024 |
favorite | -0.018 |
love | -0.017 |
liked | -0.017 |
everywhere | -0.017 |
Token | op |
Token ID | 404 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
avail | +0.256 |
ww | +0.222 |
hawk | +0.214 |
storm | +0.214 |
ation | +0.210 |
Neg logit contributions | |
like | -0.184 |
favorite | -0.140 |
dolls | -0.132 |
both | -0.130 |
liked | -0.129 |
Token | had |
Token ID | 550 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
avail | +0.094 |
ww | +0.093 |
www | +0.091 |
ister | +0.090 |
ths | +0.088 |
Neg logit contributions | |
like | -0.052 |
liked | -0.035 |
everywhere | -0.033 |
around | -0.033 |
all | -0.032 |
Token | finished |
Token ID | 5201 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
like | +0.028 |
favorite | +0.021 |
everywhere | +0.021 |
liked | +0.021 |
wherever | +0.020 |
Neg logit contributions | |
ww | -0.024 |
ister | -0.024 |
ths | -0.024 |
www | -0.023 |
service | -0.023 |
Token | it |
Token ID | 340 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ww | +0.115 |
ister | +0.113 |
www | +0.113 |
ths | +0.109 |
beast | +0.108 |
Neg logit contributions | |
like | -0.051 |
everywhere | -0.029 |
favorite | -0.027 |
liked | -0.026 |
all | -0.025 |
Token | would |
Token ID | 561 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ww | +0.054 |
ister | +0.054 |
www | +0.053 |
ths | +0.052 |
avail | +0.052 |
Neg logit contributions | |
like | -0.020 |
everywhere | -0.011 |
favorite | -0.009 |
liked | -0.009 |
back | -0.008 |
Token | room |
Token ID | 2119 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
like | +0.016 |
everywhere | +0.012 |
favorite | +0.012 |
liked | +0.012 |
around | +0.011 |
Neg logit contributions | |
ister | -0.015 |
ww | -0.015 |
ths | -0.014 |
www | -0.014 |
service | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
like | +0.007 |
pad | +0.004 |
everywhere | +0.004 |
favorite | +0.004 |
aces | +0.004 |
Neg logit contributions | |
ister | -0.017 |
service | -0.017 |
ww | -0.016 |
ths | -0.016 |
www | -0.016 |
Token | Every |
Token ID | 3887 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
ister | +0.011 |
ww | +0.011 |
www | +0.011 |
ths | +0.011 |
service | +0.011 |
Neg logit contributions | |
like | -0.008 |
everywhere | -0.005 |
favorite | -0.005 |
liked | -0.005 |
back | -0.005 |
Token | morning |
Token ID | 3329 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
keys | +0.111 |
ths | +0.108 |
izing | +0.107 |
avail | +0.106 |
irens | +0.106 |
Neg logit contributions | |
like | -0.069 |
liked | -0.051 |
favorite | -0.050 |
all | -0.046 |
everywhere | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ister | +0.108 |
ths | +0.107 |
ww | +0.107 |
www | +0.105 |
avail | +0.103 |
Neg logit contributions | |
like | -0.048 |
liked | -0.026 |
everywhere | -0.026 |
favorite | -0.024 |
around | -0.022 |
Token | m |
Token ID | 285 |
Feature activation | +9.04e+00 |
Pos logit contributions | |
ister | +0.048 |
ww | +0.047 |
ths | +0.047 |
avail | +0.047 |
www | +0.046 |
Neg logit contributions | |
like | -0.042 |
favorite | -0.031 |
liked | -0.031 |
everywhere | -0.030 |
dolls | -0.029 |
Token | op |
Token ID | 404 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
avail | +0.259 |
ww | +0.223 |
storm | +0.221 |
service | +0.214 |
www | +0.211 |
Neg logit contributions | |
like | -0.183 |
favorite | -0.143 |
dolls | -0.138 |
liked | -0.134 |
both | -0.132 |
Token | would |
Token ID | 561 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ww | +0.113 |
avail | +0.113 |
www | +0.111 |
ister | +0.110 |
ths | +0.109 |
Neg logit contributions | |
like | -0.063 |
liked | -0.043 |
everywhere | -0.040 |
favorite | -0.038 |
around | -0.038 |
Token | wake |
Token ID | 7765 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ww | +0.072 |
ths | +0.071 |
ister | +0.070 |
www | +0.069 |
avail | +0.067 |
Neg logit contributions | |
like | -0.061 |
liked | -0.042 |
everywhere | -0.041 |
favorite | -0.040 |
all | -0.038 |
Token | up |
Token ID | 510 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ww | +0.100 |
www | +0.097 |
ister | +0.097 |
ths | +0.096 |
service | +0.093 |
Neg logit contributions | |
like | -0.042 |
everywhere | -0.022 |
favorite | -0.022 |
around | -0.022 |
all | -0.022 |
Token | ready |
Token ID | 3492 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
ww | +0.010 |
ister | +0.010 |
www | +0.010 |
ths | +0.010 |
avail | +0.009 |
Neg logit contributions | |
like | -0.005 |
everywhere | -0.003 |
favorite | -0.003 |
liked | -0.003 |
all | -0.002 |
Token | while |
Token ID | 981 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ister | +0.046 |
ww | +0.043 |
irens | +0.043 |
ths | +0.043 |
keys | +0.042 |
Neg logit contributions | |
like | -0.024 |
but | -0.013 |
everywhere | -0.012 |
around | -0.012 |
liked | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ww | +0.116 |
ister | +0.115 |
www | +0.115 |
sermon | +0.113 |
ths | +0.112 |
Neg logit contributions | |
like | -0.043 |
everywhere | -0.022 |
around | -0.018 |
wherever | -0.018 |
all | -0.018 |
Token | sure |
Token ID | 1654 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
ister | +0.035 |
ww | +0.034 |
www | +0.033 |
ths | +0.033 |
service | +0.033 |
Neg logit contributions | |
like | -0.026 |
everywhere | -0.018 |
favorite | -0.017 |
liked | -0.017 |
around | -0.017 |
Token | enough |
Token ID | 1576 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
ths | +0.062 |
sermon | +0.059 |
ister | +0.059 |
izing | +0.059 |
ww | +0.059 |
Neg logit contributions | |
like | -0.045 |
all | -0.032 |
found | -0.032 |
everywhere | -0.031 |
back | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ww | +0.112 |
ister | +0.112 |
ths | +0.111 |
www | +0.110 |
sermon | +0.109 |
Neg logit contributions | |
like | -0.044 |
everywhere | -0.024 |
favorite | -0.020 |
liked | -0.020 |
wherever | -0.019 |
Token | m |
Token ID | 285 |
Feature activation | +8.98e+00 |
Pos logit contributions | |
avail | +0.060 |
ww | +0.060 |
www | +0.060 |
ths | +0.060 |
ister | +0.060 |
Neg logit contributions | |
like | -0.060 |
favorite | -0.046 |
back | -0.045 |
love | -0.045 |
liked | -0.044 |
Token | itten |
Token ID | 2621 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
avail | +0.156 |
ww | +0.126 |
www | +0.120 |
izing | +0.111 |
ation | +0.106 |
Neg logit contributions | |
like | -0.269 |
favorite | -0.238 |
aces | -0.231 |
pad | -0.223 |
back | -0.222 |
Token | floated |
Token ID | 29742 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ww | +0.146 |
avail | +0.145 |
ister | +0.144 |
www | +0.142 |
ths | +0.140 |
Neg logit contributions | |
like | -0.098 |
liked | -0.069 |
everywhere | -0.066 |
favorite | -0.064 |
around | -0.063 |
Token | down |
Token ID | 866 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ister | +0.010 |
ww | +0.010 |
ths | +0.010 |
www | +0.010 |
avail | +0.010 |
Neg logit contributions | |
like | -0.006 |
favorite | -0.004 |
dolls | -0.004 |
liked | -0.004 |
aces | -0.004 |
Token | out |
Token ID | 503 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ister | +0.011 |
ww | +0.011 |
ths | +0.011 |
www | +0.011 |
service | +0.010 |
Neg logit contributions | |
like | -0.005 |
favorite | -0.003 |
liked | -0.003 |
everywhere | -0.003 |
dolls | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
like | +0.010 |
everywhere | +0.006 |
liked | +0.006 |
favorite | +0.006 |
around | +0.006 |
Neg logit contributions | |
ww | -0.015 |
ister | -0.015 |
www | -0.015 |
ths | -0.015 |
avail | -0.015 |
Token | before |
Token ID | 878 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
ww | +0.103 |
ister | +0.102 |
ths | +0.101 |
www | +0.100 |
avail | +0.099 |
Neg logit contributions | |
like | -0.034 |
everywhere | -0.015 |
liked | -0.015 |
favorite | -0.014 |
around | -0.012 |
Token | heading |
Token ID | 9087 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ww | +0.091 |
www | +0.088 |
ths | +0.086 |
ister | +0.086 |
body | +0.085 |
Neg logit contributions | |
like | -0.069 |
everywhere | -0.048 |
all | -0.047 |
both | -0.045 |
but | -0.044 |
Token | home |
Token ID | 1363 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ister | +0.041 |
ww | +0.041 |
ths | +0.040 |
www | +0.040 |
service | +0.040 |
Neg logit contributions | |
like | -0.020 |
liked | -0.012 |
favorite | -0.012 |
everywhere | -0.012 |
dolls | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ww | +0.083 |
ister | +0.082 |
ths | +0.081 |
www | +0.081 |
avail | +0.079 |
Neg logit contributions | |
like | -0.024 |
everywhere | -0.010 |
favorite | -0.009 |
liked | -0.009 |
around | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ister | +0.034 |
ww | +0.034 |
ths | +0.034 |
www | +0.033 |
service | +0.032 |
Neg logit contributions | |
like | -0.025 |
everywhere | -0.017 |
liked | -0.017 |
favorite | -0.017 |
wherever | -0.015 |
Token | m |
Token ID | 285 |
Feature activation | +8.93e+00 |
Pos logit contributions | |
ister | +0.033 |
ww | +0.032 |
ths | +0.032 |
avail | +0.032 |
www | +0.031 |
Neg logit contributions | |
like | -0.030 |
liked | -0.022 |
favorite | -0.022 |
everywhere | -0.022 |
back | -0.021 |
Token | ule |
Token ID | 2261 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
avail | +0.142 |
ww | +0.120 |
storm | +0.115 |
www | +0.100 |
ths | +0.094 |
Neg logit contributions | |
like | -0.276 |
liked | -0.236 |
favorite | -0.236 |
and | -0.232 |
pad | -0.232 |
Token | was |
Token ID | 373 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
avail | +0.142 |
ww | +0.141 |
ister | +0.139 |
www | +0.135 |
ths | +0.133 |
Neg logit contributions | |
like | -0.082 |
liked | -0.061 |
favorite | -0.051 |
everywhere | -0.051 |
around | -0.050 |
Token | friendly |
Token ID | 8030 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ister | +0.045 |
ww | +0.044 |
ths | +0.044 |
www | +0.043 |
service | +0.042 |
Neg logit contributions | |
like | -0.026 |
everywhere | -0.017 |
favorite | -0.016 |
liked | -0.016 |
around | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
like | +0.024 |
favorite | +0.017 |
liked | +0.014 |
everywhere | +0.014 |
aces | +0.014 |
Neg logit contributions | |
service | -0.056 |
ister | -0.056 |
ths | -0.056 |
ww | -0.054 |
beast | -0.054 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ister | +0.046 |
ww | +0.044 |
ths | +0.043 |
irens | +0.043 |
avail | +0.043 |
Neg logit contributions | |
like | -0.030 |
liked | -0.021 |
favorite | -0.019 |
everywhere | -0.019 |
all | -0.018 |
Token | ! |
Token ID | 0 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
ister | +0.090 |
ww | +0.090 |
ths | +0.089 |
www | +0.088 |
avail | +0.086 |
Neg logit contributions | |
like | -0.026 |
everywhere | -0.010 |
favorite | -0.009 |
liked | -0.009 |
around | -0.006 |
Token | |
Token ID | 220 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ister | +0.027 |
ww | +0.027 |
ths | +0.026 |
www | +0.026 |
service | +0.026 |
Neg logit contributions | |
like | -0.013 |
everywhere | -0.008 |
favorite | -0.008 |
liked | -0.008 |
around | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ister | +0.006 |
ama | +0.006 |
oo | +0.006 |
ww | +0.006 |
iren | +0.006 |
Neg logit contributions | |
like | -0.005 |
liked | -0.003 |
favorite | -0.003 |
pad | -0.003 |
ti | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
like | +0.003 |
favorite | +0.002 |
everywhere | +0.002 |
liked | +0.002 |
aces | +0.002 |
Neg logit contributions | |
ister | -0.006 |
ww | -0.006 |
www | -0.006 |
ths | -0.006 |
service | -0.006 |
Token | The |
Token ID | 464 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ister | +0.015 |
ww | +0.015 |
www | +0.014 |
ths | +0.014 |
service | +0.014 |
Neg logit contributions | |
like | -0.015 |
everywhere | -0.011 |
favorite | -0.011 |
liked | -0.011 |
back | -0.011 |
Token | m |
Token ID | 285 |
Feature activation | +8.84e+00 |
Pos logit contributions | |
ister | +0.033 |
ww | +0.033 |
ths | +0.032 |
www | +0.032 |
avail | +0.032 |
Neg logit contributions | |
like | -0.033 |
favorite | -0.024 |
liked | -0.024 |
everywhere | -0.024 |
dolls | -0.022 |
Token | op |
Token ID | 404 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
avail | +0.234 |
ww | +0.206 |
storm | +0.203 |
service | +0.196 |
www | +0.193 |
Neg logit contributions | |
like | -0.195 |
favorite | -0.152 |
dolls | -0.147 |
liked | -0.147 |
everywhere | -0.141 |
Token | would |
Token ID | 561 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
avail | +0.101 |
ww | +0.101 |
www | +0.098 |
ister | +0.097 |
ths | +0.097 |
Neg logit contributions | |
like | -0.059 |
liked | -0.042 |
everywhere | -0.037 |
favorite | -0.036 |
around | -0.036 |
Token | enjoy |
Token ID | 2883 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
ww | +0.060 |
ister | +0.059 |
ths | +0.059 |
www | +0.057 |
avail | +0.056 |
Neg logit contributions | |
like | -0.050 |
liked | -0.035 |
everywhere | -0.034 |
favorite | -0.033 |
both | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ister | +0.020 |
ww | +0.020 |
ths | +0.019 |
www | +0.019 |
service | +0.019 |
Neg logit contributions | |
like | -0.012 |
everywhere | -0.008 |
favorite | -0.008 |
liked | -0.008 |
around | -0.007 |
Token | bright |
Token ID | 6016 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
like | +0.026 |
favorite | +0.019 |
everywhere | +0.018 |
liked | +0.018 |
love | +0.018 |
Neg logit contributions | |
ths | -0.026 |
ister | -0.026 |
ww | -0.025 |
avail | -0.024 |
www | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
keys | +0.072 |
www | +0.072 |
ister | +0.072 |
ww | +0.072 |
sermon | +0.071 |
Neg logit contributions | |
like | -0.027 |
all | -0.020 |
everywhere | -0.017 |
both | -0.017 |
where | -0.015 |
Token | next |
Token ID | 1306 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ister | +0.061 |
ww | +0.058 |
www | +0.057 |
keys | +0.056 |
ment | +0.056 |
Neg logit contributions | |
like | -0.031 |
favorite | -0.025 |
everywhere | -0.024 |
back | -0.024 |
t | -0.024 |
Token | morning |
Token ID | 3329 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
avail | +0.076 |
eling | +0.076 |
wen | +0.076 |
vation | +0.075 |
ister | +0.075 |
Neg logit contributions | |
like | -0.057 |
in | -0.041 |
favorite | -0.040 |
and | -0.040 |
but | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
ths | +0.139 |
ister | +0.132 |
avail | +0.131 |
ww | +0.130 |
www | +0.130 |
Neg logit contributions | |
like | -0.043 |
everywhere | -0.017 |
liked | -0.016 |
and | -0.013 |
around | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ww | +0.024 |
ister | +0.024 |
www | +0.024 |
ths | +0.024 |
sermon | +0.023 |
Neg logit contributions | |
like | -0.009 |
liked | -0.005 |
everywhere | -0.004 |
all | -0.004 |
both | -0.004 |
Token | m |
Token ID | 285 |
Feature activation | +8.78e+00 |
Pos logit contributions | |
ister | +0.033 |
ww | +0.033 |
irens | +0.032 |
ths | +0.032 |
www | +0.032 |
Neg logit contributions | |
like | -0.022 |
favorite | -0.017 |
t | -0.017 |
everywhere | -0.016 |
back | -0.016 |
Token | ama |
Token ID | 1689 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
avail | +0.141 |
ww | +0.114 |
storm | +0.110 |
site | +0.106 |
canyon | +0.105 |
Neg logit contributions | |
like | -0.262 |
favorite | -0.241 |
liked | -0.224 |
t | -0.217 |
and | -0.217 |
Token | woke |
Token ID | 19092 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
avail | +0.140 |
ister | +0.137 |
ww | +0.136 |
ths | +0.135 |
www | +0.134 |
Neg logit contributions | |
like | -0.086 |
liked | -0.060 |
everywhere | -0.055 |
favorite | -0.053 |
found | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ww | +0.120 |
ister | +0.116 |
www | +0.116 |
outage | +0.115 |
service | +0.114 |
Neg logit contributions | |
like | -0.042 |
everywhere | -0.024 |
all | -0.023 |
around | -0.022 |
back | -0.021 |
Token | baby |
Token ID | 5156 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
like | +0.033 |
favorite | +0.025 |
everywhere | +0.023 |
t | +0.023 |
love | +0.023 |
Neg logit contributions | |
ister | -0.038 |
ww | -0.038 |
ths | -0.038 |
irens | -0.037 |
www | -0.037 |
Token | up |
Token ID | 510 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ww | +0.117 |
ister | +0.114 |
www | +0.114 |
avail | +0.110 |
irens | +0.108 |
Neg logit contributions | |
like | -0.068 |
everywhere | -0.046 |
liked | -0.046 |
back | -0.045 |
around | -0.043 |
Token | that |
Token ID | 326 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
avail | +0.013 |
ww | +0.013 |
ister | +0.013 |
www | +0.013 |
sermon | +0.013 |
Neg logit contributions | |
like | -0.010 |
everywhere | -0.007 |
liked | -0.007 |
around | -0.007 |
favorite | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ister | +0.045 |
ths | +0.044 |
ww | +0.043 |
www | +0.042 |
avail | +0.042 |
Neg logit contributions | |
like | -0.056 |
everywhere | -0.043 |
liked | -0.042 |
favorite | -0.042 |
around | -0.040 |
Token | forward |
Token ID | 2651 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ister | +0.011 |
ths | +0.011 |
ww | +0.011 |
www | +0.010 |
avail | +0.010 |
Neg logit contributions | |
like | -0.004 |
everywhere | -0.002 |
liked | -0.002 |
favorite | -0.002 |
around | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ister | +0.105 |
sermon | +0.102 |
www | +0.102 |
ww | +0.102 |
ths | +0.101 |
Neg logit contributions | |
like | -0.035 |
liked | -0.016 |
everywhere | -0.015 |
back | -0.014 |
around | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ister | +0.056 |
ww | +0.055 |
ths | +0.055 |
www | +0.054 |
service | +0.053 |
Neg logit contributions | |
like | -0.030 |
everywhere | -0.018 |
favorite | -0.018 |
liked | -0.018 |
wherever | -0.016 |
Token | m |
Token ID | 285 |
Feature activation | +8.78e+00 |
Pos logit contributions | |
ister | +0.040 |
ww | +0.040 |
ths | +0.040 |
www | +0.039 |
avail | +0.039 |
Neg logit contributions | |
like | -0.030 |
favorite | -0.021 |
liked | -0.021 |
everywhere | -0.021 |
back | -0.019 |
Token | ule |
Token ID | 2261 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
avail | +0.122 |
ww | +0.098 |
storm | +0.092 |
www | +0.088 |
ths | +0.085 |
Neg logit contributions | |
like | -0.295 |
favorite | -0.253 |
liked | -0.249 |
and | -0.242 |
pad | -0.239 |
Token | and |
Token ID | 290 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
ister | +0.130 |
ww | +0.129 |
ths | +0.128 |
www | +0.126 |
service | +0.124 |
Neg logit contributions | |
like | -0.064 |
everywhere | -0.038 |
favorite | -0.037 |
liked | -0.037 |
around | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
ister | +0.026 |
ww | +0.026 |
ths | +0.025 |
www | +0.025 |
service | +0.025 |
Neg logit contributions | |
like | -0.012 |
everywhere | -0.007 |
liked | -0.007 |
favorite | -0.007 |
around | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
ister | +0.011 |
ww | +0.011 |
ths | +0.011 |
www | +0.011 |
avail | +0.011 |
Neg logit contributions | |
like | -0.008 |
favorite | -0.006 |
liked | -0.006 |
everywhere | -0.006 |
back | -0.005 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ister | +0.051 |
ww | +0.051 |
ths | +0.050 |
www | +0.050 |
service | +0.048 |
Neg logit contributions | |
like | -0.047 |
liked | -0.033 |
favorite | -0.033 |
everywhere | -0.033 |
back | -0.031 |
Token | itten |
Token ID | 2621 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
avail | +0.154 |
hawk | +0.137 |
beast | +0.136 |
storm | +0.135 |
ww | +0.133 |
Neg logit contributions | |
like | -0.175 |
favorite | -0.137 |
. | -0.133 |
both | -0.132 |
aces | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
ww | +0.092 |
ister | +0.091 |
ths | +0.090 |
avail | +0.090 |
www | +0.090 |
Neg logit contributions | |
like | -0.023 |
everywhere | -0.007 |
liked | -0.005 |
favorite | -0.005 |
around | -0.005 |
Token | Now |
Token ID | 2735 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ister | +0.028 |
ww | +0.028 |
ths | +0.027 |
www | +0.027 |
service | +0.027 |
Neg logit contributions | |
like | -0.017 |
liked | -0.011 |
favorite | -0.011 |
everywhere | -0.011 |
both | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
ister | +0.047 |
ww | +0.047 |
ths | +0.046 |
www | +0.046 |
service | +0.045 |
Neg logit contributions | |
like | -0.030 |
everywhere | -0.019 |
liked | -0.019 |
favorite | -0.019 |
around | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ister | +0.087 |
ths | +0.085 |
ww | +0.085 |
www | +0.084 |
irens | +0.083 |
Neg logit contributions | |
like | -0.051 |
liked | -0.031 |
everywhere | -0.031 |
favorite | -0.031 |
all | -0.029 |
Token | m |
Token ID | 285 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
ister | +0.035 |
ww | +0.034 |
ths | +0.034 |
www | +0.033 |
avail | +0.033 |
Neg logit contributions | |
like | -0.029 |
favorite | -0.021 |
everywhere | -0.021 |
liked | -0.021 |
dolls | -0.019 |
Token | itten |
Token ID | 2621 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
avail | +0.168 |
ww | +0.139 |
storm | +0.138 |
service | +0.133 |
ths | +0.132 |
Neg logit contributions | |
like | -0.251 |
favorite | -0.212 |
liked | -0.202 |
dolls | -0.198 |
pad | -0.197 |
Token | was |
Token ID | 373 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ister | +0.127 |
ww | +0.127 |
ths | +0.125 |
avail | +0.124 |
www | +0.123 |
Neg logit contributions | |
like | -0.080 |
liked | -0.053 |
everywhere | -0.051 |
favorite | -0.051 |
around | -0.047 |
Token | full |
Token ID | 1336 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ww | +0.046 |
ister | +0.046 |
ths | +0.046 |
www | +0.045 |
storm | +0.045 |
Neg logit contributions | |
like | -0.036 |
liked | -0.026 |
favorite | -0.025 |
everywhere | -0.025 |
pad | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
like | +0.033 |
favorite | +0.027 |
liked | +0.026 |
everywhere | +0.025 |
dolls | +0.025 |
Neg logit contributions | |
ister | -0.032 |
service | -0.031 |
ww | -0.031 |
storm | -0.030 |
www | -0.030 |
Token | Daddy |
Token ID | 26926 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
like | +0.012 |
everywhere | +0.007 |
favorite | +0.007 |
liked | +0.007 |
around | +0.006 |
Neg logit contributions | |
ister | -0.027 |
ww | -0.027 |
ths | -0.026 |
www | -0.026 |
service | -0.026 |
Token | 's |
Token ID | 338 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
ister | +0.022 |
ww | +0.022 |
ths | +0.022 |
avail | +0.022 |
www | +0.022 |
Neg logit contributions | |
like | -0.011 |
liked | -0.006 |
everywhere | -0.006 |
favorite | -0.006 |
around | -0.005 |
Token | cleaning |
Token ID | 12724 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
ww | +0.020 |
ister | +0.020 |
www | +0.020 |
ths | +0.020 |
avail | +0.019 |
Neg logit contributions | |
like | -0.021 |
favorite | -0.015 |
everywhere | -0.015 |
liked | -0.015 |
back | -0.014 |
Token | adventure |
Token ID | 8855 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ww | +0.029 |
ister | +0.028 |
www | +0.028 |
ths | +0.028 |
avail | +0.027 |
Neg logit contributions | |
like | -0.015 |
everywhere | -0.010 |
favorite | -0.009 |
liked | -0.009 |
around | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ister | +0.066 |
ww | +0.066 |
ths | +0.065 |
www | +0.064 |
avail | +0.063 |
Neg logit contributions | |
like | -0.023 |
everywhere | -0.011 |
liked | -0.010 |
favorite | -0.010 |
around | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ister | +0.039 |
ww | +0.039 |
ths | +0.039 |
www | +0.038 |
avail | +0.037 |
Neg logit contributions | |
like | -0.021 |
everywhere | -0.013 |
liked | -0.013 |
favorite | -0.012 |
wherever | -0.011 |
Token | m |
Token ID | 285 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
ister | +0.031 |
ww | +0.031 |
ths | +0.030 |
www | +0.030 |
avail | +0.029 |
Neg logit contributions | |
like | -0.030 |
everywhere | -0.022 |
favorite | -0.022 |
liked | -0.022 |
dolls | -0.020 |
Token | op |
Token ID | 404 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
avail | +0.220 |
ww | +0.186 |
storm | +0.176 |
hawk | +0.171 |
www | +0.171 |
Neg logit contributions | |
like | -0.204 |
favorite | -0.165 |
liked | -0.161 |
dolls | -0.154 |
and | -0.152 |
Token | had |
Token ID | 550 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
avail | +0.087 |
ww | +0.087 |
ister | +0.085 |
www | +0.084 |
ths | +0.084 |
Neg logit contributions | |
like | -0.053 |
liked | -0.037 |
everywhere | -0.034 |
around | -0.033 |
favorite | -0.032 |
Token | been |
Token ID | 587 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
like | +0.030 |
everywhere | +0.021 |
favorite | +0.021 |
liked | +0.020 |
around | +0.019 |
Neg logit contributions | |
ister | -0.039 |
ww | -0.039 |
ths | -0.038 |
www | -0.038 |
service | -0.037 |
Token | released |
Token ID | 2716 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
ister | +0.039 |
ww | +0.039 |
ths | +0.038 |
www | +0.038 |
service | +0.037 |
Neg logit contributions | |
like | -0.029 |
everywhere | -0.020 |
favorite | -0.019 |
liked | -0.019 |
around | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
like | +0.012 |
favorite | +0.008 |
liked | +0.008 |
dolls | +0.008 |
everywhere | +0.007 |
Neg logit contributions | |
ister | -0.026 |
ww | -0.025 |
ths | -0.025 |
service | -0.025 |
www | -0.024 |
Token | cream |
Token ID | 8566 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ister | +0.005 |
ww | +0.005 |
ths | +0.005 |
www | +0.005 |
service | +0.005 |
Neg logit contributions | |
like | -0.007 |
everywhere | -0.006 |
liked | -0.006 |
favorite | -0.006 |
wherever | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
like | +0.038 |
everywhere | +0.025 |
favorite | +0.024 |
liked | +0.024 |
dolls | +0.022 |
Neg logit contributions | |
ister | -0.063 |
ww | -0.062 |
ths | -0.061 |
www | -0.061 |
service | -0.059 |
Token | â |
Token ID | 22940 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
ister | +0.020 |
ww | +0.020 |
www | +0.020 |
ths | +0.020 |
service | +0.019 |
Neg logit contributions | |
like | -0.016 |
everywhere | -0.011 |
favorite | -0.011 |
liked | -0.011 |
around | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ths | +0.068 |
avail | +0.066 |
ww | +0.065 |
ister | +0.065 |
storm | +0.064 |
Neg logit contributions | |
like | -0.108 |
liked | -0.084 |
around | -0.080 |
back | -0.076 |
everywhere | -0.076 |
Token | The |
Token ID | 383 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ister | +0.028 |
ww | +0.027 |
www | +0.026 |
ths | +0.025 |
service | +0.025 |
Neg logit contributions | |
like | -0.029 |
everywhere | -0.023 |
favorite | -0.022 |
liked | -0.021 |
back | -0.021 |
Token | m |
Token ID | 285 |
Feature activation | +8.75e+00 |
Pos logit contributions | |
ister | +0.036 |
ths | +0.036 |
ww | +0.036 |
avail | +0.035 |
www | +0.035 |
Neg logit contributions | |
like | -0.033 |
favorite | -0.024 |
liked | -0.023 |
everywhere | -0.023 |
back | -0.021 |
Token | ama |
Token ID | 1689 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
avail | +0.126 |
storm | +0.106 |
ths | +0.102 |
ww | +0.101 |
izing | +0.096 |
Neg logit contributions | |
like | -0.289 |
favorite | -0.252 |
liked | -0.245 |
aces | -0.240 |
pad | -0.233 |
Token | said |
Token ID | 531 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
ister | +0.104 |
ww | +0.103 |
ths | +0.103 |
avail | +0.101 |
www | +0.100 |
Neg logit contributions | |
like | -0.089 |
liked | -0.063 |
everywhere | -0.062 |
favorite | -0.062 |
around | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
like | +0.007 |
everywhere | +0.005 |
favorite | +0.005 |
liked | +0.005 |
pad | +0.004 |
Neg logit contributions | |
ister | -0.013 |
ww | -0.013 |
www | -0.013 |
ths | -0.013 |
service | -0.013 |
Token | � |
Token ID | 6184 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
like | +0.047 |
everywhere | +0.022 |
favorite | +0.021 |
liked | +0.021 |
around | +0.016 |
Neg logit contributions | |
ister | -0.137 |
ww | -0.137 |
ths | -0.135 |
www | -0.134 |
service | -0.132 |
Token | � |
Token ID | 95 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ths | +0.042 |
ww | +0.041 |
ister | +0.041 |
avail | +0.041 |
storm | +0.040 |
Neg logit contributions | |
like | -0.065 |
liked | -0.049 |
favorite | -0.048 |
everywhere | -0.047 |
around | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ister | +0.047 |
ww | +0.047 |
ths | +0.046 |
www | +0.046 |
service | +0.045 |
Neg logit contributions | |
like | -0.016 |
favorite | -0.008 |
everywhere | -0.008 |
liked | -0.008 |
dolls | -0.006 |
Token | |
Token ID | 220 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
ww | +0.004 |
www | +0.004 |
sermon | +0.004 |
ister | +0.004 |
service | +0.004 |
Neg logit contributions | |
like | -0.003 |
everywhere | -0.002 |
favorite | -0.002 |
aces | -0.002 |
pad | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
like | +0.001 |
favorite | +0.001 |
liked | +0.001 |
pad | +0.001 |
ti | +0.001 |
Neg logit contributions | |
ister | -0.001 |
ama | -0.001 |
oo | -0.001 |
ww | -0.001 |
iren | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
like | +0.006 |
favorite | +0.004 |
everywhere | +0.004 |
aces | +0.004 |
pad | +0.004 |
Neg logit contributions | |
ister | -0.009 |
ww | -0.009 |
www | -0.009 |
sermon | -0.008 |
service | -0.008 |
Token | The |
Token ID | 464 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ww | +0.013 |
ister | +0.013 |
www | +0.013 |
sermon | +0.012 |
ths | +0.012 |
Neg logit contributions | |
like | -0.014 |
everywhere | -0.011 |
favorite | -0.010 |
liked | -0.010 |
wherever | -0.010 |
Token | m |
Token ID | 285 |
Feature activation | +8.73e+00 |
Pos logit contributions | |
ister | +0.036 |
ww | +0.035 |
ths | +0.035 |
www | +0.034 |
avail | +0.034 |
Neg logit contributions | |
like | -0.034 |
favorite | -0.025 |
liked | -0.025 |
everywhere | -0.025 |
dolls | -0.023 |
Token | ittens |
Token ID | 34978 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
avail | +0.161 |
ww | +0.141 |
storm | +0.133 |
ths | +0.133 |
www | +0.131 |
Neg logit contributions | |
like | -0.257 |
favorite | -0.216 |
liked | -0.209 |
dolls | -0.206 |
pad | -0.198 |
Token | were |
Token ID | 547 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
ww | +0.109 |
ister | +0.107 |
avail | +0.106 |
ths | +0.105 |
www | +0.105 |
Neg logit contributions | |
like | -0.066 |
liked | -0.045 |
everywhere | -0.043 |
favorite | -0.042 |
both | -0.039 |
Token | so |
Token ID | 523 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ww | +0.007 |
ister | +0.007 |
ths | +0.006 |
www | +0.006 |
service | +0.006 |
Neg logit contributions | |
like | -0.004 |
liked | -0.003 |
favorite | -0.003 |
everywhere | -0.003 |
pad | -0.002 |
Token | thin |
Token ID | 7888 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ths | +0.093 |
ister | +0.093 |
avail | +0.092 |
ww | +0.092 |
beast | +0.091 |
Neg logit contributions | |
like | -0.056 |
liked | -0.037 |
favorite | -0.037 |
everywhere | -0.035 |
both | -0.032 |
Token | ; |
Token ID | 26 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
like | +0.008 |
favorite | +0.006 |
liked | +0.005 |
everywhere | +0.005 |
dolls | +0.005 |
Neg logit contributions | |
ww | -0.011 |
ister | -0.011 |
ths | -0.011 |
www | -0.011 |
service | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ister | +0.065 |
ww | +0.065 |
www | +0.063 |
ths | +0.063 |
sermon | +0.061 |
Neg logit contributions | |
like | -0.051 |
everywhere | -0.035 |
liked | -0.034 |
favorite | -0.034 |
wherever | -0.032 |
Token | never |
Token ID | 1239 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ister | +0.029 |
ww | +0.029 |
ths | +0.028 |
www | +0.028 |
avail | +0.027 |
Neg logit contributions | |
like | -0.021 |
liked | -0.014 |
everywhere | -0.014 |
favorite | -0.014 |
around | -0.013 |
Token | forgot |
Token ID | 16453 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
ister | +0.048 |
ww | +0.048 |
ths | +0.047 |
www | +0.047 |
service | +0.046 |
Neg logit contributions | |
like | -0.035 |
liked | -0.023 |
everywhere | -0.023 |
favorite | -0.023 |
around | -0.021 |
Token | what |
Token ID | 644 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
like | +0.038 |
favorite | +0.025 |
liked | +0.025 |
pad | +0.024 |
everywhere | +0.023 |
Neg logit contributions | |
ister | -0.063 |
ths | -0.063 |
service | -0.062 |
storm | -0.062 |
ww | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
like | +0.021 |
everywhere | +0.015 |
favorite | +0.015 |
liked | +0.015 |
pad | +0.014 |
Neg logit contributions | |
ister | -0.024 |
ww | -0.024 |
ths | -0.023 |
www | -0.023 |
service | -0.023 |
Token | m |
Token ID | 285 |
Feature activation | +8.71e+00 |
Pos logit contributions | |
ister | +0.014 |
ww | +0.014 |
ths | +0.013 |
www | +0.013 |
avail | +0.013 |
Neg logit contributions | |
like | -0.016 |
favorite | -0.012 |
everywhere | -0.012 |
liked | -0.012 |
around | -0.011 |
Token | op |
Token ID | 404 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
avail | +0.140 |
ww | +0.119 |
ation | +0.108 |
ths | +0.105 |
www | +0.105 |
Neg logit contributions | |
like | -0.280 |
favorite | -0.237 |
pad | -0.226 |
liked | -0.225 |
. | -0.220 |
Token | taught |
Token ID | 7817 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ww | +0.094 |
avail | +0.093 |
ths | +0.092 |
ister | +0.091 |
www | +0.090 |
Neg logit contributions | |
like | -0.059 |
liked | -0.040 |
everywhere | -0.038 |
around | -0.036 |
favorite | -0.035 |
Token | him |
Token ID | 683 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ister | +0.041 |
ww | +0.041 |
ths | +0.040 |
www | +0.040 |
service | +0.039 |
Neg logit contributions | |
like | -0.024 |
favorite | -0.015 |
everywhere | -0.015 |
liked | -0.015 |
pad | -0.013 |
Token | � |
Token ID | 6184 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
like | +0.003 |
everywhere | +0.002 |
favorite | +0.002 |
liked | +0.002 |
dolls | +0.001 |
Neg logit contributions | |
ister | -0.009 |
ths | -0.009 |
ww | -0.009 |
service | -0.009 |
www | -0.009 |
Token | � |
Token ID | 95 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ww | +0.060 |
avail | +0.056 |
ths | +0.056 |
ister | +0.056 |
www | +0.055 |
Neg logit contributions | |
like | -0.083 |
liked | -0.060 |
favorite | -0.060 |
aces | -0.056 |
love | -0.056 |
Token | sharing |
Token ID | 7373 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ister | +0.057 |
ww | +0.057 |
www | +0.056 |
ths | +0.055 |
avail | +0.053 |
Neg logit contributions | |
like | -0.037 |
everywhere | -0.025 |
favorite | -0.024 |
liked | -0.024 |
all | -0.022 |
Token | is |
Token ID | 318 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
like | +0.032 |
favorite | +0.024 |
pad | +0.024 |
aces | +0.022 |
everywhere | +0.022 |
Neg logit contributions | |
ww | -0.035 |
ister | -0.035 |
ths | -0.034 |
service | -0.034 |
www | -0.033 |
Token | good |
Token ID | 922 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
ths | +0.019 |
ww | +0.019 |
ister | +0.018 |
www | +0.018 |
service | +0.018 |
Neg logit contributions | |
like | -0.019 |
pad | -0.016 |
aces | -0.015 |
everywhere | -0.015 |
liked | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
like | +0.022 |
favorite | +0.012 |
everywhere | +0.012 |
liked | +0.012 |
pad | +0.012 |
Neg logit contributions | |
ww | -0.050 |
ths | -0.049 |
ister | -0.049 |
www | -0.048 |
service | -0.048 |
Token | The |
Token ID | 383 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
ww | +0.009 |
ister | +0.009 |
ths | +0.009 |
www | +0.009 |
service | +0.009 |
Neg logit contributions | |
like | -0.005 |
everywhere | -0.003 |
favorite | -0.003 |
liked | -0.003 |
dolls | -0.003 |
Token | m |
Token ID | 285 |
Feature activation | +8.66e+00 |
Pos logit contributions | |
ister | +0.022 |
ww | +0.022 |
ths | +0.022 |
www | +0.021 |
avail | +0.021 |
Neg logit contributions | |
like | -0.022 |
everywhere | -0.016 |
favorite | -0.016 |
liked | -0.016 |
dolls | -0.015 |
Token | op |
Token ID | 404 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
avail | +0.256 |
ww | +0.215 |
storm | +0.212 |
www | +0.203 |
service | +0.202 |
Neg logit contributions | |
like | -0.163 |
dolls | -0.126 |
favorite | -0.125 |
liked | -0.122 |
both | -0.120 |
Token | was |
Token ID | 373 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ww | +0.082 |
ister | +0.081 |
ths | +0.080 |
avail | +0.080 |
www | +0.080 |
Neg logit contributions | |
like | -0.043 |
liked | -0.027 |
everywhere | -0.025 |
favorite | -0.025 |
around | -0.023 |
Token | not |
Token ID | 407 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
ths | +0.051 |
ister | +0.051 |
ww | +0.050 |
service | +0.050 |
storm | +0.050 |
Neg logit contributions | |
like | -0.041 |
pad | -0.035 |
aces | -0.033 |
everywhere | -0.031 |
liked | -0.030 |
Token | selfish |
Token ID | 20363 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
like | +0.001 |
everywhere | +0.001 |
favorite | +0.001 |
liked | +0.001 |
pad | +0.001 |
Neg logit contributions | |
ww | -0.002 |
ister | -0.002 |
ths | -0.002 |
www | -0.002 |
service | -0.002 |
Token | anymore |
Token ID | 7471 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
like | +0.034 |
ti | +0.027 |
favorite | +0.026 |
liked | +0.025 |
pad | +0.025 |
Neg logit contributions | |
ister | -0.063 |
ww | -0.062 |
ths | -0.062 |
service | -0.062 |
storm | -0.062 |
Token | were |
Token ID | 547 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ister | +0.024 |
ww | +0.024 |
ths | +0.024 |
www | +0.024 |
service | +0.023 |
Neg logit contributions | |
like | -0.018 |
everywhere | -0.012 |
favorite | -0.012 |
liked | -0.012 |
pad | -0.011 |
Token | having |
Token ID | 1719 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ister | +0.031 |
ww | +0.031 |
ths | +0.031 |
www | +0.030 |
service | +0.030 |
Neg logit contributions | |
like | -0.021 |
everywhere | -0.014 |
favorite | -0.014 |
liked | -0.014 |
wherever | -0.012 |
Token | trouble |
Token ID | 5876 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
like | +0.027 |
everywhere | +0.017 |
liked | +0.017 |
favorite | +0.017 |
pad | +0.015 |
Neg logit contributions | |
ww | -0.047 |
ister | -0.047 |
ths | -0.046 |
www | -0.046 |
service | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ister | +0.024 |
service | +0.023 |
ths | +0.023 |
ww | +0.023 |
www | +0.022 |
Neg logit contributions | |
like | -0.010 |
favorite | -0.007 |
liked | -0.006 |
everywhere | -0.006 |
pad | -0.006 |
Token | The |
Token ID | 383 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
ister | +0.004 |
ww | +0.004 |
ths | +0.004 |
www | +0.004 |
service | +0.004 |
Neg logit contributions | |
like | -0.003 |
everywhere | -0.002 |
favorite | -0.002 |
liked | -0.002 |
wherever | -0.002 |
Token | m |
Token ID | 285 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
ww | +0.022 |
ister | +0.022 |
ths | +0.022 |
avail | +0.021 |
www | +0.021 |
Neg logit contributions | |
like | -0.019 |
favorite | -0.014 |
liked | -0.014 |
everywhere | -0.013 |
back | -0.013 |
Token | ule |
Token ID | 2261 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
avail | +0.135 |
ww | +0.111 |
storm | +0.107 |
www | +0.094 |
ths | +0.092 |
Neg logit contributions | |
like | -0.275 |
liked | -0.233 |
favorite | -0.232 |
and | -0.224 |
pad | -0.220 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
avail | +0.130 |
ww | +0.128 |
ister | +0.128 |
service | +0.124 |
www | +0.124 |
Neg logit contributions | |
like | -0.076 |
liked | -0.055 |
everywhere | -0.049 |
favorite | -0.047 |
around | -0.046 |
Token | this |
Token ID | 428 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
like | +0.009 |
everywhere | +0.005 |
favorite | +0.005 |
liked | +0.005 |
around | +0.004 |
Neg logit contributions | |
ister | -0.017 |
ww | -0.017 |
ths | -0.017 |
www | -0.017 |
service | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
ister | +0.005 |
ww | +0.005 |
ths | +0.005 |
www | +0.004 |
avail | +0.004 |
Neg logit contributions | |
like | -0.001 |
everywhere | -0.001 |
favorite | -0.001 |
liked | -0.001 |
around | -0.000 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ister | +0.024 |
ww | +0.023 |
avail | +0.023 |
service | +0.023 |
sermon | +0.023 |
Neg logit contributions | |
like | -0.016 |
liked | -0.011 |
everywhere | -0.010 |
favorite | -0.010 |
all | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ister | +0.024 |
ww | +0.024 |
ths | +0.024 |
www | +0.024 |
service | +0.023 |
Neg logit contributions | |
like | -0.018 |
everywhere | -0.012 |
favorite | -0.012 |
liked | -0.012 |
pad | -0.011 |
Token | having |
Token ID | 1719 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ister | +0.031 |
ww | +0.031 |
ths | +0.031 |
www | +0.030 |
service | +0.030 |
Neg logit contributions | |
like | -0.021 |
everywhere | -0.014 |
favorite | -0.014 |
liked | -0.014 |
wherever | -0.012 |
Token | trouble |
Token ID | 5876 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
like | +0.027 |
everywhere | +0.017 |
liked | +0.017 |
favorite | +0.017 |
pad | +0.015 |
Neg logit contributions | |
ww | -0.047 |
ister | -0.047 |
ths | -0.046 |
www | -0.046 |
service | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ister | +0.024 |
service | +0.023 |
ths | +0.023 |
ww | +0.023 |
www | +0.022 |
Neg logit contributions | |
like | -0.010 |
favorite | -0.007 |
liked | -0.006 |
everywhere | -0.006 |
pad | -0.006 |
Token | The |
Token ID | 383 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
ister | +0.004 |
ww | +0.004 |
ths | +0.004 |
www | +0.004 |
service | +0.004 |
Neg logit contributions | |
like | -0.003 |
everywhere | -0.002 |
favorite | -0.002 |
liked | -0.002 |
wherever | -0.002 |
Token | m |
Token ID | 285 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
ww | +0.022 |
ister | +0.022 |
ths | +0.022 |
avail | +0.021 |
www | +0.021 |
Neg logit contributions | |
like | -0.019 |
favorite | -0.014 |
liked | -0.014 |
everywhere | -0.013 |
back | -0.013 |
Token | ule |
Token ID | 2261 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
avail | +0.135 |
ww | +0.111 |
storm | +0.107 |
www | +0.094 |
ths | +0.092 |
Neg logit contributions | |
like | -0.275 |
liked | -0.233 |
favorite | -0.232 |
and | -0.224 |
pad | -0.220 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
avail | +0.130 |
ww | +0.128 |
ister | +0.128 |
service | +0.124 |
www | +0.124 |
Neg logit contributions | |
like | -0.076 |
liked | -0.055 |
everywhere | -0.049 |
favorite | -0.047 |
around | -0.046 |
Token | this |
Token ID | 428 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
like | +0.009 |
everywhere | +0.005 |
favorite | +0.005 |
liked | +0.005 |
around | +0.004 |
Neg logit contributions | |
ister | -0.017 |
ww | -0.017 |
ths | -0.017 |
www | -0.017 |
service | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
ister | +0.005 |
ww | +0.005 |
ths | +0.005 |
www | +0.004 |
avail | +0.004 |
Neg logit contributions | |
like | -0.001 |
everywhere | -0.001 |
favorite | -0.001 |
liked | -0.001 |
around | -0.000 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ister | +0.024 |
ww | +0.023 |
avail | +0.023 |
service | +0.023 |
sermon | +0.023 |
Neg logit contributions | |
like | -0.016 |
liked | -0.011 |
everywhere | -0.010 |
favorite | -0.010 |
all | -0.010 |
Token | purple |
Token ID | 14032 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
like | +0.013 |
everywhere | +0.009 |
favorite | +0.009 |
liked | +0.009 |
dolls | +0.008 |
Neg logit contributions | |
ister | -0.017 |
ww | -0.017 |
ths | -0.017 |
www | -0.016 |
service | -0.016 |
Token | m |
Token ID | 285 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
ister | +0.007 |
ww | +0.007 |
ths | +0.007 |
www | +0.007 |
service | +0.007 |
Neg logit contributions | |
like | -0.008 |
everywhere | -0.006 |
favorite | -0.006 |
liked | -0.006 |
dolls | -0.005 |
Token | op |
Token ID | 404 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
avail | +0.102 |
ths | +0.093 |
ation | +0.084 |
situations | +0.084 |
storm | +0.083 |
Neg logit contributions | |
like | -0.234 |
favorite | -0.196 |
liked | -0.187 |
everywhere | -0.187 |
. | -0.181 |
Token | . |
Token ID | 13 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
ister | +0.048 |
ww | +0.048 |
ths | +0.047 |
www | +0.047 |
service | +0.046 |
Neg logit contributions | |
like | -0.017 |
everywhere | -0.008 |
favorite | -0.008 |
liked | -0.008 |
wherever | -0.006 |
Token | The |
Token ID | 383 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
ww | +0.003 |
ister | +0.003 |
www | +0.003 |
ths | +0.002 |
service | +0.002 |
Neg logit contributions | |
like | -0.002 |
everywhere | -0.001 |
favorite | -0.001 |
liked | -0.001 |
back | -0.001 |
Token | m |
Token ID | 285 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
ister | +0.014 |
ww | +0.013 |
ths | +0.013 |
www | +0.013 |
service | +0.013 |
Neg logit contributions | |
like | -0.015 |
everywhere | -0.011 |
favorite | -0.011 |
liked | -0.011 |
around | -0.010 |
Token | op |
Token ID | 404 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
avail | +0.217 |
storm | +0.191 |
ww | +0.189 |
service | +0.187 |
ths | +0.183 |
Neg logit contributions | |
like | -0.204 |
favorite | -0.161 |
liked | -0.156 |
dolls | -0.153 |
everywhere | -0.149 |
Token | lived |
Token ID | 5615 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
ister | +0.088 |
ww | +0.088 |
ths | +0.087 |
www | +0.086 |
service | +0.084 |
Neg logit contributions | |
like | -0.054 |
everywhere | -0.035 |
favorite | -0.034 |
liked | -0.034 |
around | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
like | +0.015 |
pad | +0.011 |
pads | +0.010 |
names | +0.010 |
aces | +0.010 |
Neg logit contributions | |
ister | -0.027 |
oo | -0.027 |
ths | -0.026 |
ww | -0.026 |
asis | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
like | +0.015 |
everywhere | +0.005 |
favorite | +0.004 |
all | +0.004 |
liked | +0.004 |
Neg logit contributions | |
ister | -0.059 |
ths | -0.058 |
www | -0.056 |
ww | -0.056 |
sermon | -0.055 |
Token | big |
Token ID | 1263 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
like | +0.017 |
everywhere | +0.012 |
liked | +0.012 |
favorite | +0.012 |
back | +0.011 |
Neg logit contributions | |
ths | -0.033 |
ister | -0.033 |
avail | -0.033 |
service | -0.033 |
vation | -0.033 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ww | +0.006 |
ths | +0.006 |
storm | +0.006 |
www | +0.006 |
ister | +0.006 |
Neg logit contributions | |
like | -0.005 |
liked | -0.004 |
favorite | -0.004 |
pad | -0.004 |
everywhere | -0.003 |
Token | !" |
Token ID | 2474 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
like | +0.027 |
liked | +0.022 |
aces | +0.022 |
pad | +0.021 |
everywhere | +0.021 |
Neg logit contributions | |
ww | -0.037 |
service | -0.036 |
www | -0.036 |
ister | -0.036 |
ths | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
ister | +0.003 |
ww | +0.003 |
ths | +0.003 |
www | +0.003 |
service | +0.003 |
Neg logit contributions | |
like | -0.001 |
everywhere | -0.001 |
favorite | -0.001 |
liked | -0.001 |
dolls | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
like | +0.010 |
everywhere | +0.005 |
favorite | +0.005 |
liked | +0.005 |
dolls | +0.004 |
Neg logit contributions | |
ister | -0.024 |
ww | -0.024 |
ths | -0.024 |
www | -0.024 |
service | -0.023 |
Token | The |
Token ID | 464 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ister | +0.014 |
ww | +0.013 |
avail | +0.013 |
service | +0.013 |
ths | +0.013 |
Neg logit contributions | |
like | -0.012 |
liked | -0.009 |
both | -0.008 |
everywhere | -0.008 |
favorite | -0.008 |
Token | m |
Token ID | 285 |
Feature activation | +8.64e+00 |
Pos logit contributions | |
ww | +0.035 |
avail | +0.035 |
ister | +0.035 |
www | +0.034 |
vation | +0.034 |
Neg logit contributions | |
like | -0.027 |
favorite | -0.020 |
liked | -0.020 |
dolls | -0.020 |
everywhere | -0.019 |
Token | op |
Token ID | 404 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
avail | +0.263 |
storm | +0.225 |
ww | +0.224 |
service | +0.211 |
www | +0.210 |
Neg logit contributions | |
like | -0.153 |
dolls | -0.120 |
favorite | -0.117 |
liked | -0.114 |
both | -0.110 |
Token | thought |
Token ID | 1807 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
ister | +0.094 |
ww | +0.094 |
ths | +0.092 |
www | +0.091 |
avail | +0.091 |
Neg logit contributions | |
like | -0.049 |
liked | -0.030 |
everywhere | -0.029 |
favorite | -0.029 |
around | -0.025 |
Token | about |
Token ID | 546 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
ister | +0.022 |
ww | +0.022 |
ths | +0.022 |
www | +0.022 |
service | +0.021 |
Neg logit contributions | |
like | -0.011 |
everywhere | -0.007 |
favorite | -0.007 |
liked | -0.007 |
around | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
ww | +0.011 |
ister | +0.011 |
www | +0.011 |
ths | +0.011 |
avail | +0.011 |
Neg logit contributions | |
like | -0.006 |
everywhere | -0.004 |
liked | -0.004 |
favorite | -0.004 |
all | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
ister | +0.012 |
ths | +0.012 |
ww | +0.012 |
service | +0.012 |
www | +0.012 |
Neg logit contributions | |
like | -0.005 |
everywhere | -0.002 |
favorite | -0.002 |
liked | -0.002 |
dolls | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
like | +0.013 |
everywhere | +0.008 |
favorite | +0.008 |
liked | +0.008 |
pad | +0.007 |
Neg logit contributions | |
ister | -0.026 |
ww | -0.026 |
ths | -0.025 |
www | -0.025 |
service | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
like | +0.003 |
everywhere | +0.002 |
liked | +0.002 |
favorite | +0.001 |
around | +0.001 |
Neg logit contributions | |
ths | -0.010 |
ww | -0.010 |
ister | -0.010 |
www | -0.010 |
avail | -0.010 |
Token | " |
Token ID | 1 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
ister | +0.029 |
ths | +0.029 |
ww | +0.028 |
avail | +0.028 |
service | +0.028 |
Neg logit contributions | |
like | -0.020 |
liked | -0.013 |
everywhere | -0.013 |
favorite | -0.012 |
back | -0.012 |
Token | W |
Token ID | 54 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
like | +0.078 |
liked | +0.055 |
favorite | +0.051 |
everywhere | +0.047 |
dolls | +0.045 |
Neg logit contributions | |
ths | -0.119 |
avail | -0.119 |
ister | -0.117 |
ww | -0.116 |
www | -0.116 |
Token | oof |
Token ID | 37711 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
ths | +0.060 |
ister | +0.060 |
ww | +0.058 |
www | +0.057 |
service | +0.056 |
Neg logit contributions | |
like | -0.082 |
favorite | -0.062 |
liked | -0.061 |
everywhere | -0.061 |
pad | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -9.03e+00 |
Pos logit contributions | |
like | +0.013 |
favorite | +0.009 |
liked | +0.008 |
everywhere | +0.008 |
wherever | +0.007 |
Neg logit contributions | |
ww | -0.021 |
ister | -0.020 |
www | -0.020 |
service | -0.019 |
ths | -0.019 |
Token | wo |
Token ID | 24486 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
like | +0.174 |
everywhere | +0.114 |
liked | +0.111 |
favorite | +0.110 |
dolls | +0.099 |
Neg logit contributions | |
ths | -0.262 |
ister | -0.261 |
ww | -0.260 |
www | -0.255 |
avail | -0.253 |
Token | of |
Token ID | 1659 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
ister | +0.016 |
ww | +0.015 |
www | +0.015 |
ths | +0.015 |
service | +0.014 |
Neg logit contributions | |
like | -0.018 |
favorite | -0.013 |
liked | -0.013 |
everywhere | -0.013 |
dolls | -0.012 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
like | +0.050 |
everywhere | +0.031 |
favorite | +0.031 |
liked | +0.031 |
around | +0.027 |
Neg logit contributions | |
ister | -0.088 |
ww | -0.088 |
ths | -0.086 |
www | -0.086 |
service | -0.084 |
Token | Spot |
Token ID | 15899 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
like | +0.009 |
liked | +0.005 |
favorite | +0.005 |
everywhere | +0.004 |
Lily | +0.004 |
Neg logit contributions | |
ths | -0.021 |
ister | -0.021 |
ww | -0.020 |
www | -0.020 |
asis | -0.020 |
Token | bark |
Token ID | 21405 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ister | +0.028 |
ww | +0.028 |
ths | +0.027 |
www | +0.027 |
service | +0.026 |
Neg logit contributions | |
like | -0.033 |
everywhere | -0.025 |
favorite | -0.025 |
liked | -0.024 |
wherever | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
ister | +0.002 |
ww | +0.002 |
ths | +0.002 |
www | +0.002 |
iren | +0.002 |
Neg logit contributions | |
like | -0.001 |
favorite | -0.001 |
everywhere | -0.001 |
liked | -0.001 |
pad | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
like | +0.000 |
favorite | +0.000 |
everywhere | +0.000 |
liked | +0.000 |
pad | +0.000 |
Neg logit contributions | |
ister | -0.001 |
ww | -0.001 |
ths | -0.001 |
www | -0.001 |
service | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
ister | +0.032 |
ww | +0.032 |
ths | +0.032 |
www | +0.031 |
service | +0.031 |
Neg logit contributions | |
like | -0.023 |
everywhere | -0.015 |
liked | -0.015 |
favorite | -0.015 |
both | -0.014 |
Token | W |
Token ID | 54 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
like | +0.092 |
everywhere | +0.071 |
favorite | +0.069 |
liked | +0.065 |
back | +0.064 |
Neg logit contributions | |
ww | -0.089 |
www | -0.086 |
ister | -0.086 |
ths | -0.085 |
service | -0.080 |
Token | oof |
Token ID | 37711 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
ths | +0.062 |
ister | +0.062 |
ww | +0.061 |
service | +0.060 |
avail | +0.060 |
Neg logit contributions | |
like | -0.082 |
favorite | -0.061 |
liked | -0.061 |
everywhere | -0.060 |
pad | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -8.89e+00 |
Pos logit contributions | |
like | +0.014 |
favorite | +0.010 |
liked | +0.010 |
everywhere | +0.010 |
wherever | +0.009 |
Neg logit contributions | |
ww | -0.021 |
ister | -0.020 |
www | -0.020 |
service | -0.018 |
storm | -0.018 |
Token | wo |
Token ID | 24486 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
like | +0.165 |
everywhere | +0.106 |
favorite | +0.105 |
liked | +0.104 |
dolls | +0.092 |
Neg logit contributions | |
ister | -0.261 |
ths | -0.260 |
ww | -0.260 |
www | -0.254 |
avail | -0.252 |
Token | of |
Token ID | 1659 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
ister | +0.015 |
ww | +0.015 |
www | +0.015 |
ths | +0.014 |
service | +0.014 |
Neg logit contributions | |
like | -0.018 |
favorite | -0.014 |
liked | -0.014 |
everywhere | -0.014 |
dolls | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
like | +0.056 |
favorite | +0.039 |
everywhere | +0.039 |
liked | +0.038 |
dolls | +0.035 |
Neg logit contributions | |
ww | -0.074 |
ister | -0.074 |
www | -0.072 |
ths | -0.070 |
service | -0.069 |
Token | I |
Token ID | 314 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
like | +0.137 |
everywhere | +0.090 |
liked | +0.088 |
favorite | +0.087 |
back | +0.078 |
Neg logit contributions | |
ths | -0.200 |
ister | -0.198 |
ww | -0.197 |
avail | -0.195 |
www | -0.194 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
like | +0.073 |
everywhere | +0.061 |
favorite | +0.057 |
dolls | +0.056 |
aces | +0.055 |
Neg logit contributions | |
ister | -0.088 |
ww | -0.088 |
www | -0.085 |
service | -0.082 |
storm | -0.081 |
Token | ed |
Token ID | 276 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
like | +0.018 |
dolls | +0.015 |
wherever | +0.014 |
favorite | +0.014 |
upon | +0.014 |
Neg logit contributions | |
ww | -0.028 |
ths | -0.028 |
intense | -0.028 |
beast | -0.027 |
storm | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
like | +0.023 |
aces | +0.021 |
pad | +0.020 |
dolls | +0.019 |
skirts | +0.018 |
Neg logit contributions | |
ths | -0.040 |
storm | -0.040 |
beast | -0.039 |
ister | -0.039 |
intense | -0.038 |
Token | " |
Token ID | 366 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
like | +0.065 |
favorite | +0.051 |
aces | +0.047 |
everywhere | +0.045 |
favorites | +0.045 |
Neg logit contributions | |
ths | -0.112 |
ister | -0.108 |
ller | -0.107 |
ww | -0.106 |
storm | -0.106 |
Token | W |
Token ID | 54 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
like | +0.118 |
everywhere | +0.089 |
favorite | +0.089 |
liked | +0.086 |
dolls | +0.082 |
Neg logit contributions | |
ww | -0.105 |
ister | -0.103 |
ths | -0.101 |
www | -0.101 |
service | -0.096 |
Token | oof |
Token ID | 37711 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
ister | +0.040 |
ww | +0.039 |
www | +0.038 |
ths | +0.038 |
service | +0.036 |
Neg logit contributions | |
like | -0.062 |
everywhere | -0.049 |
favorite | -0.048 |
liked | -0.048 |
dolls | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -8.64e+00 |
Pos logit contributions | |
like | +0.019 |
favorite | +0.014 |
liked | +0.013 |
everywhere | +0.013 |
around | +0.012 |
Neg logit contributions | |
ww | -0.027 |
ister | -0.027 |
www | -0.026 |
service | -0.024 |
storm | -0.024 |
Token | wo |
Token ID | 24486 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
like | +0.172 |
everywhere | +0.118 |
favorite | +0.118 |
liked | +0.116 |
around | +0.107 |
Neg logit contributions | |
ister | -0.240 |
ww | -0.238 |
www | -0.231 |
ths | -0.230 |
service | -0.225 |
Token | of |
Token ID | 1659 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
ister | +0.019 |
ww | +0.018 |
www | +0.018 |
ths | +0.017 |
service | +0.017 |
Neg logit contributions | |
like | -0.022 |
favorite | -0.017 |
liked | -0.017 |
everywhere | -0.016 |
dolls | -0.016 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
like | +0.059 |
favorite | +0.041 |
everywhere | +0.040 |
liked | +0.040 |
dolls | +0.037 |
Neg logit contributions | |
ww | -0.079 |
ister | -0.079 |
www | -0.076 |
ths | -0.074 |
service | -0.073 |
Token | Tom |
Token ID | 4186 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
like | +0.008 |
liked | +0.005 |
everywhere | +0.005 |
favorite | +0.004 |
both | +0.004 |
Neg logit contributions | |
ww | -0.019 |
ister | -0.019 |
ths | -0.019 |
www | -0.019 |
avail | -0.019 |
Token | knew |
Token ID | 2993 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ister | +0.013 |
ths | +0.012 |
ww | +0.012 |
www | +0.012 |
service | +0.012 |
Neg logit contributions | |
like | -0.011 |
everywhere | -0.008 |
favorite | -0.008 |
wherever | -0.007 |
dolls | -0.007 |
Token | ed |
Token ID | 276 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
like | +0.016 |
dolls | +0.014 |
upon | +0.013 |
everywhere | +0.013 |
wherever | +0.013 |
Neg logit contributions | |
ww | -0.018 |
www | -0.017 |
oo | -0.016 |
intense | -0.016 |
ths | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
pad | +0.027 |
like | +0.027 |
aces | +0.027 |
pads | +0.024 |
skirts | +0.023 |
Neg logit contributions | |
ths | -0.038 |
avail | -0.037 |
storm | -0.037 |
service | -0.037 |
beast | -0.037 |
Token | " |
Token ID | 366 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
like | +0.053 |
aces | +0.041 |
favorite | +0.038 |
everywhere | +0.037 |
favorites | +0.037 |
Neg logit contributions | |
ths | -0.091 |
ller | -0.088 |
www | -0.087 |
ister | -0.087 |
ww | -0.087 |
Token | W |
Token ID | 54 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
like | +0.115 |
everywhere | +0.097 |
favorite | +0.089 |
dolls | +0.088 |
back | +0.087 |
Neg logit contributions | |
ww | -0.115 |
www | -0.110 |
ths | -0.101 |
ister | -0.101 |
body | -0.100 |
Token | oof |
Token ID | 37711 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ister | +0.044 |
ww | +0.043 |
ths | +0.042 |
www | +0.042 |
service | +0.040 |
Neg logit contributions | |
like | -0.066 |
everywhere | -0.051 |
favorite | -0.051 |
liked | -0.051 |
around | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -8.55e+00 |
Pos logit contributions | |
like | +0.028 |
favorite | +0.020 |
liked | +0.020 |
everywhere | +0.019 |
dolls | +0.018 |
Neg logit contributions | |
ww | -0.038 |
ister | -0.037 |
www | -0.036 |
service | -0.033 |
ths | -0.033 |
Token | wo |
Token ID | 24486 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
like | +0.177 |
everywhere | +0.129 |
favorite | +0.127 |
liked | +0.123 |
around | +0.121 |
Neg logit contributions | |
ww | -0.227 |
ister | -0.224 |
www | -0.218 |
service | -0.209 |
storm | -0.209 |
Token | of |
Token ID | 1659 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ister | +0.013 |
ww | +0.013 |
www | +0.012 |
ths | +0.011 |
service | +0.011 |
Neg logit contributions | |
like | -0.016 |
favorite | -0.012 |
liked | -0.012 |
everywhere | -0.012 |
dolls | -0.011 |
Token | !" |
Token ID | 2474 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
like | +0.059 |
favorite | +0.044 |
everywhere | +0.042 |
liked | +0.041 |
dolls | +0.039 |
Neg logit contributions | |
ww | -0.072 |
ister | -0.071 |
www | -0.069 |
ths | -0.066 |
service | -0.065 |
Token | They |
Token ID | 1119 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ister | +0.002 |
ths | +0.002 |
ww | +0.002 |
avail | +0.002 |
www | +0.002 |
Neg logit contributions | |
like | -0.001 |
liked | -0.001 |
favorite | -0.001 |
everywhere | -0.001 |
both | -0.001 |
Token | both |
Token ID | 1111 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
like | +0.047 |
joy | +0.040 |
hers | +0.040 |
Whe | +0.039 |
aces | +0.037 |
Neg logit contributions | |
ths | -0.053 |
ww | -0.051 |
www | -0.051 |
intense | -0.050 |
storm | -0.050 |
Token | says |
Token ID | 1139 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
ister | +0.003 |
ths | +0.003 |
ww | +0.003 |
www | +0.003 |
service | +0.003 |
Neg logit contributions | |
like | -0.003 |
everywhere | -0.002 |
wherever | -0.002 |
favorite | -0.002 |
aces | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
like | +0.017 |
everywhere | +0.011 |
favorite | +0.011 |
liked | +0.010 |
pad | +0.010 |
Neg logit contributions | |
ister | -0.031 |
ww | -0.030 |
ths | -0.029 |
www | -0.029 |
service | -0.029 |
Token | " |
Token ID | 366 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
like | +0.057 |
favorite | +0.034 |
everywhere | +0.033 |
liked | +0.028 |
dolls | +0.028 |
Neg logit contributions | |
ister | -0.131 |
ww | -0.128 |
ths | -0.128 |
www | -0.126 |
service | -0.125 |
Token | W |
Token ID | 54 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
like | +0.101 |
everywhere | +0.075 |
favorite | +0.074 |
liked | +0.072 |
dolls | +0.068 |
Neg logit contributions | |
ww | -0.102 |
ister | -0.101 |
ths | -0.099 |
www | -0.098 |
service | -0.095 |
Token | oof |
Token ID | 37711 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ths | +0.047 |
ister | +0.046 |
avail | +0.045 |
ww | +0.044 |
storm | +0.043 |
Neg logit contributions | |
like | -0.076 |
favorite | -0.057 |
liked | -0.057 |
love | -0.056 |
everywhere | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -8.48e+00 |
Pos logit contributions | |
like | +0.026 |
favorite | +0.018 |
liked | +0.017 |
everywhere | +0.017 |
around | +0.015 |
Neg logit contributions | |
ww | -0.041 |
ister | -0.041 |
www | -0.040 |
service | -0.038 |
ths | -0.037 |
Token | wo |
Token ID | 24486 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
like | +0.153 |
everywhere | +0.096 |
favorite | +0.094 |
liked | +0.094 |
back | +0.083 |
Neg logit contributions | |
ths | -0.256 |
ister | -0.254 |
ww | -0.253 |
avail | -0.250 |
www | -0.248 |
Token | of |
Token ID | 1659 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
ister | +0.016 |
ww | +0.016 |
www | +0.016 |
ths | +0.016 |
service | +0.015 |
Neg logit contributions | |
like | -0.019 |
favorite | -0.014 |
liked | -0.014 |
everywhere | -0.014 |
dolls | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
like | +0.054 |
favorite | +0.037 |
everywhere | +0.036 |
liked | +0.035 |
dolls | +0.032 |
Neg logit contributions | |
ister | -0.090 |
ww | -0.089 |
www | -0.086 |
ths | -0.084 |
service | -0.083 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
like | +0.124 |
everywhere | +0.077 |
liked | +0.075 |
favorite | +0.074 |
back | +0.068 |
Neg logit contributions | |
ths | -0.205 |
avail | -0.202 |
ister | -0.200 |
ww | -0.198 |
www | -0.195 |
Token | ! |
Token ID | 0 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
like | +0.036 |
favorite | +0.028 |
everywhere | +0.026 |
liked | +0.023 |
dolls | +0.023 |
Neg logit contributions | |
ister | -0.066 |
ww | -0.063 |
www | -0.062 |
beast | -0.059 |
service | -0.059 |
Token | said |
Token ID | 531 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
like | +0.023 |
everywhere | +0.017 |
liked | +0.017 |
favorite | +0.017 |
around | +0.016 |
Neg logit contributions | |
ister | -0.023 |
ww | -0.023 |
ths | -0.022 |
www | -0.022 |
service | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
like | +0.018 |
pad | +0.014 |
everywhere | +0.014 |
favorite | +0.013 |
liked | +0.012 |
Neg logit contributions | |
ister | -0.027 |
ww | -0.026 |
service | -0.025 |
www | -0.025 |
ths | -0.024 |
Token | " |
Token ID | 366 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
like | +0.074 |
favorite | +0.046 |
everywhere | +0.045 |
aces | +0.042 |
liked | +0.040 |
Neg logit contributions | |
ister | -0.154 |
ths | -0.150 |
service | -0.146 |
ww | -0.144 |
sermon | -0.144 |
Token | W |
Token ID | 54 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
like | +0.098 |
liked | +0.070 |
everywhere | +0.069 |
favorite | +0.069 |
wherever | +0.063 |
Neg logit contributions | |
ister | -0.104 |
ths | -0.102 |
ww | -0.102 |
www | -0.099 |
service | -0.098 |
Token | oof |
Token ID | 37711 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
ister | +0.050 |
ths | +0.049 |
ww | +0.048 |
www | +0.047 |
avail | +0.046 |
Neg logit contributions | |
like | -0.074 |
favorite | -0.057 |
liked | -0.057 |
everywhere | -0.056 |
pad | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -8.38e+00 |
Pos logit contributions | |
like | +0.017 |
favorite | +0.011 |
everywhere | +0.011 |
liked | +0.011 |
around | +0.010 |
Neg logit contributions | |
ww | -0.028 |
ister | -0.028 |
www | -0.027 |
service | -0.026 |
ths | -0.026 |
Token | wo |
Token ID | 24486 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
like | +0.149 |
everywhere | +0.092 |
favorite | +0.092 |
liked | +0.090 |
dolls | +0.081 |
Neg logit contributions | |
ths | -0.257 |
ister | -0.253 |
avail | -0.253 |
ww | -0.252 |
www | -0.249 |
Token | of |
Token ID | 1659 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
ister | +0.023 |
ww | +0.023 |
ths | +0.022 |
www | +0.022 |
service | +0.022 |
Neg logit contributions | |
like | -0.025 |
everywhere | -0.018 |
favorite | -0.018 |
liked | -0.018 |
around | -0.017 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
like | +0.054 |
favorite | +0.034 |
everywhere | +0.034 |
liked | +0.034 |
around | +0.030 |
Neg logit contributions | |
ister | -0.092 |
ww | -0.092 |
www | -0.089 |
ths | -0.089 |
service | -0.087 |
Token |
|
Token ID | 198 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
like | +0.012 |
favorite | +0.008 |
everywhere | +0.008 |
liked | +0.007 |
pad | +0.007 |
Neg logit contributions | |
ister | -0.022 |
ww | -0.021 |
service | -0.021 |
iren | -0.020 |
www | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ister | +0.002 |
ww | +0.002 |
ths | +0.002 |
www | +0.002 |
service | +0.002 |
Neg logit contributions | |
like | -0.001 |
favorite | -0.001 |
everywhere | -0.001 |
liked | -0.001 |
pad | -0.000 |
Token | tail |
Token ID | 7894 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
like | +0.038 |
everywhere | +0.027 |
favorite | +0.027 |
liked | +0.026 |
around | +0.024 |
Neg logit contributions | |
ister | -0.046 |
ww | -0.046 |
ths | -0.045 |
www | -0.045 |
service | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
like | +0.016 |
favorite | +0.011 |
liked | +0.009 |
everywhere | +0.009 |
wherever | +0.009 |
Neg logit contributions | |
ister | -0.041 |
ww | -0.040 |
service | -0.039 |
storm | -0.039 |
www | -0.039 |
Token | " |
Token ID | 366 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
like | +0.002 |
everywhere | +0.001 |
favorite | +0.001 |
liked | +0.001 |
wherever | +0.001 |
Neg logit contributions | |
ister | -0.004 |
ww | -0.004 |
www | -0.004 |
ths | -0.004 |
ama | -0.004 |
Token | W |
Token ID | 54 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
like | +0.103 |
everywhere | +0.079 |
favorite | +0.077 |
liked | +0.073 |
back | +0.071 |
Neg logit contributions | |
ww | -0.109 |
ister | -0.105 |
www | -0.105 |
ths | -0.103 |
service | -0.099 |
Token | oof |
Token ID | 37711 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
ister | +0.056 |
ww | +0.055 |
ths | +0.054 |
www | +0.053 |
service | +0.052 |
Neg logit contributions | |
like | -0.084 |
everywhere | -0.065 |
favorite | -0.065 |
liked | -0.064 |
around | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | -8.29e+00 |
Pos logit contributions | |
like | +0.013 |
favorite | +0.009 |
everywhere | +0.009 |
liked | +0.009 |
around | +0.008 |
Neg logit contributions | |
ww | -0.020 |
ister | -0.019 |
www | -0.019 |
service | -0.018 |
ths | -0.017 |
Token | wo |
Token ID | 24486 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
like | +0.163 |
everywhere | +0.110 |
favorite | +0.108 |
liked | +0.108 |
around | +0.097 |
Neg logit contributions | |
ister | -0.234 |
ww | -0.232 |
ths | -0.229 |
www | -0.227 |
service | -0.222 |
Token | of |
Token ID | 1659 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
ww | +0.015 |
ister | +0.015 |
www | +0.014 |
ths | +0.013 |
service | +0.013 |
Neg logit contributions | |
like | -0.018 |
favorite | -0.014 |
liked | -0.014 |
everywhere | -0.014 |
dolls | -0.013 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
like | +0.056 |
favorite | +0.039 |
everywhere | +0.039 |
liked | +0.038 |
dolls | +0.035 |
Neg logit contributions | |
ister | -0.073 |
ww | -0.073 |
www | -0.071 |
ths | -0.070 |
service | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
like | +0.008 |
everywhere | +0.005 |
favorite | +0.005 |
liked | +0.005 |
dolls | +0.004 |
Neg logit contributions | |
ister | -0.018 |
ww | -0.018 |
ths | -0.018 |
www | -0.018 |
service | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
like | +0.006 |
everywhere | +0.003 |
favorite | +0.003 |
liked | +0.003 |
pad | +0.003 |
Neg logit contributions | |
ister | -0.014 |
ww | -0.014 |
ths | -0.013 |
www | -0.013 |
service | -0.013 |
Token | says |
Token ID | 1139 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ww | +0.027 |
ister | +0.026 |
ths | +0.026 |
www | +0.026 |
service | +0.025 |
Neg logit contributions | |
like | -0.027 |
everywhere | -0.020 |
favorite | -0.020 |
liked | -0.019 |
wherever | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
like | +0.021 |
everywhere | +0.014 |
favorite | +0.014 |
liked | +0.014 |
pad | +0.013 |
Neg logit contributions | |
ister | -0.037 |
ww | -0.037 |
ths | -0.035 |
www | -0.035 |
service | -0.035 |
Token | " |
Token ID | 366 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
like | +0.057 |
favorite | +0.037 |
everywhere | +0.034 |
dolls | +0.032 |
aces | +0.031 |
Neg logit contributions | |
ister | -0.119 |
ths | -0.116 |
ww | -0.115 |
storm | -0.114 |
service | -0.114 |
Token | W |
Token ID | 54 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
like | +0.090 |
liked | +0.064 |
favorite | +0.060 |
everywhere | +0.058 |
love | +0.056 |
Neg logit contributions | |
ister | -0.108 |
ths | -0.108 |
avail | -0.104 |
service | -0.103 |
ww | -0.102 |
Token | oof |
Token ID | 37711 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ths | +0.051 |
ister | +0.050 |
ww | +0.049 |
service | +0.048 |
avail | +0.048 |
Neg logit contributions | |
like | -0.065 |
liked | -0.047 |
favorite | -0.047 |
everywhere | -0.047 |
pad | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -8.26e+00 |
Pos logit contributions | |
like | +0.022 |
favorite | +0.016 |
liked | +0.015 |
everywhere | +0.015 |
around | +0.014 |
Neg logit contributions | |
ww | -0.034 |
ister | -0.034 |
www | -0.033 |
service | -0.031 |
storm | -0.030 |
Token | wo |
Token ID | 24486 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
like | +0.154 |
everywhere | +0.099 |
favorite | +0.098 |
liked | +0.097 |
dolls | +0.086 |
Neg logit contributions | |
ister | -0.243 |
ths | -0.242 |
ww | -0.241 |
www | -0.237 |
avail | -0.234 |
Token | of |
Token ID | 1659 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
ister | +0.021 |
ww | +0.021 |
www | +0.020 |
ths | +0.020 |
service | +0.019 |
Neg logit contributions | |
like | -0.024 |
favorite | -0.018 |
liked | -0.018 |
everywhere | -0.018 |
dolls | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
like | +0.054 |
favorite | +0.036 |
everywhere | +0.036 |
liked | +0.035 |
dolls | +0.032 |
Neg logit contributions | |
ister | -0.086 |
ww | -0.086 |
www | -0.083 |
ths | -0.081 |
service | -0.080 |
Token | my |
Token ID | 616 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
like | +0.132 |
everywhere | +0.086 |
favorite | +0.084 |
liked | +0.084 |
back | +0.076 |
Neg logit contributions | |
ths | -0.200 |
ister | -0.198 |
ww | -0.196 |
www | -0.193 |
avail | -0.193 |
Token | name |
Token ID | 1438 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
like | +0.038 |
everywhere | +0.026 |
liked | +0.025 |
favorite | +0.025 |
around | +0.023 |
Neg logit contributions | |
ister | -0.054 |
ww | -0.054 |
ths | -0.053 |
www | -0.052 |
service | -0.051 |
Token | said |
Token ID | 531 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
like | +0.007 |
everywhere | +0.005 |
favorite | +0.005 |
liked | +0.005 |
aces | +0.005 |
Neg logit contributions | |
ww | -0.008 |
www | -0.008 |
ths | -0.008 |
ister | -0.008 |
service | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
like | +0.017 |
pad | +0.013 |
everywhere | +0.012 |
favorite | +0.011 |
favorites | +0.011 |
Neg logit contributions | |
ww | -0.022 |
ister | -0.022 |
www | -0.021 |
service | -0.020 |
ths | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
like | +0.053 |
favorite | +0.034 |
everywhere | +0.032 |
aces | +0.031 |
liked | +0.030 |
Neg logit contributions | |
ister | -0.102 |
ww | -0.099 |
www | -0.099 |
ths | -0.098 |
storm | -0.096 |
Token | W |
Token ID | 54 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
like | +0.102 |
everywhere | +0.082 |
favorite | +0.082 |
aces | +0.077 |
dolls | +0.077 |
Neg logit contributions | |
ww | -0.092 |
www | -0.089 |
ths | -0.082 |
ister | -0.081 |
body | -0.078 |
Token | oof |
Token ID | 37711 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
ister | +0.056 |
ww | +0.055 |
ths | +0.054 |
www | +0.053 |
service | +0.051 |
Neg logit contributions | |
like | -0.084 |
everywhere | -0.065 |
favorite | -0.065 |
liked | -0.064 |
around | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
like | +0.018 |
favorite | +0.013 |
liked | +0.013 |
everywhere | +0.012 |
around | +0.012 |
Neg logit contributions | |
ww | -0.027 |
ister | -0.026 |
www | -0.025 |
service | -0.023 |
storm | -0.023 |
Token | wo |
Token ID | 24486 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
like | +0.170 |
everywhere | +0.123 |
favorite | +0.123 |
liked | +0.121 |
around | +0.115 |
Neg logit contributions | |
ister | -0.214 |
ww | -0.212 |
www | -0.204 |
storm | -0.197 |
service | -0.196 |
Token | of |
Token ID | 1659 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
ister | +0.026 |
ww | +0.026 |
www | +0.025 |
ths | +0.024 |
service | +0.024 |
Neg logit contributions | |
like | -0.032 |
favorite | -0.024 |
liked | -0.024 |
everywhere | -0.024 |
dolls | -0.023 |
Token | !" |
Token ID | 2474 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
like | +0.051 |
favorite | +0.036 |
everywhere | +0.035 |
liked | +0.034 |
dolls | +0.032 |
Neg logit contributions | |
ww | -0.071 |
ister | -0.071 |
www | -0.068 |
ths | -0.066 |
service | -0.065 |
Token | The |
Token ID | 383 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ths | +0.016 |
ister | +0.016 |
avail | +0.016 |
ww | +0.015 |
www | +0.015 |
Neg logit contributions | |
like | -0.007 |
liked | -0.005 |
and | -0.004 |
favorite | -0.004 |
Lily | -0.004 |
Token | leash |
Token ID | 40529 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
ww | +0.040 |
ister | +0.040 |
www | +0.039 |
ths | +0.038 |
storm | +0.038 |
Neg logit contributions | |
like | -0.018 |
everywhere | -0.010 |
favorite | -0.010 |
liked | -0.010 |
around | -0.009 |
Token | says |
Token ID | 1139 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
ww | +0.011 |
ister | +0.010 |
www | +0.010 |
service | +0.010 |
sermon | +0.010 |
Neg logit contributions | |
like | -0.011 |
everywhere | -0.009 |
wherever | -0.008 |
aces | -0.008 |
favorite | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
like | +0.015 |
pad | +0.012 |
favorite | +0.010 |
liked | +0.010 |
everywhere | +0.010 |
Neg logit contributions | |
ister | -0.021 |
ww | -0.020 |
service | -0.019 |
ths | -0.019 |
www | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
like | +0.066 |
favorite | +0.042 |
everywhere | +0.041 |
aces | +0.036 |
pad | +0.035 |
Neg logit contributions | |
ister | -0.139 |
ths | -0.136 |
service | -0.135 |
ww | -0.134 |
sermon | -0.132 |
Token | W |
Token ID | 54 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
like | +0.093 |
everywhere | +0.071 |
favorite | +0.067 |
liked | +0.063 |
pad | +0.063 |
Neg logit contributions | |
ww | -0.109 |
ister | -0.105 |
www | -0.104 |
ths | -0.101 |
service | -0.099 |
Token | oof |
Token ID | 37711 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ths | +0.049 |
ister | +0.048 |
ww | +0.048 |
www | +0.046 |
avail | +0.046 |
Neg logit contributions | |
like | -0.065 |
favorite | -0.048 |
liked | -0.048 |
everywhere | -0.048 |
love | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -8.08e+00 |
Pos logit contributions | |
like | +0.024 |
favorite | +0.018 |
everywhere | +0.016 |
liked | +0.016 |
around | +0.015 |
Neg logit contributions | |
ww | -0.036 |
ister | -0.035 |
www | -0.034 |
service | -0.032 |
storm | -0.031 |
Token | wo |
Token ID | 24486 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
like | +0.158 |
everywhere | +0.108 |
favorite | +0.105 |
liked | +0.105 |
around | +0.096 |
Neg logit contributions | |
ister | -0.227 |
ww | -0.226 |
ths | -0.220 |
www | -0.220 |
service | -0.216 |
Token | of |
Token ID | 1659 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
ister | +0.014 |
ww | +0.014 |
www | +0.013 |
ths | +0.013 |
service | +0.012 |
Neg logit contributions | |
like | -0.016 |
favorite | -0.013 |
liked | -0.012 |
everywhere | -0.012 |
dolls | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
like | +0.054 |
favorite | +0.039 |
everywhere | +0.036 |
liked | +0.034 |
pad | +0.033 |
Neg logit contributions | |
ister | -0.094 |
ww | -0.094 |
www | -0.089 |
service | -0.086 |
oo | -0.085 |
Token | You |
Token ID | 921 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
like | +0.033 |
everywhere | +0.028 |
favorite | +0.026 |
liked | +0.026 |
around | +0.025 |
Neg logit contributions | |
ww | -0.026 |
ister | -0.025 |
www | -0.024 |
service | -0.023 |
storm | -0.023 |
Token | are |
Token ID | 389 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
like | +0.055 |
favorite | +0.040 |
everywhere | +0.039 |
pad | +0.037 |
dolls | +0.035 |
Neg logit contributions | |
ww | -0.123 |
ister | -0.121 |
www | -0.119 |
storm | -0.118 |
service | -0.117 |
Token | said |
Token ID | 531 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
like | +0.004 |
everywhere | +0.003 |
favorite | +0.003 |
wherever | +0.003 |
pad | +0.003 |
Neg logit contributions | |
ww | -0.004 |
ths | -0.004 |
ister | -0.004 |
www | -0.004 |
service | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
like | +0.011 |
pad | +0.009 |
everywhere | +0.008 |
favorite | +0.008 |
liked | +0.008 |
Neg logit contributions | |
ister | -0.015 |
ww | -0.015 |
www | -0.013 |
service | -0.013 |
storm | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
like | +0.079 |
favorite | +0.057 |
favorites | +0.052 |
aces | +0.052 |
everywhere | +0.051 |
Neg logit contributions | |
ister | -0.128 |
storm | -0.121 |
service | -0.121 |
ths | -0.120 |
ller | -0.119 |
Token | W |
Token ID | 54 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
like | +0.103 |
everywhere | +0.078 |
favorite | +0.077 |
liked | +0.074 |
around | +0.071 |
Neg logit contributions | |
ww | -0.101 |
ister | -0.099 |
www | -0.097 |
ths | -0.097 |
service | -0.093 |
Token | oof |
Token ID | 37711 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
ister | +0.050 |
ww | +0.050 |
ths | +0.048 |
www | +0.048 |
service | +0.046 |
Neg logit contributions | |
like | -0.077 |
everywhere | -0.060 |
favorite | -0.059 |
liked | -0.059 |
around | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -8.05e+00 |
Pos logit contributions | |
like | +0.013 |
favorite | +0.009 |
liked | +0.009 |
everywhere | +0.009 |
around | +0.008 |
Neg logit contributions | |
ww | -0.021 |
ister | -0.021 |
www | -0.020 |
service | -0.019 |
storm | -0.019 |
Token | wo |
Token ID | 24486 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
like | +0.160 |
everywhere | +0.110 |
favorite | +0.108 |
liked | +0.108 |
around | +0.100 |
Neg logit contributions | |
ister | -0.224 |
ww | -0.223 |
www | -0.216 |
ths | -0.216 |
service | -0.212 |
Token | of |
Token ID | 1659 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
ister | +0.026 |
ww | +0.026 |
www | +0.025 |
ths | +0.024 |
service | +0.024 |
Neg logit contributions | |
like | -0.030 |
favorite | -0.023 |
liked | -0.022 |
everywhere | -0.022 |
dolls | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
like | +0.047 |
favorite | +0.032 |
everywhere | +0.030 |
liked | +0.030 |
dolls | +0.027 |
Neg logit contributions | |
ister | -0.079 |
ww | -0.079 |
www | -0.076 |
ths | -0.074 |
service | -0.073 |
Token | wo |
Token ID | 24486 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
like | +0.137 |
everywhere | +0.095 |
favorite | +0.094 |
liked | +0.094 |
around | +0.086 |
Neg logit contributions | |
ister | -0.174 |
ww | -0.173 |
ths | -0.168 |
www | -0.168 |
service | -0.164 |
Token | of |
Token ID | 1659 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
ister | +0.038 |
ww | +0.038 |
ths | +0.037 |
www | +0.037 |
service | +0.036 |
Neg logit contributions | |
like | -0.043 |
everywhere | -0.032 |
favorite | -0.031 |
liked | -0.031 |
dolls | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
like | +0.015 |
everywhere | +0.009 |
favorite | +0.008 |
liked | +0.008 |
wherever | +0.007 |
Neg logit contributions | |
ister | -0.031 |
ww | -0.031 |
ths | -0.031 |
www | -0.030 |
service | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
like | +0.002 |
everywhere | +0.001 |
favorite | +0.001 |
liked | +0.001 |
around | +0.001 |
Neg logit contributions | |
ister | -0.004 |
ww | -0.004 |
ths | -0.004 |
www | -0.004 |
service | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
ths | +0.023 |
ister | +0.023 |
ww | +0.023 |
avail | +0.023 |
service | +0.022 |
Neg logit contributions | |
like | -0.016 |
liked | -0.011 |
everywhere | -0.010 |
favorite | -0.010 |
both | -0.010 |
Token | W |
Token ID | 54 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
like | +0.073 |
liked | +0.051 |
favorite | +0.049 |
everywhere | +0.046 |
both | +0.043 |
Neg logit contributions | |
ister | -0.100 |
ths | -0.099 |
avail | -0.098 |
ww | -0.097 |
service | -0.096 |
Token | oof |
Token ID | 37711 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
ister | +0.057 |
ww | +0.056 |
ths | +0.056 |
www | +0.054 |
service | +0.053 |
Neg logit contributions | |
like | -0.084 |
everywhere | -0.064 |
favorite | -0.064 |
liked | -0.064 |
around | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -8.00e+00 |
Pos logit contributions | |
like | +0.012 |
favorite | +0.008 |
everywhere | +0.008 |
liked | +0.008 |
wherever | +0.007 |
Neg logit contributions | |
ww | -0.019 |
ister | -0.019 |
www | -0.018 |
service | -0.018 |
ths | -0.017 |
Token | wo |
Token ID | 24486 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
like | +0.153 |
everywhere | +0.101 |
favorite | +0.100 |
liked | +0.099 |
around | +0.089 |
Neg logit contributions | |
ister | -0.230 |
ww | -0.229 |
ths | -0.226 |
www | -0.223 |
service | -0.219 |
Token | of |
Token ID | 1659 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ister | +0.027 |
ww | +0.027 |
www | +0.026 |
ths | +0.026 |
service | +0.025 |
Neg logit contributions | |
like | -0.030 |
favorite | -0.022 |
liked | -0.022 |
everywhere | -0.022 |
dolls | -0.020 |
Token | !" |
Token ID | 2474 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
like | +0.044 |
everywhere | +0.027 |
favorite | +0.027 |
liked | +0.027 |
around | +0.023 |
Neg logit contributions | |
ister | -0.077 |
ww | -0.077 |
ths | -0.076 |
www | -0.075 |
service | -0.074 |
Token | Spot |
Token ID | 15899 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
like | +0.010 |
liked | +0.004 |
favorite | +0.004 |
everywhere | +0.004 |
both | +0.003 |
Neg logit contributions | |
ths | -0.031 |
ister | -0.031 |
ww | -0.030 |
www | -0.030 |
service | -0.029 |
Token | bark |
Token ID | 21405 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ister | +0.029 |
ww | +0.028 |
www | +0.028 |
ths | +0.028 |
service | +0.026 |
Neg logit contributions | |
like | -0.035 |
everywhere | -0.027 |
favorite | -0.026 |
wherever | -0.025 |
liked | -0.025 |
Token | said |
Token ID | 531 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
like | +0.003 |
everywhere | +0.002 |
wherever | +0.002 |
favorite | +0.002 |
pad | +0.002 |
Neg logit contributions | |
ths | -0.003 |
ww | -0.003 |
ister | -0.003 |
www | -0.003 |
service | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
like | +0.011 |
pad | +0.007 |
everywhere | +0.007 |
liked | +0.007 |
favorite | +0.007 |
Neg logit contributions | |
ister | -0.017 |
ww | -0.017 |
ths | -0.016 |
www | -0.016 |
service | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
like | +0.066 |
favorite | +0.041 |
everywhere | +0.038 |
liked | +0.033 |
pad | +0.033 |
Neg logit contributions | |
ister | -0.141 |
ths | -0.135 |
ww | -0.135 |
service | -0.134 |
storm | -0.133 |
Token | W |
Token ID | 54 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
like | +0.081 |
liked | +0.056 |
favorite | +0.053 |
everywhere | +0.052 |
both | +0.048 |
Neg logit contributions | |
ister | -0.109 |
ths | -0.108 |
ww | -0.106 |
www | -0.105 |
service | -0.104 |
Token | oof |
Token ID | 37711 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
ths | +0.048 |
ister | +0.048 |
ww | +0.047 |
service | +0.046 |
www | +0.046 |
Neg logit contributions | |
like | -0.066 |
liked | -0.049 |
favorite | -0.049 |
everywhere | -0.049 |
love | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
like | +0.018 |
favorite | +0.013 |
liked | +0.012 |
everywhere | +0.012 |
around | +0.011 |
Neg logit contributions | |
ww | -0.030 |
ister | -0.030 |
www | -0.029 |
service | -0.027 |
ths | -0.027 |
Token | wo |
Token ID | 24486 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
like | +0.154 |
everywhere | +0.101 |
favorite | +0.100 |
liked | +0.099 |
dolls | +0.089 |
Neg logit contributions | |
ister | -0.229 |
ths | -0.229 |
ww | -0.228 |
www | -0.224 |
avail | -0.221 |
Token | of |
Token ID | 1659 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
ister | +0.026 |
ww | +0.026 |
ths | +0.025 |
www | +0.025 |
service | +0.025 |
Neg logit contributions | |
like | -0.029 |
favorite | -0.021 |
everywhere | -0.021 |
liked | -0.021 |
dolls | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
like | +0.047 |
favorite | +0.031 |
everywhere | +0.030 |
liked | +0.029 |
dolls | +0.026 |
Neg logit contributions | |
ister | -0.086 |
ww | -0.086 |
www | -0.083 |
ths | -0.081 |
service | -0.080 |
Token | sorry |
Token ID | 7926 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
like | +0.152 |
everywhere | +0.111 |
favorite | +0.110 |
liked | +0.109 |
dolls | +0.101 |
Neg logit contributions | |
ister | -0.150 |
ww | -0.149 |
ths | -0.148 |
www | -0.145 |
avail | -0.142 |
Token | , |
Token ID | 11 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
like | +0.005 |
everywhere | +0.004 |
liked | +0.004 |
pad | +0.004 |
aces | +0.004 |
Neg logit contributions | |
ww | -0.007 |
ister | -0.007 |
www | -0.007 |
storm | -0.007 |
service | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
like | +0.027 |
everywhere | +0.018 |
favorite | +0.018 |
liked | +0.016 |
pad | +0.016 |
Neg logit contributions | |
ister | -0.046 |
ww | -0.045 |
www | -0.044 |
service | -0.043 |
ths | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
like | +0.016 |
favorite | +0.010 |
everywhere | +0.009 |
liked | +0.009 |
pad | +0.008 |
Neg logit contributions | |
ister | -0.031 |
ww | -0.030 |
www | -0.029 |
ths | -0.029 |
service | -0.029 |
Token | " |
Token ID | 1 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
ister | +0.009 |
ww | +0.009 |
ths | +0.008 |
www | +0.008 |
service | +0.008 |
Neg logit contributions | |
like | -0.007 |
everywhere | -0.005 |
liked | -0.005 |
favorite | -0.005 |
around | -0.004 |
Token | W |
Token ID | 54 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
like | +0.072 |
liked | +0.053 |
favorite | +0.047 |
love | +0.043 |
dolls | +0.042 |
Neg logit contributions | |
avail | -0.098 |
ths | -0.097 |
ister | -0.096 |
asis | -0.094 |
service | -0.093 |
Token | oof |
Token ID | 37711 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ths | +0.058 |
ister | +0.057 |
ww | +0.056 |
www | +0.055 |
avail | +0.054 |
Neg logit contributions | |
like | -0.074 |
favorite | -0.054 |
liked | -0.054 |
everywhere | -0.052 |
pad | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -7.93e+00 |
Pos logit contributions | |
like | +0.009 |
favorite | +0.006 |
everywhere | +0.006 |
liked | +0.006 |
wherever | +0.005 |
Neg logit contributions | |
ww | -0.016 |
ister | -0.016 |
www | -0.015 |
ths | -0.015 |
service | -0.015 |
Token | wo |
Token ID | 24486 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
like | +0.140 |
everywhere | +0.084 |
liked | +0.083 |
favorite | +0.082 |
dolls | +0.074 |
Neg logit contributions | |
ths | -0.250 |
avail | -0.247 |
ister | -0.241 |
ww | -0.240 |
www | -0.239 |
Token | of |
Token ID | 1659 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
ister | +0.024 |
ww | +0.024 |
www | +0.023 |
ths | +0.023 |
service | +0.022 |
Neg logit contributions | |
like | -0.027 |
favorite | -0.020 |
everywhere | -0.020 |
liked | -0.020 |
dolls | -0.019 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
like | +0.043 |
everywhere | +0.026 |
liked | +0.025 |
favorite | +0.025 |
around | +0.021 |
Neg logit contributions | |
ister | -0.088 |
ww | -0.087 |
ths | -0.087 |
www | -0.086 |
service | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
like | +0.016 |
everywhere | +0.008 |
liked | +0.008 |
favorite | +0.008 |
both | +0.007 |
Neg logit contributions | |
ww | -0.043 |
ths | -0.043 |
ister | -0.043 |
www | -0.042 |
service | -0.041 |
Token | dolls |
Token ID | 36062 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
ths | +0.060 |
avail | +0.057 |
ww | +0.056 |
www | +0.055 |
ister | +0.055 |
Neg logit contributions | |
like | -0.033 |
dolls | -0.024 |
liked | -0.024 |
favorite | -0.023 |
back | -0.021 |
Token | says |
Token ID | 1139 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
like | +0.004 |
everywhere | +0.003 |
liked | +0.003 |
favorite | +0.003 |
around | +0.003 |
Neg logit contributions | |
ister | -0.005 |
ww | -0.005 |
ths | -0.005 |
www | -0.005 |
service | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
like | +0.022 |
everywhere | +0.014 |
favorite | +0.014 |
liked | +0.014 |
around | +0.013 |
Neg logit contributions | |
ister | -0.036 |
ww | -0.036 |
ths | -0.035 |
www | -0.035 |
service | -0.034 |
Token | " |
Token ID | 366 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
like | +0.068 |
favorite | +0.039 |
everywhere | +0.037 |
liked | +0.035 |
aces | +0.030 |
Neg logit contributions | |
ister | -0.172 |
ww | -0.167 |
ths | -0.166 |
service | -0.165 |
www | -0.163 |
Token | W |
Token ID | 54 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
like | +0.081 |
liked | +0.057 |
everywhere | +0.056 |
favorite | +0.056 |
around | +0.051 |
Neg logit contributions | |
ister | -0.092 |
ww | -0.090 |
ths | -0.090 |
www | -0.088 |
service | -0.087 |
Token | oof |
Token ID | 37711 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
ths | +0.043 |
ister | +0.042 |
ww | +0.041 |
avail | +0.040 |
storm | +0.040 |
Neg logit contributions | |
like | -0.055 |
liked | -0.040 |
favorite | -0.040 |
everywhere | -0.038 |
love | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -7.87e+00 |
Pos logit contributions | |
like | +0.016 |
favorite | +0.011 |
everywhere | +0.011 |
liked | +0.010 |
around | +0.009 |
Neg logit contributions | |
ister | -0.028 |
ww | -0.028 |
www | -0.027 |
ths | -0.027 |
service | -0.027 |
Token | wo |
Token ID | 24486 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
like | +0.149 |
everywhere | +0.097 |
favorite | +0.095 |
liked | +0.094 |
dolls | +0.084 |
Neg logit contributions | |
ister | -0.228 |
ths | -0.228 |
ww | -0.227 |
www | -0.222 |
avail | -0.221 |
Token | of |
Token ID | 1659 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
ister | +0.022 |
ww | +0.022 |
ths | +0.022 |
www | +0.022 |
service | +0.021 |
Neg logit contributions | |
like | -0.024 |
everywhere | -0.018 |
favorite | -0.017 |
liked | -0.017 |
around | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
like | +0.047 |
everywhere | +0.029 |
favorite | +0.029 |
liked | +0.028 |
around | +0.025 |
Neg logit contributions | |
ister | -0.084 |
ww | -0.084 |
ths | -0.082 |
www | -0.082 |
service | -0.080 |
Token | I |
Token ID | 314 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
like | +0.035 |
everywhere | +0.027 |
favorite | +0.026 |
liked | +0.026 |
around | +0.025 |
Neg logit contributions | |
ww | -0.032 |
ister | -0.031 |
www | -0.030 |
service | -0.029 |
ths | -0.029 |
Token | understand |
Token ID | 1833 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
like | +0.052 |
everywhere | +0.037 |
favorite | +0.036 |
liked | +0.033 |
dolls | +0.033 |
Neg logit contributions | |
ister | -0.084 |
ww | -0.084 |
www | -0.082 |
service | -0.080 |
ths | -0.080 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
like | +0.011 |
favorite | +0.009 |
everywhere | +0.009 |
skirts | +0.008 |
liked | +0.008 |
Neg logit contributions | |
ister | -0.010 |
ww | -0.010 |
www | -0.009 |
beast | -0.009 |
service | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
like | +0.011 |
everywhere | +0.007 |
favorite | +0.007 |
liked | +0.007 |
around | +0.006 |
Neg logit contributions | |
ister | -0.022 |
ww | -0.021 |
ths | -0.021 |
www | -0.021 |
service | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
like | +0.003 |
everywhere | +0.002 |
favorite | +0.002 |
liked | +0.002 |
pad | +0.001 |
Neg logit contributions | |
ister | -0.007 |
ww | -0.007 |
ths | -0.007 |
www | -0.007 |
service | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
ister | +0.026 |
ww | +0.026 |
ths | +0.025 |
www | +0.025 |
service | +0.024 |
Neg logit contributions | |
like | -0.023 |
everywhere | -0.016 |
favorite | -0.016 |
liked | -0.016 |
around | -0.015 |
Token | Bang |
Token ID | 43984 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
like | +0.108 |
everywhere | +0.089 |
favorite | +0.087 |
where | +0.083 |
pad | +0.083 |
Neg logit contributions | |
ww | -0.075 |
www | -0.071 |
ths | -0.070 |
ister | -0.069 |
body | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
like | +0.004 |
favorite | +0.004 |
liked | +0.003 |
everywhere | +0.003 |
dolls | +0.003 |
Neg logit contributions | |
ister | -0.006 |
ww | -0.006 |
www | -0.005 |
ths | -0.005 |
beast | -0.005 |
Token | bang |
Token ID | 20188 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
like | +0.210 |
everywhere | +0.159 |
favorite | +0.158 |
liked | +0.157 |
around | +0.148 |
Neg logit contributions | |
ister | -0.164 |
ww | -0.162 |
ths | -0.159 |
www | -0.157 |
service | -0.152 |
Token | , |
Token ID | 11 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
like | +0.030 |
favorite | +0.021 |
liked | +0.021 |
everywhere | +0.021 |
dolls | +0.019 |
Neg logit contributions | |
ister | -0.042 |
ww | -0.042 |
www | -0.041 |
ths | -0.041 |
service | -0.040 |
Token | bang |
Token ID | 20188 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
like | +0.177 |
everywhere | +0.135 |
favorite | +0.135 |
liked | +0.134 |
around | +0.126 |
Neg logit contributions | |
ister | -0.136 |
ww | -0.135 |
ths | -0.131 |
www | -0.130 |
service | -0.126 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
like | +0.017 |
favorite | +0.012 |
liked | +0.012 |
everywhere | +0.012 |
dolls | +0.011 |
Neg logit contributions | |
ww | -0.022 |
ister | -0.022 |
www | -0.021 |
ths | -0.021 |
service | -0.020 |
Token | Sam |
Token ID | 3409 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
like | +0.015 |
everywhere | +0.008 |
favorite | +0.008 |
liked | +0.008 |
around | +0.007 |
Neg logit contributions | |
ister | -0.034 |
ww | -0.033 |
ths | -0.033 |
www | -0.033 |
service | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
like | +0.004 |
Whe | +0.004 |
favorite | +0.003 |
liked | +0.003 |
ti | +0.003 |
Neg logit contributions | |
service | -0.006 |
outage | -0.005 |
ister | -0.005 |
asis | -0.005 |
site | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
like | +0.022 |
everywhere | +0.015 |
favorite | +0.014 |
liked | +0.014 |
pad | +0.013 |
Neg logit contributions | |
ister | -0.037 |
ww | -0.037 |
ths | -0.036 |
www | -0.036 |
service | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -6.32e-03 |
Pos logit contributions | |
like | +0.020 |
favorite | +0.012 |
everywhere | +0.012 |
liked | +0.012 |
pad | +0.011 |
Neg logit contributions | |
ister | -0.041 |
ww | -0.040 |
ths | -0.039 |
www | -0.039 |
service | -0.039 |
Token | " |
Token ID | 1 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
like | +0.000 |
liked | +0.000 |
everywhere | +0.000 |
favorite | +0.000 |
both | +0.000 |
Neg logit contributions | |
ister | -0.000 |
ww | -0.000 |
ths | -0.000 |
www | -0.000 |
avail | -0.000 |
Token | Bang |
Token ID | 43984 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
like | +0.090 |
everywhere | +0.069 |
favorite | +0.068 |
liked | +0.065 |
around | +0.064 |
Neg logit contributions | |
ww | -0.081 |
ister | -0.078 |
www | -0.078 |
ths | -0.078 |
service | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | -7.71e+00 |
Pos logit contributions | |
like | +0.002 |
liked | +0.001 |
favorite | +0.001 |
everywhere | +0.001 |
dolls | +0.001 |
Neg logit contributions | |
ister | -0.003 |
ww | -0.003 |
www | -0.003 |
ths | -0.002 |
avail | -0.002 |
Token | bang |
Token ID | 20188 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
like | +0.199 |
favorite | +0.155 |
liked | +0.151 |
everywhere | +0.151 |
around | +0.143 |
Neg logit contributions | |
ister | -0.168 |
ww | -0.165 |
www | -0.159 |
ths | -0.159 |
storm | -0.156 |
Token | , |
Token ID | 11 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
like | +0.024 |
everywhere | +0.015 |
favorite | +0.015 |
liked | +0.015 |
around | +0.013 |
Neg logit contributions | |
ister | -0.043 |
ww | -0.043 |
ths | -0.042 |
www | -0.042 |
service | -0.041 |
Token | bang |
Token ID | 20188 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
like | +0.167 |
favorite | +0.126 |
everywhere | +0.126 |
liked | +0.125 |
around | +0.117 |
Neg logit contributions | |
ister | -0.150 |
ww | -0.149 |
ths | -0.144 |
www | -0.144 |
service | -0.140 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
like | +0.014 |
everywhere | +0.010 |
favorite | +0.009 |
liked | +0.009 |
around | +0.009 |
Neg logit contributions | |
ister | -0.021 |
ww | -0.021 |
ths | -0.021 |
www | -0.020 |
service | -0.020 |
Token | Tom |
Token ID | 4186 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
like | +0.019 |
liked | +0.009 |
everywhere | +0.009 |
favorite | +0.009 |
both | +0.008 |
Neg logit contributions | |
ww | -0.049 |
ths | -0.049 |
ister | -0.049 |
www | -0.048 |
service | -0.047 |
Token | neck |
Token ID | 7393 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ister | +0.011 |
ths | +0.011 |
ww | +0.011 |
www | +0.011 |
avail | +0.010 |
Neg logit contributions | |
like | -0.010 |
everywhere | -0.007 |
liked | -0.007 |
favorite | -0.006 |
both | -0.006 |
Token | l |
Token ID | 75 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
like | +0.027 |
favorite | +0.016 |
everywhere | +0.015 |
liked | +0.015 |
dolls | +0.014 |
Neg logit contributions | |
ister | -0.072 |
ww | -0.070 |
ths | -0.069 |
service | -0.069 |
www | -0.068 |
Token | aces |
Token ID | 2114 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
like | +0.030 |
everywhere | +0.018 |
favorite | +0.018 |
liked | +0.017 |
dolls | +0.015 |
Neg logit contributions | |
ister | -0.057 |
ww | -0.057 |
ths | -0.056 |
www | -0.055 |
service | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
like | +0.041 |
dolls | +0.029 |
favorite | +0.029 |
Whe | +0.026 |
love | +0.026 |
Neg logit contributions | |
ister | -0.093 |
ww | -0.086 |
ths | -0.085 |
www | -0.083 |
keys | -0.083 |
Token | grape |
Token ID | 30777 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
like | +0.044 |
favorite | +0.025 |
everywhere | +0.025 |
liked | +0.023 |
dolls | +0.020 |
Neg logit contributions | |
ister | -0.103 |
ths | -0.102 |
ww | -0.102 |
www | -0.100 |
service | -0.100 |
Token | brace |
Token ID | 22581 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
like | +0.033 |
favorite | +0.022 |
everywhere | +0.022 |
liked | +0.021 |
wherever | +0.019 |
Neg logit contributions | |
ww | -0.052 |
ister | -0.052 |
ths | -0.051 |
www | -0.051 |
service | -0.050 |
Token | lets |
Token ID | 5289 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
like | +0.164 |
Whe | +0.130 |
everywhere | +0.130 |
liked | +0.127 |
dolls | +0.127 |
Neg logit contributions | |
ww | -0.171 |
ller | -0.157 |
www | -0.156 |
ths | -0.151 |
ink | -0.148 |
Token | , |
Token ID | 11 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
like | +0.075 |
favorite | +0.055 |
Whe | +0.052 |
liked | +0.049 |
dolls | +0.047 |
Neg logit contributions | |
ister | -0.160 |
service | -0.153 |
ww | -0.151 |
ths | -0.149 |
field | -0.149 |
Token | and |
Token ID | 290 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
like | +0.075 |
everywhere | +0.050 |
favorite | +0.048 |
liked | +0.047 |
around | +0.044 |
Neg logit contributions | |
ww | -0.118 |
ister | -0.116 |
ths | -0.115 |
www | -0.114 |
service | -0.112 |
Token | grape |
Token ID | 30777 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
like | +0.041 |
everywhere | +0.027 |
favorite | +0.027 |
liked | +0.027 |
dolls | +0.024 |
Neg logit contributions | |
ister | -0.061 |
ww | -0.060 |
ths | -0.060 |
www | -0.059 |
service | -0.058 |
Token | crown |
Token ID | 12389 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
like | +0.033 |
favorite | +0.022 |
everywhere | +0.021 |
liked | +0.021 |
wherever | +0.018 |
Neg logit contributions | |
ww | -0.059 |
ister | -0.058 |
www | -0.057 |
ths | -0.057 |
service | -0.056 |
Token | says |
Token ID | 1139 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
like | +0.001 |
everywhere | +0.001 |
wherever | +0.001 |
favorite | +0.001 |
pad | +0.001 |
Neg logit contributions | |
ister | -0.001 |
ths | -0.001 |
ww | -0.001 |
service | -0.001 |
www | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
like | +0.019 |
pad | +0.014 |
everywhere | +0.013 |
favorite | +0.013 |
liked | +0.013 |
Neg logit contributions | |
ister | -0.028 |
ww | -0.028 |
www | -0.026 |
service | -0.026 |
ths | -0.026 |
Token | " |
Token ID | 366 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
like | +0.061 |
favorite | +0.037 |
everywhere | +0.036 |
liked | +0.031 |
aces | +0.030 |
Neg logit contributions | |
ister | -0.132 |
ths | -0.127 |
ww | -0.127 |
service | -0.125 |
www | -0.124 |
Token | W |
Token ID | 54 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
like | +0.090 |
liked | +0.063 |
everywhere | +0.062 |
favorite | +0.062 |
wherever | +0.057 |
Neg logit contributions | |
ister | -0.103 |
ths | -0.101 |
ww | -0.101 |
www | -0.099 |
service | -0.098 |
Token | oof |
Token ID | 37711 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
ister | +0.050 |
ths | +0.049 |
ww | +0.049 |
www | +0.048 |
service | +0.047 |
Neg logit contributions | |
like | -0.070 |
favorite | -0.053 |
everywhere | -0.053 |
liked | -0.053 |
pad | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
like | +0.015 |
favorite | +0.011 |
everywhere | +0.010 |
liked | +0.010 |
around | +0.009 |
Neg logit contributions | |
ww | -0.025 |
ister | -0.025 |
www | -0.024 |
service | -0.023 |
storm | -0.022 |
Token | wo |
Token ID | 24486 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
like | +0.141 |
everywhere | +0.090 |
favorite | +0.089 |
liked | +0.089 |
dolls | +0.079 |
Neg logit contributions | |
ister | -0.225 |
ths | -0.225 |
ww | -0.224 |
www | -0.220 |
avail | -0.218 |
Token | of |
Token ID | 1659 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
ister | +0.028 |
ww | +0.028 |
www | +0.027 |
ths | +0.026 |
service | +0.026 |
Neg logit contributions | |
like | -0.033 |
favorite | -0.025 |
liked | -0.025 |
everywhere | -0.025 |
dolls | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
like | +0.041 |
favorite | +0.026 |
everywhere | +0.025 |
liked | +0.024 |
dolls | +0.021 |
Neg logit contributions | |
ister | -0.084 |
ww | -0.083 |
www | -0.081 |
ths | -0.079 |
service | -0.078 |
Token | hello |
Token ID | 23748 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
like | +0.124 |
everywhere | +0.082 |
favorite | +0.081 |
liked | +0.080 |
dolls | +0.073 |
Neg logit contributions | |
ths | -0.175 |
ister | -0.174 |
ww | -0.172 |
www | -0.169 |
avail | -0.169 |
Token | , |
Token ID | 11 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
like | +0.029 |
everywhere | +0.020 |
liked | +0.019 |
favorite | +0.018 |
dolls | +0.018 |
Neg logit contributions | |
ister | -0.067 |
ww | -0.066 |
www | -0.063 |
service | -0.062 |
ths | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
like | +0.010 |
liked | +0.007 |
favorite | +0.006 |
everywhere | +0.005 |
ti | +0.005 |
Neg logit contributions | |
ister | -0.020 |
service | -0.020 |
ww | -0.020 |
ths | -0.020 |
beast | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
like | +0.016 |
everywhere | +0.011 |
liked | +0.011 |
favorite | +0.011 |
back | +0.010 |
Neg logit contributions | |
ister | -0.022 |
ww | -0.022 |
ths | -0.022 |
www | -0.022 |
storm | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
like | +0.014 |
favorite | +0.009 |
everywhere | +0.009 |
liked | +0.008 |
aces | +0.008 |
Neg logit contributions | |
ister | -0.026 |
ww | -0.026 |
www | -0.025 |
ths | -0.025 |
service | -0.024 |
Token | " |
Token ID | 1 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
ister | +0.004 |
ww | +0.004 |
ths | +0.004 |
www | +0.004 |
service | +0.004 |
Neg logit contributions | |
like | -0.004 |
everywhere | -0.003 |
favorite | -0.003 |
liked | -0.003 |
around | -0.003 |
Token | Bang |
Token ID | 43984 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
like | +0.099 |
everywhere | +0.081 |
favorite | +0.079 |
where | +0.075 |
around | +0.074 |
Neg logit contributions | |
ww | -0.083 |
www | -0.078 |
ths | -0.075 |
ister | -0.072 |
avail | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | -7.61e+00 |
Pos logit contributions | |
like | +0.004 |
liked | +0.003 |
favorite | +0.003 |
everywhere | +0.003 |
dolls | +0.003 |
Neg logit contributions | |
ister | -0.006 |
ww | -0.006 |
www | -0.006 |
ths | -0.005 |
beast | -0.005 |
Token | bang |
Token ID | 20188 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
like | +0.196 |
everywhere | +0.147 |
favorite | +0.146 |
liked | +0.145 |
around | +0.135 |
Neg logit contributions | |
ister | -0.169 |
ww | -0.167 |
ths | -0.164 |
www | -0.162 |
service | -0.158 |
Token | , |
Token ID | 11 |
Feature activation | -6.27e+00 |
Pos logit contributions | |
like | +0.024 |
favorite | +0.016 |
everywhere | +0.016 |
liked | +0.016 |
dolls | +0.014 |
Neg logit contributions | |
ister | -0.039 |
ww | -0.039 |
ths | -0.038 |
www | -0.038 |
service | -0.037 |
Token | you |
Token ID | 345 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
like | +0.157 |
everywhere | +0.117 |
favorite | +0.116 |
liked | +0.116 |
around | +0.108 |
Neg logit contributions | |
ister | -0.142 |
ww | -0.142 |
ths | -0.139 |
www | -0.137 |
service | -0.133 |
Token | 're |
Token ID | 821 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
like | +0.061 |
everywhere | +0.041 |
favorite | +0.040 |
liked | +0.040 |
around | +0.036 |
Neg logit contributions | |
ister | -0.090 |
ww | -0.090 |
ths | -0.088 |
www | -0.088 |
service | -0.086 |
Token | dead |
Token ID | 2636 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ww | +0.014 |
ister | +0.014 |
ths | +0.014 |
www | +0.014 |
storm | +0.014 |
Neg logit contributions | |
like | -0.013 |
liked | -0.009 |
favorite | -0.009 |
everywhere | -0.009 |
pad | -0.008 |
Token | him |
Token ID | 683 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
like | +0.018 |
liked | +0.012 |
everywhere | +0.012 |
favorite | +0.012 |
pad | +0.011 |
Neg logit contributions | |
ww | -0.028 |
ister | -0.028 |
ths | -0.028 |
www | -0.027 |
service | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
like | +0.021 |
liked | +0.013 |
everywhere | +0.013 |
favorite | +0.012 |
pad | +0.011 |
Neg logit contributions | |
ister | -0.043 |
ww | -0.042 |
service | -0.042 |
ths | -0.042 |
www | -0.041 |
Token | coat |
Token ID | 13209 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
like | +0.015 |
favorite | +0.011 |
everywhere | +0.011 |
liked | +0.011 |
back | +0.010 |
Neg logit contributions | |
ths | -0.017 |
ister | -0.017 |
ww | -0.017 |
www | -0.017 |
avail | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
like | +0.017 |
everywhere | +0.009 |
favorite | +0.009 |
liked | +0.009 |
dolls | +0.007 |
Neg logit contributions | |
ister | -0.041 |
ww | -0.041 |
ths | -0.040 |
www | -0.040 |
service | -0.040 |
Token | He |
Token ID | 679 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ister | +0.006 |
ww | +0.006 |
ths | +0.006 |
www | +0.006 |
service | +0.006 |
Neg logit contributions | |
like | -0.005 |
favorite | -0.003 |
liked | -0.003 |
everywhere | -0.003 |
both | -0.003 |
Token | must |
Token ID | 1276 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
like | +0.005 |
liked | +0.003 |
favorite | +0.003 |
everywhere | +0.003 |
both | +0.003 |
Neg logit contributions | |
ister | -0.008 |
ww | -0.008 |
ths | -0.008 |
www | -0.008 |
avail | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
ww | +0.135 |
ths | +0.134 |
ister | +0.129 |
www | +0.128 |
sermon | +0.124 |
Neg logit contributions | |
like | -0.110 |
liked | -0.072 |
favorite | -0.071 |
both | -0.070 |
everywhere | -0.069 |
Token | cold |
Token ID | 4692 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ww | +0.014 |
ths | +0.014 |
ister | +0.013 |
www | +0.013 |
service | +0.013 |
Neg logit contributions | |
like | -0.013 |
everywhere | -0.009 |
favorite | -0.009 |
liked | -0.009 |
wherever | -0.009 |
Token | ." |
Token ID | 526 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
like | +0.024 |
everywhere | +0.011 |
favorite | +0.010 |
liked | +0.010 |
around | +0.008 |
Neg logit contributions | |
ister | -0.073 |
ww | -0.072 |
ths | -0.072 |
www | -0.071 |
service | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
ister | +0.018 |
ww | +0.018 |
ths | +0.017 |
www | +0.017 |
service | +0.017 |
Neg logit contributions | |
like | -0.009 |
everywhere | -0.005 |
favorite | -0.005 |
liked | -0.005 |
pad | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ister | +0.015 |
ww | +0.014 |
www | +0.014 |
ths | +0.014 |
service | +0.014 |
Neg logit contributions | |
like | -0.007 |
everywhere | -0.004 |
favorite | -0.004 |
liked | -0.004 |
pad | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
ister | +0.017 |
ths | +0.017 |
ww | +0.017 |
www | +0.017 |
service | +0.017 |
Neg logit contributions | |
like | -0.012 |
favorite | -0.008 |
everywhere | -0.008 |
liked | -0.007 |
wherever | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
like | +0.005 |
everywhere | +0.004 |
liked | +0.003 |
favorite | +0.003 |
both | +0.003 |
Neg logit contributions | |
ww | -0.009 |
ister | -0.009 |
www | -0.009 |
ths | -0.009 |
avail | -0.009 |
Token | excited |
Token ID | 6568 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
avail | +0.070 |
ww | +0.066 |
ths | +0.066 |
beast | +0.066 |
www | +0.065 |
Neg logit contributions | |
like | -0.031 |
liked | -0.019 |
both | -0.017 |
everywhere | -0.017 |
favorite | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ister | +0.094 |
ww | +0.093 |
ths | +0.092 |
www | +0.091 |
service | +0.090 |
Neg logit contributions | |
like | -0.038 |
everywhere | -0.020 |
favorite | -0.019 |
liked | -0.019 |
around | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ister | +0.050 |
ww | +0.050 |
ths | +0.049 |
www | +0.048 |
service | +0.047 |
Neg logit contributions | |
like | -0.053 |
everywhere | -0.039 |
favorite | -0.038 |
liked | -0.038 |
around | -0.035 |
Token | m |
Token ID | 285 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
ww | +0.029 |
ister | +0.029 |
ths | +0.029 |
www | +0.028 |
avail | +0.028 |
Neg logit contributions | |
like | -0.027 |
favorite | -0.020 |
liked | -0.019 |
everywhere | -0.019 |
back | -0.019 |
Token | ule |
Token ID | 2261 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
avail | +0.124 |
ww | +0.104 |
storm | +0.100 |
www | +0.089 |
sermon | +0.084 |
Neg logit contributions | |
like | -0.257 |
favorite | -0.221 |
liked | -0.216 |
aces | -0.215 |
both | -0.213 |
Token | was |
Token ID | 373 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ister | +0.101 |
ww | +0.100 |
ths | +0.099 |
www | +0.098 |
service | +0.096 |
Neg logit contributions | |
like | -0.069 |
everywhere | -0.046 |
favorite | -0.046 |
liked | -0.045 |
dolls | -0.041 |
Token | helping |
Token ID | 5742 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ister | +0.044 |
ths | +0.043 |
ww | +0.043 |
service | +0.042 |
www | +0.042 |
Neg logit contributions | |
like | -0.037 |
favorite | -0.027 |
liked | -0.026 |
everywhere | -0.026 |
pad | -0.025 |
Token | them |
Token ID | 606 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ister | +0.060 |
ths | +0.059 |
service | +0.058 |
ww | +0.058 |
www | +0.057 |
Neg logit contributions | |
like | -0.029 |
favorite | -0.019 |
liked | -0.018 |
everywhere | -0.017 |
pad | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
like | +0.006 |
favorite | +0.003 |
everywhere | +0.003 |
liked | +0.003 |
pad | +0.003 |
Neg logit contributions | |
ister | -0.015 |
ths | -0.015 |
ww | -0.015 |
www | -0.015 |
service | -0.014 |
Token | ." |
Token ID | 526 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
ths | +0.001 |
ww | +0.001 |
ister | +0.001 |
www | +0.001 |
avail | +0.001 |
Neg logit contributions | |
like | -0.001 |
everywhere | -0.000 |
favorite | -0.000 |
liked | -0.000 |
around | -0.000 |
Token | |
Token ID | 220 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ww | +0.032 |
ister | +0.031 |
ths | +0.031 |
www | +0.030 |
avail | +0.030 |
Neg logit contributions | |
like | -0.013 |
liked | -0.007 |
favorite | -0.006 |
both | -0.006 |
everywhere | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
ister | +0.004 |
ww | +0.004 |
ths | +0.004 |
www | +0.004 |
service | +0.004 |
Neg logit contributions | |
like | -0.002 |
favorite | -0.001 |
liked | -0.001 |
everywhere | -0.001 |
dolls | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ww | +0.015 |
ths | +0.014 |
avail | +0.014 |
www | +0.014 |
storm | +0.014 |
Neg logit contributions | |
like | -0.004 |
liked | -0.001 |
both | -0.001 |
everywhere | -0.001 |
back | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
avail | +0.037 |
ww | +0.036 |
storm | +0.036 |
asis | +0.035 |
ths | +0.034 |
Neg logit contributions | |
like | -0.024 |
liked | -0.017 |
both | -0.015 |
back | -0.014 |
but | -0.014 |
Token | elderly |
Token ID | 13830 |
Feature activation | +7.29e+00 |
Pos logit contributions | |
ww | +0.054 |
ths | +0.054 |
mmm | +0.053 |
www | +0.052 |
avail | +0.051 |
Neg logit contributions | |
like | -0.039 |
back | -0.032 |
favorite | -0.031 |
dolls | -0.030 |
all | -0.030 |
Token | person |
Token ID | 1048 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
ister | +0.135 |
ww | +0.130 |
ths | +0.127 |
www | +0.126 |
service | +0.124 |
Neg logit contributions | |
like | -0.217 |
everywhere | -0.172 |
favorite | -0.169 |
liked | -0.166 |
wherever | -0.160 |
Token | replied |
Token ID | 8712 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ister | +0.094 |
ww | +0.094 |
ths | +0.091 |
www | +0.091 |
avail | +0.089 |
Neg logit contributions | |
like | -0.089 |
liked | -0.065 |
everywhere | -0.064 |
favorite | -0.064 |
around | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
like | +0.032 |
pad | +0.022 |
favorite | +0.022 |
everywhere | +0.022 |
liked | +0.021 |
Neg logit contributions | |
ister | -0.046 |
ths | -0.044 |
ww | -0.044 |
www | -0.043 |
service | -0.043 |
Token | " |
Token ID | 366 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
like | +0.043 |
favorite | +0.022 |
everywhere | +0.022 |
liked | +0.019 |
dolls | +0.017 |
Neg logit contributions | |
ister | -0.113 |
ths | -0.111 |
ww | -0.111 |
www | -0.110 |
service | -0.108 |
Token | No |
Token ID | 2949 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
like | +0.085 |
everywhere | +0.059 |
favorite | +0.059 |
liked | +0.059 |
around | +0.054 |
Neg logit contributions | |
ister | -0.102 |
ww | -0.102 |
ths | -0.100 |
www | -0.099 |
service | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
like | +0.017 |
favorite | +0.010 |
everywhere | +0.010 |
liked | +0.010 |
pad | +0.008 |
Neg logit contributions | |
ister | -0.037 |
ww | -0.037 |
ths | -0.036 |
www | -0.036 |
service | -0.035 |
Token | They |
Token ID | 2990 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
ister | +0.010 |
ww | +0.010 |
ths | +0.010 |
www | +0.009 |
service | +0.009 |
Neg logit contributions | |
like | -0.008 |
everywhere | -0.006 |
liked | -0.006 |
favorite | -0.006 |
both | -0.005 |
Token | played |
Token ID | 2826 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
like | +0.045 |
aces | +0.035 |
hers | +0.035 |
favorite | +0.034 |
wherever | +0.033 |
Neg logit contributions | |
ths | -0.045 |
ister | -0.044 |
service | -0.044 |
field | -0.044 |
storm | -0.044 |
Token | in |
Token ID | 287 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
like | +0.005 |
pad | +0.004 |
favorite | +0.003 |
liked | +0.003 |
everywhere | +0.003 |
Neg logit contributions | |
site | -0.010 |
ister | -0.010 |
service | -0.010 |
asis | -0.010 |
ths | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
like | +0.014 |
aces | +0.012 |
pad | +0.011 |
favorite | +0.011 |
liked | +0.011 |
Neg logit contributions | |
service | -0.017 |
storm | -0.016 |
ister | -0.016 |
site | -0.016 |
ths | -0.016 |
Token | o |
Token ID | 267 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
like | +0.011 |
favorite | +0.008 |
everywhere | +0.008 |
liked | +0.008 |
back | +0.008 |
Neg logit contributions | |
ister | -0.012 |
ths | -0.012 |
ww | -0.011 |
www | -0.011 |
avail | -0.011 |
Token | asis |
Token ID | 17765 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
avail | +0.077 |
www | +0.060 |
ww | +0.058 |
ths | +0.058 |
beast | +0.055 |
Neg logit contributions | |
like | -0.180 |
liked | -0.150 |
until | -0.147 |
favorite | -0.147 |
back | -0.144 |
Token | for |
Token ID | 329 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
ister | +0.023 |
ww | +0.023 |
ths | +0.022 |
www | +0.022 |
service | +0.022 |
Neg logit contributions | |
like | -0.007 |
everywhere | -0.003 |
favorite | -0.003 |
liked | -0.003 |
dolls | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
ister | +0.027 |
ww | +0.027 |
ths | +0.027 |
www | +0.026 |
avail | +0.026 |
Neg logit contributions | |
like | -0.008 |
everywhere | -0.003 |
liked | -0.003 |
favorite | -0.003 |
both | -0.002 |
Token | while |
Token ID | 981 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
like | +0.016 |
everywhere | +0.011 |
favorite | +0.011 |
liked | +0.011 |
aces | +0.010 |
Neg logit contributions | |
ww | -0.022 |
ister | -0.022 |
www | -0.021 |
ths | -0.021 |
service | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
ister | +0.085 |
ww | +0.084 |
ths | +0.084 |
www | +0.083 |
service | +0.081 |
Neg logit contributions | |
like | -0.029 |
everywhere | -0.014 |
favorite | -0.013 |
liked | -0.013 |
around | -0.010 |
Token | down |
Token ID | 866 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ister | +0.031 |
ths | +0.030 |
avail | +0.029 |
service | +0.029 |
ww | +0.029 |
Neg logit contributions | |
like | -0.017 |
favorite | -0.010 |
pad | -0.010 |
liked | -0.010 |
everywhere | -0.010 |
Token | for |
Token ID | 329 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
like | +0.006 |
favorite | +0.003 |
liked | +0.003 |
everywhere | +0.003 |
dolls | +0.003 |
Neg logit contributions | |
ister | -0.015 |
ths | -0.015 |
ww | -0.015 |
service | -0.015 |
www | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ister | +0.045 |
ww | +0.044 |
www | +0.044 |
ths | +0.043 |
ule | +0.041 |
Neg logit contributions | |
like | -0.017 |
everywhere | -0.009 |
all | -0.008 |
favorite | -0.008 |
liked | -0.008 |
Token | nap |
Token ID | 25422 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
ister | +0.003 |
ww | +0.003 |
www | +0.003 |
ths | +0.003 |
avail | +0.003 |
Neg logit contributions | |
like | -0.003 |
favorite | -0.002 |
everywhere | -0.002 |
liked | -0.002 |
dolls | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ister | +0.097 |
ww | +0.096 |
ths | +0.095 |
www | +0.094 |
service | +0.093 |
Neg logit contributions | |
like | -0.037 |
everywhere | -0.019 |
favorite | -0.018 |
liked | -0.018 |
dolls | -0.014 |
Token | While |
Token ID | 2893 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
ister | +0.037 |
ww | +0.036 |
ths | +0.036 |
www | +0.035 |
avail | +0.034 |
Neg logit contributions | |
like | -0.021 |
liked | -0.013 |
favorite | -0.013 |
everywhere | -0.013 |
wherever | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ister | +0.150 |
ww | +0.149 |
www | +0.147 |
ths | +0.143 |
avail | +0.141 |
Neg logit contributions | |
like | -0.094 |
everywhere | -0.064 |
all | -0.061 |
liked | -0.060 |
wherever | -0.058 |
Token | was |
Token ID | 373 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ister | +0.043 |
ww | +0.042 |
avail | +0.042 |
www | +0.042 |
irens | +0.042 |
Neg logit contributions | |
like | -0.022 |
liked | -0.016 |
everywhere | -0.013 |
found | -0.013 |
favorite | -0.012 |
Token | lying |
Token ID | 9105 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ister | +0.043 |
ww | +0.043 |
ths | +0.042 |
www | +0.042 |
avail | +0.040 |
Neg logit contributions | |
like | -0.037 |
everywhere | -0.026 |
liked | -0.025 |
favorite | -0.025 |
around | -0.024 |
Token | down |
Token ID | 866 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
like | +0.002 |
favorite | +0.001 |
everywhere | +0.001 |
liked | +0.001 |
dolls | +0.001 |
Neg logit contributions | |
ister | -0.005 |
ww | -0.005 |
ths | -0.005 |
www | -0.005 |
service | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
ww | +0.033 |
ister | +0.032 |
www | +0.032 |
ths | +0.032 |
avail | +0.031 |
Neg logit contributions | |
like | -0.014 |
everywhere | -0.008 |
liked | -0.008 |
favorite | -0.007 |
back | -0.007 |
Token | truck |
Token ID | 7779 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
like | +0.033 |
everywhere | +0.024 |
favorite | +0.024 |
liked | +0.024 |
wherever | +0.023 |
Neg logit contributions | |
ister | -0.028 |
ww | -0.028 |
ths | -0.027 |
www | -0.027 |
service | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ister | +0.045 |
service | +0.043 |
ths | +0.043 |
ww | +0.043 |
www | +0.042 |
Neg logit contributions | |
like | -0.015 |
favorite | -0.007 |
everywhere | -0.007 |
liked | -0.007 |
dolls | -0.005 |
Token | asks |
Token ID | 7893 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
like | +0.032 |
everywhere | +0.024 |
favorite | +0.024 |
liked | +0.023 |
wherever | +0.022 |
Neg logit contributions | |
ister | -0.026 |
ww | -0.026 |
ths | -0.026 |
www | -0.026 |
service | -0.025 |
Token | for |
Token ID | 329 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ister | +0.014 |
ama | +0.013 |
service | +0.013 |
oo | +0.012 |
avail | +0.012 |
Neg logit contributions | |
like | -0.011 |
pad | -0.010 |
aces | -0.010 |
favorite | -0.009 |
pads | -0.009 |
Token | mint |
Token ID | 21043 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
ister | +0.045 |
ww | +0.045 |
ths | +0.044 |
service | +0.044 |
www | +0.044 |
Neg logit contributions | |
like | -0.026 |
everywhere | -0.017 |
liked | -0.017 |
favorite | -0.016 |
pad | -0.015 |
Token | ice |
Token ID | 4771 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
like | +0.015 |
liked | +0.011 |
everywhere | +0.011 |
pad | +0.011 |
favorite | +0.010 |
Neg logit contributions | |
ister | -0.017 |
ww | -0.017 |
www | -0.016 |
ths | -0.016 |
service | -0.016 |
Token | cream |
Token ID | 8566 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
ister | +0.012 |
ww | +0.012 |
www | +0.011 |
service | +0.011 |
ths | +0.011 |
Neg logit contributions | |
like | -0.020 |
everywhere | -0.016 |
liked | -0.016 |
pad | -0.016 |
wherever | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
like | +0.031 |
liked | +0.020 |
favorite | +0.020 |
everywhere | +0.019 |
dolls | +0.018 |
Neg logit contributions | |
ister | -0.078 |
service | -0.075 |
ww | -0.075 |
www | -0.074 |
ths | -0.072 |
Token | The |
Token ID | 383 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
like | +0.016 |
everywhere | +0.011 |
favorite | +0.010 |
liked | +0.010 |
wherever | +0.009 |
Neg logit contributions | |
ister | -0.022 |
ww | -0.022 |
ths | -0.022 |
www | -0.021 |
service | -0.021 |
Token | ice |
Token ID | 4771 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
ister | +0.028 |
ww | +0.028 |
ths | +0.028 |
www | +0.028 |
avail | +0.027 |
Neg logit contributions | |
like | -0.030 |
favorite | -0.022 |
liked | -0.022 |
everywhere | -0.022 |
dolls | -0.021 |
Token | cream |
Token ID | 8566 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
ister | +0.066 |
ww | +0.065 |
ths | +0.064 |
www | +0.063 |
service | +0.061 |
Neg logit contributions | |
like | -0.097 |
everywhere | -0.075 |
favorite | -0.074 |
liked | -0.074 |
wherever | -0.070 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
like | +0.016 |
aces | +0.011 |
ti | +0.010 |
pad | +0.009 |
liked | +0.009 |
Neg logit contributions | |
ister | -0.029 |
ama | -0.028 |
storm | -0.027 |
ww | -0.026 |
ule | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
like | +0.042 |
pad | +0.032 |
everywhere | +0.032 |
aces | +0.030 |
favorite | +0.030 |
Neg logit contributions | |
ww | -0.069 |
ister | -0.068 |
sermon | -0.067 |
body | -0.066 |
storm | -0.066 |
Token | time |
Token ID | 640 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
like | +0.043 |
aces | +0.035 |
dolls | +0.035 |
everywhere | +0.035 |
wherever | +0.034 |
Neg logit contributions | |
ww | -0.033 |
www | -0.031 |
ister | -0.030 |
storm | -0.029 |
ths | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ister | +0.010 |
ww | +0.010 |
ama | +0.009 |
storm | +0.009 |
ths | +0.009 |
Neg logit contributions | |
like | -0.010 |
aces | -0.008 |
pad | -0.008 |
favorite | -0.008 |
pads | -0.008 |
Token | there |
Token ID | 612 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
like | +0.029 |
aces | +0.025 |
pad | +0.023 |
pads | +0.023 |
skirts | +0.022 |
Neg logit contributions | |
ww | -0.032 |
body | -0.031 |
storm | -0.030 |
ister | -0.030 |
ths | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
like | +0.015 |
aces | +0.011 |
pad | +0.011 |
favorite | +0.011 |
everywhere | +0.011 |
Neg logit contributions | |
ister | -0.013 |
ww | -0.013 |
ths | -0.012 |
www | -0.012 |
storm | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
ww | +0.028 |
www | +0.026 |
storm | +0.026 |
ister | +0.026 |
body | +0.026 |
Neg logit contributions | |
like | -0.016 |
aces | -0.011 |
everywhere | -0.011 |
pad | -0.011 |
liked | -0.011 |
Token | big |
Token ID | 1263 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
like | +0.014 |
liked | +0.010 |
favorite | +0.010 |
everywhere | +0.010 |
dolls | +0.009 |
Neg logit contributions | |
ister | -0.019 |
ww | -0.019 |
ths | -0.019 |
www | -0.019 |
service | -0.019 |
Token | elephant |
Token ID | 20950 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
ths | +0.009 |
ister | +0.009 |
ww | +0.009 |
www | +0.008 |
avail | +0.008 |
Neg logit contributions | |
like | -0.007 |
liked | -0.005 |
everywhere | -0.004 |
favorite | -0.004 |
back | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ister | +0.021 |
ww | +0.021 |
ths | +0.020 |
www | +0.020 |
avail | +0.020 |
Neg logit contributions | |
like | -0.010 |
everywhere | -0.006 |
liked | -0.006 |
favorite | -0.006 |
around | -0.005 |
Token | He |
Token ID | 679 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
like | +0.002 |
everywhere | +0.002 |
favorite | +0.002 |
liked | +0.001 |
pad | +0.001 |
Neg logit contributions | |
ister | -0.003 |
ww | -0.003 |
www | -0.003 |
ths | -0.003 |
service | -0.003 |
Token | very |
Token ID | 845 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ww | +0.028 |
ister | +0.028 |
ths | +0.027 |
www | +0.027 |
avail | +0.027 |
Neg logit contributions | |
like | -0.019 |
everywhere | -0.012 |
liked | -0.012 |
favorite | -0.012 |
around | -0.011 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ths | +0.070 |
ww | +0.069 |
avail | +0.068 |
ister | +0.068 |
irens | +0.066 |
Neg logit contributions | |
like | -0.045 |
liked | -0.029 |
favorite | -0.027 |
around | -0.027 |
both | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
ister | +0.044 |
ww | +0.044 |
ths | +0.043 |
www | +0.043 |
avail | +0.042 |
Neg logit contributions | |
like | -0.016 |
everywhere | -0.007 |
favorite | -0.007 |
liked | -0.007 |
around | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
ister | +0.024 |
ww | +0.024 |
www | +0.023 |
ths | +0.023 |
service | +0.023 |
Neg logit contributions | |
like | -0.017 |
everywhere | -0.012 |
favorite | -0.012 |
liked | -0.011 |
dolls | -0.011 |
Token | wanted |
Token ID | 2227 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
ister | +0.021 |
ww | +0.020 |
avail | +0.020 |
ths | +0.020 |
service | +0.020 |
Neg logit contributions | |
like | -0.014 |
liked | -0.010 |
everywhere | -0.009 |
favorite | -0.009 |
both | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ister | +0.036 |
ww | +0.036 |
ths | +0.036 |
www | +0.035 |
avail | +0.034 |
Neg logit contributions | |
like | -0.011 |
everywhere | -0.005 |
favorite | -0.005 |
liked | -0.004 |
back | -0.004 |
Token | see |
Token ID | 766 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ww | +0.075 |
ths | +0.074 |
www | +0.070 |
ister | +0.070 |
irens | +0.070 |
Neg logit contributions | |
like | -0.054 |
both | -0.034 |
all | -0.034 |
love | -0.033 |
liked | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
like | +0.019 |
liked | +0.013 |
favorite | +0.012 |
pad | +0.012 |
aces | +0.012 |
Neg logit contributions | |
ister | -0.031 |
ths | -0.030 |
service | -0.030 |
avail | -0.029 |
ww | -0.029 |
Token | mountain |
Token ID | 8598 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
like | +0.028 |
everywhere | +0.021 |
favorite | +0.021 |
liked | +0.020 |
dolls | +0.019 |
Neg logit contributions | |
ister | -0.025 |
ww | -0.024 |
ths | -0.024 |
www | -0.024 |
avail | -0.023 |
Token | up |
Token ID | 510 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ww | +0.085 |
www | +0.082 |
ister | +0.081 |
ths | +0.079 |
avail | +0.079 |
Neg logit contributions | |
like | -0.032 |
everywhere | -0.015 |
around | -0.014 |
liked | -0.013 |
all | -0.013 |
Token | close |
Token ID | 1969 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ister | +0.032 |
ww | +0.032 |
ths | +0.032 |
www | +0.031 |
service | +0.031 |
Neg logit contributions | |
like | -0.018 |
everywhere | -0.012 |
favorite | -0.012 |
liked | -0.011 |
dolls | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
like | +0.004 |
favorite | +0.003 |
pad | +0.002 |
ti | +0.002 |
liked | +0.002 |
Neg logit contributions | |
ister | -0.008 |
service | -0.008 |
ths | -0.008 |
site | -0.008 |
storm | -0.008 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
like | +0.018 |
everywhere | +0.013 |
favorite | +0.012 |
liked | +0.012 |
around | +0.011 |
Neg logit contributions | |
ww | -0.025 |
ister | -0.025 |
www | -0.024 |
ths | -0.024 |
service | -0.024 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ister | +0.046 |
ths | +0.045 |
ww | +0.044 |
service | +0.043 |
www | +0.043 |
Neg logit contributions | |
like | -0.035 |
favorite | -0.025 |
everywhere | -0.025 |
wherever | -0.024 |
pad | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
aces | +0.029 |
like | +0.029 |
dolls | +0.026 |
Whe | +0.026 |
pad | +0.026 |
Neg logit contributions | |
ister | -0.049 |
storm | -0.048 |
ths | -0.047 |
ww | -0.047 |
service | -0.046 |
Token | went |
Token ID | 1816 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
like | +0.006 |
everywhere | +0.004 |
liked | +0.004 |
favorite | +0.004 |
around | +0.003 |
Neg logit contributions | |
ister | -0.008 |
ww | -0.008 |
ths | -0.008 |
www | -0.008 |
service | -0.007 |
Token | back |
Token ID | 736 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ister | +0.042 |
ths | +0.041 |
ww | +0.041 |
service | +0.041 |
www | +0.041 |
Neg logit contributions | |
like | -0.018 |
liked | -0.010 |
favorite | -0.010 |
everywhere | -0.009 |
pad | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ister | +0.057 |
service | +0.057 |
ths | +0.056 |
ww | +0.055 |
www | +0.054 |
Neg logit contributions | |
like | -0.030 |
liked | -0.019 |
favorite | -0.018 |
everywhere | -0.018 |
aces | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
ister | +0.045 |
ww | +0.045 |
ths | +0.044 |
www | +0.044 |
service | +0.043 |
Neg logit contributions | |
like | -0.027 |
everywhere | -0.017 |
favorite | -0.017 |
liked | -0.017 |
around | -0.015 |
Token | kitchen |
Token ID | 9592 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
like | +0.017 |
aces | +0.012 |
liked | +0.012 |
everywhere | +0.012 |
favorite | +0.012 |
Neg logit contributions | |
service | -0.016 |
ister | -0.016 |
storm | -0.015 |
ths | -0.015 |
ww | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
like | +0.009 |
favorite | +0.005 |
everywhere | +0.005 |
liked | +0.005 |
wherever | +0.004 |
Neg logit contributions | |
service | -0.020 |
ister | -0.019 |
site | -0.019 |
ths | -0.019 |
sermon | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
like | +0.014 |
everywhere | +0.010 |
favorite | +0.010 |
aces | +0.010 |
pad | +0.010 |
Neg logit contributions | |
ww | -0.014 |
www | -0.014 |
ister | -0.014 |
storm | -0.014 |
irens | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ister | +0.029 |
ww | +0.029 |
ths | +0.028 |
www | +0.028 |
service | +0.028 |
Neg logit contributions | |
like | -0.011 |
everywhere | -0.006 |
favorite | -0.005 |
liked | -0.005 |
dolls | -0.004 |
Token | be |
Token ID | 307 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ww | +0.056 |
ths | +0.054 |
www | +0.053 |
ister | +0.052 |
izing | +0.051 |
Neg logit contributions | |
like | -0.037 |
both | -0.024 |
all | -0.023 |
back | -0.022 |
love | -0.021 |
Token | saved |
Token ID | 7448 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ister | +0.004 |
ww | +0.004 |
ths | +0.004 |
www | +0.004 |
service | +0.004 |
Neg logit contributions | |
like | -0.003 |
everywhere | -0.002 |
favorite | -0.002 |
liked | -0.002 |
dolls | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ww | +0.038 |
ister | +0.038 |
ths | +0.038 |
www | +0.037 |
service | +0.037 |
Neg logit contributions | |
like | -0.021 |
everywhere | -0.013 |
favorite | -0.012 |
liked | -0.012 |
around | -0.011 |
Token | But |
Token ID | 887 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ister | +0.036 |
ww | +0.036 |
ths | +0.036 |
www | +0.035 |
service | +0.035 |
Neg logit contributions | |
like | -0.017 |
everywhere | -0.010 |
favorite | -0.010 |
liked | -0.010 |
around | -0.008 |
Token | no |
Token ID | 645 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ww | +0.061 |
ister | +0.061 |
www | +0.060 |
iren | +0.059 |
sermon | +0.059 |
Neg logit contributions | |
like | -0.035 |
everywhere | -0.021 |
all | -0.020 |
both | -0.020 |
liked | -0.020 |
Token | one |
Token ID | 530 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ister | +0.042 |
irens | +0.040 |
iren | +0.039 |
sermon | +0.038 |
asis | +0.038 |
Neg logit contributions | |
like | -0.043 |
but | -0.029 |
favorite | -0.029 |
love | -0.029 |
liked | -0.029 |
Token | came |
Token ID | 1625 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
ister | +0.065 |
ww | +0.064 |
avail | +0.064 |
ths | +0.063 |
www | +0.062 |
Neg logit contributions | |
like | -0.042 |
liked | -0.029 |
everywhere | -0.027 |
favorite | -0.026 |
around | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
like | +0.011 |
everywhere | +0.006 |
favorite | +0.006 |
liked | +0.006 |
back | +0.005 |
Neg logit contributions | |
ww | -0.024 |
ister | -0.024 |
ths | -0.024 |
www | -0.024 |
service | -0.023 |
Token | help |
Token ID | 1037 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ww | +0.005 |
www | +0.005 |
ths | +0.005 |
ister | +0.005 |
sermon | +0.004 |
Neg logit contributions | |
like | -0.003 |
liked | -0.001 |
everywhere | -0.001 |
love | -0.001 |
favorite | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
ww | +0.043 |
ister | +0.043 |
ths | +0.043 |
www | +0.042 |
service | +0.041 |
Neg logit contributions | |
like | -0.018 |
everywhere | -0.009 |
liked | -0.009 |
favorite | -0.008 |
around | -0.007 |
Token | Tom |
Token ID | 13787 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ister | +0.012 |
ww | +0.012 |
ths | +0.012 |
www | +0.012 |
service | +0.012 |
Neg logit contributions | |
like | -0.010 |
favorite | -0.007 |
everywhere | -0.007 |
liked | -0.007 |
pad | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
like | +0.003 |
everywhere | +0.002 |
favorite | +0.002 |
wherever | +0.002 |
hers | +0.001 |
Neg logit contributions | |
ister | -0.007 |
ww | -0.007 |
ths | -0.007 |
www | -0.007 |
beast | -0.007 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
like | +0.009 |
everywhere | +0.004 |
favorite | +0.004 |
liked | +0.004 |
pad | +0.003 |
Neg logit contributions | |
ister | -0.029 |
ww | -0.029 |
ths | -0.029 |
www | -0.029 |
service | -0.028 |
Token | nod |
Token ID | 18666 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
like | +0.039 |
favorite | +0.030 |
everywhere | +0.029 |
dolls | +0.028 |
pad | +0.028 |
Neg logit contributions | |
ister | -0.048 |
service | -0.046 |
ths | -0.045 |
storm | -0.045 |
ww | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
like | +0.021 |
aces | +0.015 |
favorite | +0.015 |
pad | +0.014 |
everywhere | +0.014 |
Neg logit contributions | |
ister | -0.043 |
storm | -0.043 |
service | -0.042 |
ww | -0.041 |
avail | -0.041 |
Token | They |
Token ID | 1119 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
like | +0.023 |
everywhere | +0.015 |
favorite | +0.015 |
liked | +0.015 |
around | +0.013 |
Neg logit contributions | |
ister | -0.036 |
ww | -0.036 |
ths | -0.035 |
www | -0.035 |
service | -0.034 |
Token | are |
Token ID | 389 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
like | +0.039 |
everywhere | +0.035 |
dolls | +0.035 |
aces | +0.035 |
pad | +0.035 |
Neg logit contributions | |
ister | -0.036 |
storm | -0.034 |
service | -0.033 |
www | -0.031 |
ww | -0.031 |
Token | OK |
Token ID | 7477 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
like | +0.014 |
pad | +0.011 |
aces | +0.010 |
wherever | +0.010 |
everywhere | +0.010 |
Neg logit contributions | |
ister | -0.017 |
storm | -0.016 |
ww | -0.016 |
service | -0.015 |
ths | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
ister | +0.026 |
ww | +0.025 |
ths | +0.025 |
service | +0.025 |
storm | +0.025 |
Neg logit contributions | |
like | -0.009 |
favorite | -0.005 |
everywhere | -0.005 |
liked | -0.005 |
pad | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
like | +0.015 |
liked | +0.009 |
favorite | +0.009 |
everywhere | +0.009 |
both | +0.008 |
Neg logit contributions | |
ister | -0.025 |
ww | -0.024 |
ths | -0.024 |
www | -0.024 |
service | -0.023 |
Token | are |
Token ID | 389 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
like | +0.035 |
everywhere | +0.032 |
dolls | +0.031 |
aces | +0.031 |
pad | +0.031 |
Neg logit contributions | |
ister | -0.035 |
storm | -0.034 |
service | -0.034 |
ww | -0.031 |
www | -0.031 |
Token | could |
Token ID | 714 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
ister | +0.027 |
ww | +0.027 |
avail | +0.026 |
irens | +0.026 |
www | +0.026 |
Neg logit contributions | |
like | -0.016 |
liked | -0.012 |
everywhere | -0.010 |
both | -0.010 |
all | -0.010 |
Token | imagine |
Token ID | 5967 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ww | +0.085 |
www | +0.081 |
ths | +0.080 |
ister | +0.080 |
irens | +0.077 |
Neg logit contributions | |
like | -0.064 |
liked | -0.041 |
both | -0.040 |
favorite | -0.040 |
all | -0.040 |
Token | how |
Token ID | 703 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
ister | +0.030 |
ww | +0.030 |
ths | +0.030 |
www | +0.029 |
service | +0.029 |
Neg logit contributions | |
like | -0.018 |
everywhere | -0.012 |
favorite | -0.011 |
liked | -0.011 |
around | -0.010 |
Token | it |
Token ID | 340 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
like | +0.012 |
liked | +0.008 |
everywhere | +0.008 |
favorite | +0.008 |
around | +0.007 |
Neg logit contributions | |
ister | -0.020 |
ww | -0.020 |
ths | -0.020 |
www | -0.020 |
avail | -0.019 |
Token | would |
Token ID | 561 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ister | +0.048 |
ww | +0.048 |
www | +0.046 |
ths | +0.045 |
avail | +0.045 |
Neg logit contributions | |
like | -0.030 |
liked | -0.020 |
everywhere | -0.019 |
favorite | -0.018 |
around | -0.018 |
Token | be |
Token ID | 307 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ww | +0.038 |
ister | +0.038 |
ths | +0.037 |
www | +0.037 |
avail | +0.035 |
Neg logit contributions | |
like | -0.038 |
everywhere | -0.027 |
liked | -0.026 |
favorite | -0.026 |
back | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
like | +0.003 |
favorite | +0.002 |
everywhere | +0.002 |
liked | +0.002 |
dolls | +0.002 |
Neg logit contributions | |
ister | -0.007 |
ww | -0.007 |
ths | -0.007 |
www | -0.007 |
service | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ww | +0.024 |
ths | +0.023 |
www | +0.023 |
ister | +0.023 |
irens | +0.022 |
Neg logit contributions | |
like | -0.022 |
all | -0.014 |
love | -0.014 |
everywhere | -0.014 |
liked | -0.014 |
Token | as |
Token ID | 355 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ister | +0.005 |
ww | +0.005 |
ths | +0.005 |
www | +0.005 |
service | +0.005 |
Neg logit contributions | |
like | -0.003 |
everywhere | -0.002 |
favorite | -0.002 |
liked | -0.002 |
dolls | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
ths | +0.053 |
ww | +0.053 |
ister | +0.053 |
www | +0.052 |
avail | +0.051 |
Neg logit contributions | |
like | -0.036 |
everywhere | -0.023 |
favorite | -0.022 |
liked | -0.022 |
all | -0.021 |
Token | as |
Token ID | 355 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
like | +0.038 |
everywhere | +0.022 |
liked | +0.022 |
favorite | +0.022 |
dolls | +0.018 |
Neg logit contributions | |
ister | -0.091 |
ww | -0.091 |
ths | -0.090 |
service | -0.089 |
www | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
like | +0.013 |
favorite | +0.008 |
everywhere | +0.008 |
liked | +0.008 |
pad | +0.007 |
Neg logit contributions | |
ister | -0.023 |
ww | -0.022 |
www | -0.022 |
ths | -0.022 |
service | -0.022 |
Token | " |
Token ID | 1 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
ww | +0.011 |
ister | +0.010 |
www | +0.010 |
ths | +0.010 |
service | +0.009 |
Neg logit contributions | |
like | -0.011 |
favorite | -0.008 |
everywhere | -0.008 |
liked | -0.007 |
aces | -0.007 |
Token | Oh |
Token ID | 5812 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
like | +0.086 |
everywhere | +0.064 |
favorite | +0.064 |
liked | +0.061 |
around | +0.059 |
Neg logit contributions | |
ww | -0.091 |
ister | -0.089 |
ths | -0.087 |
www | -0.087 |
service | -0.085 |
Token | no |
Token ID | 645 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
like | +0.013 |
everywhere | +0.008 |
favorite | +0.008 |
liked | +0.008 |
around | +0.008 |
Neg logit contributions | |
ww | -0.025 |
ister | -0.024 |
www | -0.024 |
ths | -0.024 |
service | -0.023 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ister | +0.026 |
ths | +0.025 |
ww | +0.025 |
www | +0.025 |
service | +0.024 |
Neg logit contributions | |
like | -0.014 |
everywhere | -0.008 |
favorite | -0.008 |
liked | -0.008 |
dolls | -0.007 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
like | +0.019 |
everywhere | +0.012 |
favorite | +0.012 |
liked | +0.012 |
pad | +0.011 |
Neg logit contributions | |
ister | -0.032 |
ww | -0.032 |
www | -0.031 |
ths | -0.031 |
service | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
ister | +0.006 |
ww | +0.006 |
ths | +0.006 |
www | +0.006 |
avail | +0.006 |
Neg logit contributions | |
like | -0.004 |
everywhere | -0.002 |
liked | -0.002 |
favorite | -0.002 |
around | -0.002 |
Token | Ben |
Token ID | 3932 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
like | +0.012 |
everywhere | +0.006 |
favorite | +0.006 |
liked | +0.006 |
around | +0.005 |
Neg logit contributions | |
ister | -0.031 |
ww | -0.031 |
ths | -0.031 |
www | -0.030 |
service | -0.030 |
Token | say |
Token ID | 910 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
like | +0.011 |
favorite | +0.009 |
everywhere | +0.009 |
liked | +0.009 |
wherever | +0.008 |
Neg logit contributions | |
ister | -0.008 |
ww | -0.008 |
ths | -0.008 |
www | -0.008 |
service | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
like | +0.013 |
liked | +0.008 |
favorite | +0.007 |
everywhere | +0.007 |
pad | +0.007 |
Neg logit contributions | |
ister | -0.034 |
service | -0.033 |
ww | -0.032 |
ths | -0.032 |
www | -0.032 |
Token | They |
Token ID | 1119 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
like | +0.028 |
aces | +0.019 |
favorite | +0.019 |
everywhere | +0.019 |
pad | +0.018 |
Neg logit contributions | |
ister | -0.037 |
ww | -0.037 |
service | -0.036 |
www | -0.036 |
ths | -0.036 |
Token | surprise |
Token ID | 5975 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
like | +0.019 |
everywhere | +0.013 |
liked | +0.013 |
favorite | +0.013 |
around | +0.013 |
Neg logit contributions | |
ww | -0.022 |
ister | -0.022 |
www | -0.021 |
ths | -0.021 |
service | -0.021 |
Token | for |
Token ID | 329 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ister | +0.039 |
service | +0.038 |
ths | +0.038 |
ww | +0.038 |
www | +0.037 |
Neg logit contributions | |
like | -0.016 |
favorite | -0.009 |
liked | -0.009 |
everywhere | -0.008 |
aces | -0.008 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
ister | +0.056 |
ww | +0.056 |
ths | +0.055 |
www | +0.055 |
service | +0.054 |
Neg logit contributions | |
like | -0.024 |
everywhere | -0.014 |
favorite | -0.013 |
liked | -0.013 |
dolls | -0.011 |
Token | - |
Token ID | 532 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
like | +0.009 |
favorite | +0.006 |
liked | +0.005 |
everywhere | +0.005 |
aces | +0.005 |
Neg logit contributions | |
ister | -0.018 |
ths | -0.018 |
service | -0.018 |
ww | -0.017 |
www | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
like | +0.017 |
aces | +0.012 |
everywhere | +0.012 |
favorite | +0.012 |
liked | +0.011 |
Neg logit contributions | |
ister | -0.028 |
ww | -0.028 |
ths | -0.028 |
www | -0.027 |
service | -0.027 |
Token | new |
Token ID | 649 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
like | +0.003 |
everywhere | +0.002 |
favorite | +0.002 |
liked | +0.002 |
around | +0.002 |
Neg logit contributions | |
ister | -0.004 |
ww | -0.004 |
ths | -0.004 |
www | -0.004 |
service | -0.004 |
Token | doll |
Token ID | 3654 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
like | +0.016 |
everywhere | +0.012 |
aces | +0.012 |
wherever | +0.011 |
around | +0.011 |
Neg logit contributions | |
ww | -0.017 |
www | -0.017 |
ister | -0.017 |
storm | -0.016 |
service | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
like | +0.017 |
favorite | +0.012 |
everywhere | +0.011 |
liked | +0.011 |
dolls | +0.010 |
Neg logit contributions | |
ister | -0.027 |
ww | -0.026 |
www | -0.026 |
ths | -0.026 |
service | -0.025 |
Token | play |
Token ID | 711 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ister | +0.052 |
ww | +0.051 |
ths | +0.051 |
www | +0.050 |
service | +0.049 |
Neg logit contributions | |
like | -0.032 |
everywhere | -0.021 |
favorite | -0.021 |
liked | -0.021 |
around | -0.018 |
Token | with |
Token ID | 351 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
like | +0.017 |
favorite | +0.014 |
pad | +0.014 |
everywhere | +0.013 |
liked | +0.012 |
Neg logit contributions | |
ister | -0.034 |
site | -0.032 |
ths | -0.032 |
ww | -0.032 |
service | -0.032 |
Token | at |
Token ID | 379 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
like | +0.035 |
favorite | +0.024 |
pad | +0.022 |
liked | +0.022 |
aces | +0.022 |
Neg logit contributions | |
ister | -0.073 |
ths | -0.070 |
service | -0.070 |
ww | -0.069 |
www | -0.068 |
Token | in |
Token ID | 287 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
like | +0.010 |
liked | +0.009 |
pad | +0.008 |
favorites | +0.008 |
favorite | +0.008 |
Neg logit contributions | |
ister | -0.016 |
storm | -0.015 |
ww | -0.015 |
ths | -0.015 |
beast | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
like | +0.012 |
favorite | +0.009 |
liked | +0.009 |
aces | +0.008 |
pad | +0.008 |
Neg logit contributions | |
ister | -0.024 |
service | -0.023 |
avail | -0.023 |
storm | -0.023 |
ths | -0.023 |
Token | She |
Token ID | 1375 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
ister | +0.014 |
ww | +0.014 |
ths | +0.014 |
www | +0.014 |
service | +0.014 |
Neg logit contributions | |
like | -0.010 |
everywhere | -0.006 |
favorite | -0.006 |
liked | -0.006 |
dolls | -0.005 |
Token | soon |
Token ID | 2582 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ister | +0.017 |
ww | +0.017 |
avail | +0.016 |
ths | +0.016 |
www | +0.016 |
Neg logit contributions | |
like | -0.011 |
liked | -0.008 |
favorite | -0.008 |
everywhere | -0.007 |
both | -0.007 |
Token | realized |
Token ID | 6939 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ww | +0.037 |
ister | +0.037 |
www | +0.036 |
ths | +0.036 |
storm | +0.035 |
Neg logit contributions | |
like | -0.029 |
favorite | -0.021 |
everywhere | -0.020 |
liked | -0.019 |
dolls | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
ww | +0.038 |
ister | +0.037 |
www | +0.037 |
ths | +0.037 |
service | +0.036 |
Neg logit contributions | |
like | -0.033 |
everywhere | -0.023 |
favorite | -0.023 |
liked | -0.023 |
around | -0.021 |
Token | couldn |
Token ID | 3521 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
like | +0.014 |
liked | +0.009 |
everywhere | +0.009 |
favorite | +0.008 |
around | +0.008 |
Neg logit contributions | |
ww | -0.025 |
ister | -0.025 |
www | -0.024 |
avail | -0.024 |
ths | -0.024 |
Token | 't |
Token ID | 470 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
avail | +0.125 |
ww | +0.124 |
ths | +0.124 |
sermon | +0.123 |
www | +0.120 |
Neg logit contributions | |
like | -0.087 |
all | -0.067 |
both | -0.066 |
and | -0.065 |
. | -0.065 |
Token | swim |
Token ID | 9422 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ww | +0.057 |
ister | +0.056 |
ths | +0.056 |
www | +0.055 |
avail | +0.053 |
Neg logit contributions | |
like | -0.060 |
liked | -0.043 |
everywhere | -0.042 |
favorite | -0.042 |
around | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
like | +0.008 |
pad | +0.006 |
liked | +0.006 |
dolls | +0.006 |
favorite | +0.006 |
Neg logit contributions | |
ister | -0.020 |
ww | -0.019 |
storm | -0.019 |
ths | -0.018 |
www | -0.018 |
Token | started |
Token ID | 2067 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ister | +0.010 |
ww | +0.010 |
www | +0.010 |
ths | +0.010 |
avail | +0.010 |
Neg logit contributions | |
like | -0.007 |
liked | -0.005 |
everywhere | -0.005 |
all | -0.004 |
favorite | -0.004 |
Token | truck |
Token ID | 7779 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
like | +0.020 |
favorite | +0.015 |
liked | +0.015 |
everywhere | +0.015 |
around | +0.014 |
Neg logit contributions | |
ister | -0.016 |
ww | -0.015 |
www | -0.015 |
storm | -0.015 |
service | -0.015 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
ww | +0.042 |
ths | +0.042 |
ister | +0.042 |
avail | +0.041 |
www | +0.041 |
Neg logit contributions | |
like | -0.028 |
everywhere | -0.018 |
liked | -0.017 |
favorite | -0.017 |
around | -0.016 |
Token | Anna |
Token ID | 11735 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
like | +0.008 |
liked | +0.004 |
everywhere | +0.004 |
favorite | +0.004 |
both | +0.004 |
Neg logit contributions | |
ths | -0.023 |
ister | -0.023 |
ww | -0.023 |
www | -0.022 |
service | -0.022 |
Token | says |
Token ID | 1139 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
ister | +0.001 |
ww | +0.001 |
www | +0.001 |
ths | +0.001 |
service | +0.001 |
Neg logit contributions | |
like | -0.001 |
everywhere | -0.001 |
favorite | -0.001 |
wherever | -0.001 |
liked | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
like | +0.012 |
favorite | +0.007 |
liked | +0.007 |
everywhere | +0.007 |
pad | +0.007 |
Neg logit contributions | |
ister | -0.029 |
service | -0.028 |
ths | -0.028 |
ww | -0.028 |
sermon | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
like | +0.019 |
favorite | +0.013 |
everywhere | +0.012 |
liked | +0.011 |
pad | +0.011 |
Neg logit contributions | |
ister | -0.032 |
ww | -0.031 |
www | -0.030 |
iren | -0.030 |
ths | -0.030 |
Token | It |
Token ID | 1026 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
like | +0.107 |
everywhere | +0.084 |
favorite | +0.081 |
liked | +0.076 |
dolls | +0.076 |
Neg logit contributions | |
ww | -0.108 |
ister | -0.106 |
www | -0.104 |
ths | -0.102 |
service | -0.100 |
Token | has |
Token ID | 468 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
ister | +0.007 |
ww | +0.007 |
ths | +0.007 |
www | +0.007 |
avail | +0.007 |
Neg logit contributions | |
like | -0.006 |
everywhere | -0.004 |
liked | -0.004 |
favorite | -0.004 |
around | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
like | +0.047 |
everywhere | +0.028 |
liked | +0.028 |
favorite | +0.027 |
around | +0.025 |
Neg logit contributions | |
ww | -0.100 |
www | -0.096 |
ister | -0.096 |
service | -0.095 |
ths | -0.095 |
Token | bow |
Token ID | 9563 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
like | +0.021 |
favorite | +0.015 |
everywhere | +0.015 |
liked | +0.014 |
back | +0.014 |
Neg logit contributions | |
ths | -0.024 |
ister | -0.023 |
ww | -0.022 |
avail | -0.022 |
service | -0.022 |
Token | like |
Token ID | 588 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
like | +0.038 |
liked | +0.027 |
favorite | +0.027 |
everywhere | +0.025 |
love | +0.023 |
Neg logit contributions | |
ister | -0.070 |
ww | -0.070 |
www | -0.067 |
service | -0.065 |
beast | -0.065 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ister | +0.001 |
ths | +0.001 |
service | +0.001 |
ww | +0.001 |
storm | +0.001 |
Neg logit contributions | |
like | -0.001 |
everywhere | -0.001 |
liked | -0.001 |
pad | -0.001 |
wherever | -0.001 |
Token | hugged |
Token ID | 41130 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
ister | +0.060 |
ths | +0.059 |
ww | +0.058 |
www | +0.057 |
service | +0.057 |
Neg logit contributions | |
like | -0.049 |
favorite | -0.036 |
everywhere | -0.035 |
wherever | -0.034 |
pad | -0.033 |
Token | them |
Token ID | 606 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
like | +0.016 |
favorite | +0.013 |
pad | +0.013 |
aces | +0.013 |
liked | +0.012 |
Neg logit contributions | |
ister | -0.020 |
ths | -0.019 |
irens | -0.019 |
service | -0.019 |
iren | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
like | +0.078 |
ti | +0.068 |
favorites | +0.061 |
aces | +0.060 |
pad | +0.060 |
Neg logit contributions | |
service | -0.117 |
ister | -0.112 |
ths | -0.110 |
ama | -0.107 |
iren | -0.104 |
Token | said |
Token ID | 531 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
like | +0.008 |
everywhere | +0.006 |
favorite | +0.006 |
liked | +0.006 |
around | +0.005 |
Neg logit contributions | |
ister | -0.007 |
ww | -0.007 |
ths | -0.007 |
www | -0.007 |
service | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
like | +0.012 |
pad | +0.008 |
favorite | +0.008 |
liked | +0.008 |
everywhere | +0.008 |
Neg logit contributions | |
ister | -0.018 |
ww | -0.017 |
ths | -0.017 |
service | -0.017 |
www | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
like | +0.063 |
favorite | +0.037 |
everywhere | +0.035 |
liked | +0.031 |
pad | +0.030 |
Neg logit contributions | |
ister | -0.146 |
ths | -0.144 |
ww | -0.141 |
service | -0.141 |
www | -0.138 |
Token | I |
Token ID | 40 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
like | +0.071 |
liked | +0.050 |
everywhere | +0.047 |
favorite | +0.047 |
both | +0.043 |
Neg logit contributions | |
ister | -0.097 |
ww | -0.094 |
ths | -0.094 |
avail | -0.093 |
www | -0.092 |
Token | forgive |
Token ID | 20927 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
like | +0.053 |
everywhere | +0.043 |
favorite | +0.040 |
aces | +0.040 |
around | +0.039 |
Neg logit contributions | |
ister | -0.058 |
ww | -0.057 |
service | -0.055 |
www | -0.055 |
ths | -0.053 |
Token | you |
Token ID | 345 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
ister | +0.019 |
ww | +0.019 |
ths | +0.018 |
www | +0.018 |
service | +0.017 |
Neg logit contributions | |
like | -0.036 |
everywhere | -0.028 |
favorite | -0.028 |
liked | -0.028 |
pad | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
like | +0.052 |
liked | +0.036 |
favorite | +0.035 |
everywhere | +0.035 |
pad | +0.032 |
Neg logit contributions | |
ister | -0.093 |
service | -0.089 |
ths | -0.088 |
ww | -0.088 |
storm | -0.086 |
Token | lion |
Token ID | 18744 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
like | +0.034 |
everywhere | +0.025 |
liked | +0.025 |
favorite | +0.025 |
around | +0.023 |
Neg logit contributions | |
ww | -0.031 |
ister | -0.031 |
www | -0.030 |
ths | -0.030 |
service | -0.030 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
like | +0.031 |
favorite | +0.022 |
everywhere | +0.022 |
liked | +0.022 |
wherever | +0.020 |
Neg logit contributions | |
ister | -0.042 |
ww | -0.042 |
www | -0.040 |
ths | -0.040 |
service | -0.040 |
Token | he |
Token ID | 339 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
like | +0.026 |
everywhere | +0.015 |
favorite | +0.015 |
liked | +0.014 |
around | +0.012 |
Neg logit contributions | |
ister | -0.059 |
ww | -0.059 |
ths | -0.058 |
www | -0.058 |
service | -0.057 |
Token | said |
Token ID | 531 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ister | +0.000 |
ww | +0.000 |
ths | +0.000 |
www | +0.000 |
service | +0.000 |
Neg logit contributions | |
like | -0.000 |
liked | -0.000 |
everywhere | -0.000 |
favorite | -0.000 |
both | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
like | +0.005 |
pad | +0.004 |
liked | +0.004 |
everywhere | +0.004 |
favorite | +0.003 |
Neg logit contributions | |
ister | -0.009 |
service | -0.009 |
avail | -0.009 |
ths | -0.009 |
oo | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
like | +0.020 |
everywhere | +0.013 |
favorite | +0.013 |
wherever | +0.012 |
pad | +0.012 |
Neg logit contributions | |
ister | -0.034 |
ww | -0.033 |
www | -0.032 |
service | -0.032 |
iren | -0.032 |
Token | It |
Token ID | 1026 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
like | +0.105 |
everywhere | +0.081 |
favorite | +0.079 |
liked | +0.074 |
around | +0.072 |
Neg logit contributions | |
ww | -0.111 |
ister | -0.108 |
www | -0.106 |
ths | -0.105 |
service | -0.102 |
Token | is |
Token ID | 318 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ister | +0.003 |
ths | +0.003 |
avail | +0.003 |
ww | +0.003 |
www | +0.003 |
Neg logit contributions | |
like | -0.003 |
liked | -0.002 |
everywhere | -0.002 |
favorite | -0.002 |
both | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
like | +0.005 |
liked | +0.003 |
favorite | +0.003 |
everywhere | +0.003 |
wherever | +0.003 |
Neg logit contributions | |
ww | -0.007 |
ister | -0.007 |
www | -0.007 |
ths | -0.007 |
storm | -0.007 |
Token | cool |
Token ID | 3608 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ths | +0.084 |
ister | +0.082 |
avail | +0.080 |
service | +0.078 |
ww | +0.078 |
Neg logit contributions | |
like | -0.052 |
liked | -0.033 |
everywhere | -0.033 |
favorite | -0.033 |
both | -0.029 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
like | +0.025 |
favorite | +0.016 |
liked | +0.016 |
everywhere | +0.016 |
dolls | +0.014 |
Neg logit contributions | |
ww | -0.044 |
ister | -0.044 |
www | -0.043 |
ths | -0.043 |
service | -0.042 |
Token | other |
Token ID | 584 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
like | +0.007 |
liked | +0.005 |
favorite | +0.005 |
everywhere | +0.005 |
pad | +0.005 |
Neg logit contributions | |
ww | -0.008 |
ister | -0.008 |
service | -0.008 |
www | -0.008 |
body | -0.008 |
Token | ," |
Token ID | 553 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
like | +0.052 |
everywhere | +0.035 |
favorite | +0.035 |
liked | +0.035 |
wherever | +0.031 |
Neg logit contributions | |
ister | -0.073 |
ww | -0.072 |
ths | -0.071 |
www | -0.070 |
service | -0.069 |
Token | Ben |
Token ID | 3932 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
like | +0.009 |
everywhere | +0.004 |
favorite | +0.004 |
liked | +0.004 |
both | +0.003 |
Neg logit contributions | |
ister | -0.025 |
ww | -0.025 |
ths | -0.024 |
www | -0.024 |
service | -0.024 |
Token | says |
Token ID | 1139 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
ister | +0.010 |
ww | +0.009 |
service | +0.009 |
www | +0.009 |
ths | +0.008 |
Neg logit contributions | |
like | -0.026 |
everywhere | -0.022 |
favorite | -0.022 |
wherever | -0.022 |
liked | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
like | +0.012 |
favorite | +0.007 |
liked | +0.007 |
everywhere | +0.006 |
pad | +0.006 |
Neg logit contributions | |
ister | -0.029 |
service | -0.028 |
ths | -0.027 |
ww | -0.027 |
avail | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
like | +0.013 |
everywhere | +0.008 |
favorite | +0.008 |
pad | +0.008 |
wherever | +0.007 |
Neg logit contributions | |
ister | -0.020 |
ww | -0.020 |
service | -0.020 |
ths | -0.020 |
www | -0.020 |
Token | We |
Token ID | 1135 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
like | +0.103 |
everywhere | +0.079 |
favorite | +0.076 |
liked | +0.072 |
around | +0.070 |
Neg logit contributions | |
ww | -0.106 |
ister | -0.105 |
ths | -0.105 |
www | -0.102 |
service | -0.101 |
Token | are |
Token ID | 389 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
like | +0.069 |
joy | +0.066 |
hers | +0.065 |
where | +0.064 |
skirts | +0.063 |
Neg logit contributions | |
storm | -0.102 |
ister | -0.099 |
www | -0.097 |
ww | -0.097 |
service | -0.092 |
Token | twins |
Token ID | 20345 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
like | +0.011 |
pad | +0.010 |
liked | +0.009 |
everywhere | +0.009 |
favorite | +0.009 |
Neg logit contributions | |
ister | -0.012 |
service | -0.012 |
storm | -0.012 |
ths | -0.012 |
ww | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
like | +0.050 |
favorite | +0.035 |
everywhere | +0.034 |
pad | +0.034 |
Whe | +0.033 |
Neg logit contributions | |
service | -0.100 |
ister | -0.098 |
ths | -0.094 |
ww | -0.094 |
keys | -0.092 |
Token | We |
Token ID | 775 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
like | +0.014 |
everywhere | +0.011 |
favorite | +0.010 |
liked | +0.010 |
around | +0.010 |
Neg logit contributions | |
ww | -0.011 |
ister | -0.011 |
www | -0.011 |
ths | -0.011 |
service | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
like | +0.073 |
favorite | +0.046 |
everywhere | +0.044 |
liked | +0.039 |
aces | +0.039 |
Neg logit contributions | |
ister | -0.153 |
ths | -0.150 |
ww | -0.147 |
service | -0.145 |
www | -0.145 |
Token | This |
Token ID | 1212 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
like | +0.090 |
everywhere | +0.066 |
favorite | +0.066 |
liked | +0.064 |
around | +0.060 |
Neg logit contributions | |
ww | -0.098 |
ister | -0.096 |
www | -0.095 |
ths | -0.095 |
service | -0.090 |
Token | is |
Token ID | 318 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
ww | +0.006 |
ister | +0.006 |
www | +0.006 |
ths | +0.006 |
service | +0.006 |
Neg logit contributions | |
like | -0.006 |
everywhere | -0.005 |
favorite | -0.005 |
liked | -0.005 |
wherever | -0.004 |
Token | ind |
Token ID | 773 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
ww | +0.028 |
ister | +0.027 |
ths | +0.027 |
www | +0.027 |
service | +0.026 |
Neg logit contributions | |
like | -0.016 |
liked | -0.011 |
everywhere | -0.011 |
favorite | -0.010 |
pad | -0.010 |
Token | igo |
Token ID | 14031 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
like | +0.096 |
everywhere | +0.075 |
liked | +0.074 |
favorite | +0.072 |
around | +0.069 |
Neg logit contributions | |
ister | -0.070 |
ths | -0.069 |
ww | -0.068 |
www | -0.065 |
avail | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
like | +0.073 |
everywhere | +0.048 |
favorite | +0.047 |
liked | +0.045 |
wherever | +0.040 |
Neg logit contributions | |
ww | -0.129 |
ister | -0.127 |
www | -0.123 |
ths | -0.121 |
service | -0.119 |
Token | and |
Token ID | 290 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
like | +0.136 |
liked | +0.093 |
everywhere | +0.093 |
favorite | +0.092 |
dolls | +0.086 |
Neg logit contributions | |
ister | -0.156 |
ths | -0.154 |
ww | -0.153 |
avail | -0.152 |
www | -0.150 |
Token | this |
Token ID | 428 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
like | +0.056 |
everywhere | +0.041 |
favorite | +0.041 |
liked | +0.041 |
around | +0.038 |
Neg logit contributions | |
ister | -0.053 |
ww | -0.052 |
ths | -0.051 |
www | -0.051 |
service | -0.049 |
Token | is |
Token ID | 318 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
ww | +0.014 |
ister | +0.014 |
ths | +0.014 |
www | +0.014 |
service | +0.013 |
Neg logit contributions | |
like | -0.012 |
everywhere | -0.009 |
favorite | -0.009 |
liked | -0.009 |
wherever | -0.008 |
Token | violet |
Token ID | 45725 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
ww | +0.020 |
ister | +0.020 |
ths | +0.020 |
www | +0.020 |
service | +0.019 |
Neg logit contributions | |
like | -0.013 |
everywhere | -0.009 |
liked | -0.008 |
favorite | -0.008 |
wherever | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
like | +0.009 |
everywhere | +0.005 |
liked | +0.005 |
favorite | +0.005 |
wherever | +0.004 |
Neg logit contributions | |
ister | -0.023 |
ww | -0.023 |
ths | -0.022 |
www | -0.022 |
service | -0.022 |