TOP ACTIVATIONS
MAX = 13.528

food . The st eg osaurus came out of
adventure !" The se ag ull s and the
the corn field . The st alks looked happy to see
" No !" and the se ag ull flew away .
dust and dirt . The st alks were hidden and the
as she could . The se ag ull flew away ,
them feel secure . The pers istant love of their parents
Suddenly , a se ag ull came and landed
too . The se ag ull tried to take
books first ?" Un cle Tom laughed and said
welcome here ." Un cle Jack gr umbled and
's silly !" Un cle smiled and said ,
't work either . The pr une just stayed the same
, why don 't you un pack your things and make
something extraordinary . On the sw ans back was a journal
Suddenly , a se ag ull flew down ,
hurt . The sw an is angry . It
better ?" The sw an looked at him and
He carefully pulled at the st alks of cel ery until
deep breath and shouted " ST OP !"

MIN ACTIVATIONS
MIN = -9.819

<|endoftext|> Anna and Ben are brother and sister . They like
<|endoftext|> Anna and Ben are sister and brother . They like
L ily and Ben are brother and sister . They like
L ily and Ben are brother and sister . They like
be scared of getting lost anymore . Max 's distant memory
<|endoftext|> Tom and Lily are brother and sister . They like
<|endoftext|> Tim and Sue are brother and sister . They like
L ily and Tom are brother and sister . They like
S ara and Ben are brother and sister . They are
S ara and Ben are brother and sister . They live
<|endoftext|> Tom and Lily are brother and sister . They like
<|endoftext|> Tom and Anna are brother and sister . They like
<|endoftext|> Tom and Lily are brother and sister . They like
S ara and Tom are brother and sister . They like
and Tom agreed and hugged mom . They all went to
<|endoftext|> Tom and Lily are brother and sister . They like
<|endoftext|> Tom and Lily were brother and sister . They lived
<|endoftext|> Tim and Mia are brother and sister . They live
<|endoftext|> Tom and Lily are brother and sister . They like
Lily and Max were normal brother and sister again . <|endoftext|>

INTERVAL 7.691 - 13.528
CONTAINS 0.256%

™ s like that . â € Jane was
a few shells and some seaw eed and built a castle
! Please help me ! â € The machine
she had to help the sw an , so she carefully
speaking friend said , " Spe ak slow and I will

INTERVAL 1.854 - 7.691
CONTAINS 16.308%

fast ." Sam came to the window too .
It looks like you are going to have a very special
loved to look at . One day , Lily 's little
went around and around the thick stone walls . Everyone was
found them . They woke up and saw the

INTERVAL -3.983 - 1.854
CONTAINS 80.880%

. She dreamed of being flexible , kind and helpful .
F ritz bark ed again and pointed at the
<|endoftext|> Once there was a horse who loved to listen .
the desk . But , the desk was not clean .
He hugged Lily and thanked her . He put on the

INTERVAL -9.819 - -3.983
CONTAINS 2.556%

the water . They are happy . <|endoftext|> S ara liked
and Sam were not happy anymore . <|endoftext|> Once upon a
The End . <|endoftext|> Once upon a time there
ipped right back to his family and his home in the
The end . <|endoftext|> Once upon a time there
Token food
Token ID2057
Feature activation-1.35e+00

Pos logit contributions
s+0.043
 sky+0.036
 nowhere+0.036
 twins+0.033
 living+0.033
Neg logit contributions
gh-0.054
 som-0.052
 insist-0.052
iding-0.051
 compete-0.051
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
s+0.028
 living+0.019
 twins+0.018
 sky+0.018
 nowhere+0.018
Neg logit contributions
heit-0.056
 som-0.053
gh-0.053
iding-0.052
 accompl-0.052
Token
Token ID198
Feature activation-5.13e-01

Pos logit contributions
gh+0.004
 som+0.004
 insist+0.004
 compete+0.004
iding+0.004
Neg logit contributions
s-0.002
 sky-0.001
 nowhere-0.001
ls-0.001
actus-0.001
Token
Token ID198
Feature activation+4.77e-01

Pos logit contributions
s+0.010
 sky+0.009
pill+0.009
 nowhere+0.009
ls+0.008
Neg logit contributions
gh-0.017
 som-0.016
 insist-0.016
iding-0.016
 compete-0.016
TokenThe
Token ID464
Feature activation+1.20e-01

Pos logit contributions
gh+0.013
 som+0.012
 insist+0.012
 compete+0.012
iding+0.012
Neg logit contributions
s-0.014
 sky-0.013
 nowhere-0.012
ls-0.012
pill-0.011
Token st
Token ID336
Feature activation+1.35e+01

Pos logit contributions
gh+0.004
 som+0.004
 insist+0.004
 compete+0.004
iding+0.004
Neg logit contributions
s-0.003
 sky-0.002
 nowhere-0.002
ls-0.002
 twins-0.002
Tokeneg
Token ID1533
Feature activation+6.17e+00

Pos logit contributions
gh+0.243
 som+0.201
iding+0.190
 compete+0.168
 skate+0.165
Neg logit contributions
s-0.510
 nowhere-0.504
 sky-0.474
 she-0.461
ls-0.457
Tokenosaurus
Token ID47650
Feature activation+2.64e+00

Pos logit contributions
gh+0.120
 skate+0.089
iding+0.083
 insist+0.081
 som+0.080
Neg logit contributions
 sky-0.221
s-0.215
 nowhere-0.210
ls-0.194
Someone-0.193
Token came
Token ID1625
Feature activation+1.54e+00

Pos logit contributions
gh+0.092
iding+0.091
 som+0.089
 insist+0.088
 accompl+0.088
Neg logit contributions
s-0.063
 sky-0.050
 nowhere-0.047
ls-0.043
 twins-0.041
Token out
Token ID503
Feature activation-5.48e-01

Pos logit contributions
gh+0.050
 som+0.048
 insist+0.048
 compete+0.048
iding+0.047
Neg logit contributions
s-0.039
 sky-0.032
 nowhere-0.031
ls-0.029
 living-0.027
Token of
Token ID286
Feature activation-2.03e+00

Pos logit contributions
s+0.008
 sky+0.006
 nowhere+0.005
ls+0.004
 living+0.004
Neg logit contributions
gh-0.024
 som-0.023
 insist-0.023
 compete-0.023
iding-0.023
Token adventure
Token ID8855
Feature activation+3.34e+00

Pos logit contributions
iding+0.026
gh+0.024
icious+0.024
 som+0.024
oving+0.023
Neg logit contributions
s-0.018
 sky-0.018
 nowhere-0.017
 living-0.016
 pieces-0.015
Token!"
Token ID2474
Feature activation-2.38e+00

Pos logit contributions
heit+0.117
gh+0.117
 som+0.116
 insist+0.115
 accompl+0.114
Neg logit contributions
s-0.079
 sky-0.065
 nowhere-0.063
 pieces-0.054
 living-0.053
Token
Token ID198
Feature activation-3.14e-01

Pos logit contributions
s+0.038
 sky+0.028
 nowhere+0.026
ls+0.022
 living+0.020
Neg logit contributions
gh-0.099
 insist-0.096
 som-0.096
 compete-0.095
iding-0.093
Token
Token ID198
Feature activation+4.79e-01

Pos logit contributions
s+0.005
 sky+0.004
 nowhere+0.004
ls+0.003
pill+0.003
Neg logit contributions
gh-0.013
 som-0.012
 insist-0.012
 compete-0.012
iding-0.012
TokenThe
Token ID464
Feature activation+4.21e-01

Pos logit contributions
gh+0.017
 som+0.016
 insist+0.016
heit+0.016
 accompl+0.016
Neg logit contributions
s-0.011
 nowhere-0.008
 sky-0.008
Someone-0.007
 living-0.007
Token se
Token ID384
Feature activation+1.35e+01

Pos logit contributions
gh+0.015
 insist+0.014
 som+0.014
 compete+0.014
iding+0.013
Neg logit contributions
s-0.010
 sky-0.007
 nowhere-0.007
ls-0.007
pill-0.006
Tokenag
Token ID363
Feature activation+7.72e+00

Pos logit contributions
 insist+0.303
 som+0.302
 compete+0.300
gh+0.296
 accompl+0.285
Neg logit contributions
s-0.451
 sky-0.368
 nowhere-0.359
ls-0.354
pill-0.342
Tokenull
Token ID724
Feature activation-2.61e-01

Pos logit contributions
gh+0.160
iding+0.144
 som+0.133
 compete+0.129
 insist+0.127
Neg logit contributions
s-0.274
pill-0.253
 sky-0.244
ls-0.242
 nowhere-0.228
Tokens
Token ID82
Feature activation+1.28e-01

Pos logit contributions
s+0.007
 sky+0.006
 nowhere+0.005
ls+0.005
 living+0.005
Neg logit contributions
gh-0.008
 som-0.008
 compete-0.008
 insist-0.008
 accompl-0.008
Token and
Token ID290
Feature activation-2.07e+00

Pos logit contributions
gh+0.004
 accompl+0.004
 insist+0.004
 compete+0.004
icious+0.004
Neg logit contributions
s-0.003
 sky-0.002
 nowhere-0.002
 pieces-0.002
ls-0.002
Token the
Token ID262
Feature activation-8.05e-01

Pos logit contributions
s+0.046
 sky+0.038
 nowhere+0.035
ls+0.032
 pieces+0.031
Neg logit contributions
gh-0.079
iding-0.074
 insist-0.071
 som-0.071
 compete-0.070
Token the
Token ID262
Feature activation-1.63e+00

Pos logit contributions
gh+0.097
iding+0.096
icious+0.093
heit+0.091
rated+0.091
Neg logit contributions
s-0.040
 living-0.039
 sky-0.033
 twins-0.033
 nowhere-0.033
Token corn
Token ID11676
Feature activation+3.42e+00

Pos logit contributions
s+0.039
 sky+0.034
 nowhere+0.032
 living+0.029
ls+0.028
Neg logit contributions
gh-0.056
iding-0.054
 som-0.053
 compete-0.053
 insist-0.053
Token field
Token ID2214
Feature activation+5.20e-01

Pos logit contributions
gh+0.115
 insist+0.110
 som+0.109
 compete+0.108
iding+0.106
Neg logit contributions
s-0.087
 sky-0.072
 nowhere-0.067
 living-0.062
ls-0.061
Token.
Token ID13
Feature activation+2.55e-01

Pos logit contributions
gh+0.019
heit+0.019
 insist+0.019
 som+0.019
 compete+0.018
Neg logit contributions
s-0.011
 sky-0.009
 nowhere-0.008
 living-0.008
 pieces-0.007
Token The
Token ID383
Feature activation-6.54e-01

Pos logit contributions
gh+0.009
 som+0.009
 insist+0.009
 compete+0.009
iding+0.008
Neg logit contributions
s-0.005
 nowhere-0.004
 sky-0.004
ls-0.004
 living-0.004
Token st
Token ID336
Feature activation+1.34e+01

Pos logit contributions
s+0.014
 sky+0.011
 nowhere+0.011
ls+0.009
 living+0.009
Neg logit contributions
gh-0.024
 insist-0.023
 som-0.023
 compete-0.023
iding-0.022
Tokenalks
Token ID23833
Feature activation+1.53e+00

Pos logit contributions
gh+0.271
iding+0.268
 som+0.254
 boost+0.246
heit+0.234
Neg logit contributions
 nowhere-0.449
s-0.430
 living-0.400
 sky-0.397
 twins-0.393
Token looked
Token ID3114
Feature activation+1.30e+00

Pos logit contributions
gh+0.046
 som+0.045
 insist+0.045
 compete+0.043
 boost+0.042
Neg logit contributions
s-0.038
 nowhere-0.032
 sky-0.032
pill-0.030
 twins-0.029
Token happy
Token ID3772
Feature activation-5.61e+00

Pos logit contributions
gh+0.041
 compete+0.039
 insist+0.039
 som+0.039
iding+0.038
Neg logit contributions
s-0.035
 sky-0.029
 nowhere-0.028
ls-0.026
 living-0.025
Token to
Token ID284
Feature activation+1.67e+00

Pos logit contributions
s+0.105
 sky+0.080
 nowhere+0.076
ls+0.063
 living+0.062
Neg logit contributions
gh-0.223
 insist-0.216
 som-0.214
 compete-0.213
iding-0.210
Token see
Token ID766
Feature activation-2.71e+00

Pos logit contributions
iding+0.060
heit+0.057
gh+0.057
oving+0.056
 som+0.055
Neg logit contributions
s-0.033
 sky-0.032
 nowhere-0.029
-0.027
 she-0.026
Token "
Token ID366
Feature activation+1.30e-01

Pos logit contributions
 insist+0.052
 compete+0.052
 som+0.051
heit+0.051
gh+0.050
Neg logit contributions
s-0.034
 sky-0.025
 nowhere-0.024
 living-0.023
ls-0.022
TokenNo
Token ID2949
Feature activation+3.16e+00

Pos logit contributions
gh+0.004
 som+0.004
iding+0.004
 insist+0.004
 compete+0.004
Neg logit contributions
s-0.003
 sky-0.003
 nowhere-0.003
Someone-0.002
 pieces-0.002
Token!"
Token ID2474
Feature activation-2.28e-01

Pos logit contributions
 accompl+0.111
Deal+0.105
iding+0.104
oving+0.099
orthy+0.098
Neg logit contributions
s-0.071
 sky-0.058
 pieces-0.052
 twins-0.051
 children-0.048
Token and
Token ID290
Feature activation+3.76e-01

Pos logit contributions
s+0.004
 sky+0.004
 nowhere+0.003
 twins+0.003
 living+0.003
Neg logit contributions
gh-0.009
 som-0.009
 insist-0.009
 compete-0.008
iding-0.008
Token the
Token ID262
Feature activation+1.22e+00

Pos logit contributions
gh+0.015
iding+0.014
icious+0.013
 compete+0.013
 insist+0.013
Neg logit contributions
s-0.008
 sky-0.006
 nowhere-0.006
 she-0.006
 living-0.005
Token se
Token ID384
Feature activation+1.34e+01

Pos logit contributions
gh+0.036
 insist+0.034
 som+0.034
 compete+0.034
iding+0.033
Neg logit contributions
s-0.035
 sky-0.030
 nowhere-0.029
ls-0.026
 twins-0.026
Tokenag
Token ID363
Feature activation+8.30e+00

Pos logit contributions
 insist+0.304
 som+0.302
 compete+0.298
gh+0.295
 accompl+0.283
Neg logit contributions
s-0.453
 sky-0.366
 nowhere-0.357
ls-0.351
pill-0.338
Tokenull
Token ID724
Feature activation-4.48e-01

Pos logit contributions
gh+0.202
 som+0.181
iding+0.180
 insist+0.170
 compete+0.169
Neg logit contributions
s-0.276
 sky-0.243
pill-0.239
ls-0.232
 nowhere-0.230
Token flew
Token ID13112
Feature activation+3.22e+00

Pos logit contributions
s+0.014
ls+0.010
 sky+0.010
 nowhere+0.009
 pieces+0.009
Neg logit contributions
gh-0.014
 accompl-0.013
 compete-0.013
 insist-0.013
iding-0.013
Token away
Token ID1497
Feature activation-3.65e-02

Pos logit contributions
gh+0.100
 insist+0.097
 compete+0.096
 som+0.095
 accompl+0.094
Neg logit contributions
s-0.094
 sky-0.078
 nowhere-0.074
 everywhere-0.069
ls-0.068
Token.
Token ID13
Feature activation+8.43e-01

Pos logit contributions
s+0.001
 sky+0.001
 nowhere+0.001
ls+0.000
 living+0.000
Neg logit contributions
gh-0.001
heit-0.001
 insist-0.001
 compete-0.001
 som-0.001
Token dust
Token ID8977
Feature activation+2.41e+00

Pos logit contributions
s+0.063
 sky+0.054
 nowhere+0.051
 pieces+0.044
 living+0.044
Neg logit contributions
gh-0.099
iding-0.095
 compete-0.094
 insist-0.094
 som-0.093
Token and
Token ID290
Feature activation-2.26e+00

Pos logit contributions
gh+0.094
 compete+0.093
 insist+0.093
 accompl+0.091
 som+0.091
Neg logit contributions
s-0.050
 sky-0.038
 nowhere-0.033
ls-0.031
 pieces-0.030
Token dirt
Token ID13647
Feature activation+1.73e+00

Pos logit contributions
s+0.055
 sky+0.044
 nowhere+0.043
ls+0.039
 twins+0.037
Neg logit contributions
gh-0.075
 som-0.073
 insist-0.073
 compete-0.072
iding-0.070
Token.
Token ID13
Feature activation+1.07e+00

Pos logit contributions
gh+0.063
 insist+0.063
 compete+0.062
 accompl+0.060
 som+0.060
Neg logit contributions
s-0.039
 sky-0.031
 nowhere-0.028
ls-0.027
 pieces-0.026
Token The
Token ID383
Feature activation-5.95e-01

Pos logit contributions
gh+0.048
 insist+0.046
iding+0.046
 som+0.046
 compete+0.045
Neg logit contributions
s-0.015
 sky-0.012
 nowhere-0.009
 living-0.007
 twins-0.007
Token st
Token ID336
Feature activation+1.32e+01

Pos logit contributions
s+0.015
 nowhere+0.012
 sky+0.012
ls+0.011
pill+0.011
Neg logit contributions
gh-0.019
 insist-0.019
 som-0.018
 compete-0.018
iding-0.017
Tokenalks
Token ID23833
Feature activation+1.49e+00

Pos logit contributions
 som+0.298
gh+0.293
iding+0.289
 boost+0.281
 insist+0.270
Neg logit contributions
 nowhere-0.404
s-0.391
 living-0.348
 twins-0.342
ls-0.337
Token were
Token ID547
Feature activation-1.40e+00

Pos logit contributions
gh+0.047
 insist+0.047
 som+0.046
 compete+0.045
iding+0.044
Neg logit contributions
s-0.036
 sky-0.030
 nowhere-0.029
pill-0.027
ls-0.027
Token hidden
Token ID7104
Feature activation+1.21e+00

Pos logit contributions
s+0.032
 sky+0.026
 nowhere+0.025
ls+0.023
 living+0.021
Neg logit contributions
gh-0.049
 som-0.047
 insist-0.047
 compete-0.046
iding-0.045
Token and
Token ID290
Feature activation-2.73e+00

Pos logit contributions
gh+0.044
 insist+0.042
 som+0.042
 compete+0.042
iding+0.041
Neg logit contributions
s-0.027
 sky-0.021
 nowhere-0.021
ls-0.019
 living-0.018
Token the
Token ID262
Feature activation-1.70e+00

Pos logit contributions
s+0.061
 sky+0.048
 nowhere+0.046
ls+0.042
pill+0.041
Neg logit contributions
gh-0.095
 som-0.094
 insist-0.093
 compete-0.091
iding-0.089
Token as
Token ID355
Feature activation-2.96e+00

Pos logit contributions
gh+0.150
icious+0.150
 insist+0.149
iding+0.145
heit+0.144
Neg logit contributions
s-0.071
 she-0.053
 sky-0.050
ls-0.042
 that-0.042
Token she
Token ID673
Feature activation+2.19e+00

Pos logit contributions
s+0.032
 sky+0.022
 she+0.021
 nowhere+0.019
ls+0.014
Neg logit contributions
gh-0.137
 insist-0.136
iding-0.135
heit-0.134
 som-0.131
Token could
Token ID714
Feature activation+3.30e+00

Pos logit contributions
iding+0.099
gh+0.096
 compete+0.096
 accompl+0.096
 insist+0.095
Neg logit contributions
s-0.037
 sky-0.023
 nowhere-0.021
ls-0.018
 was-0.013
Token.
Token ID13
Feature activation+1.20e+00

Pos logit contributions
heit+0.144
 accompl+0.137
icious+0.130
Deal+0.130
 som+0.126
Neg logit contributions
s-0.067
 sky-0.040
 of-0.038
-0.035
 she-0.034
Token The
Token ID383
Feature activation-2.37e-01

Pos logit contributions
gh+0.046
iding+0.044
 som+0.043
 insist+0.043
 compete+0.043
Neg logit contributions
s-0.026
 sky-0.022
 nowhere-0.018
 twins-0.016
-0.016
Token se
Token ID384
Feature activation+1.29e+01

Pos logit contributions
s+0.007
 sky+0.006
 nowhere+0.006
ls+0.005
 living+0.005
Neg logit contributions
gh-0.007
 som-0.007
 insist-0.007
 compete-0.006
iding-0.006
Tokenag
Token ID363
Feature activation+8.22e+00

Pos logit contributions
 insist+0.281
gh+0.280
 som+0.278
 compete+0.276
 accompl+0.260
Neg logit contributions
s-0.451
 sky-0.374
 nowhere-0.363
ls-0.357
pill-0.338
Tokenull
Token ID724
Feature activation-2.18e-01

Pos logit contributions
gh+0.190
iding+0.167
 som+0.166
 insist+0.158
 compete+0.154
Neg logit contributions
s-0.279
pill-0.251
 sky-0.247
ls-0.242
 nowhere-0.233
Token flew
Token ID13112
Feature activation+3.44e+00

Pos logit contributions
s+0.006
 sky+0.005
 nowhere+0.005
ls+0.005
 pieces+0.004
Neg logit contributions
gh-0.007
 compete-0.006
iding-0.006
 som-0.006
 insist-0.006
Token away
Token ID1497
Feature activation-4.55e-02

Pos logit contributions
gh+0.107
 insist+0.102
 compete+0.101
 som+0.100
 accompl+0.099
Neg logit contributions
s-0.101
 sky-0.085
 nowhere-0.079
ls-0.073
 everywhere-0.071
Token,
Token ID11
Feature activation-6.63e-01

Pos logit contributions
s+0.001
 sky+0.001
 nowhere+0.001
ls+0.000
 living+0.000
Neg logit contributions
gh-0.002
 insist-0.002
 compete-0.002
heit-0.002
 som-0.002
Token them
Token ID606
Feature activation-2.59e+00

Pos logit contributions
s+0.001
 sky+0.001
 pieces+0.001
 twins+0.001
 living+0.001
Neg logit contributions
gh-0.002
 insist-0.002
iding-0.002
 compete-0.002
 accompl-0.002
Token feel
Token ID1254
Feature activation-5.58e+00

Pos logit contributions
s+0.070
 sky+0.056
 twins+0.051
 pieces+0.051
 living+0.049
Neg logit contributions
gh-0.084
heit-0.079
 accompl-0.077
 insist-0.077
 som-0.076
Token secure
Token ID5713
Feature activation-3.03e-01

Pos logit contributions
s+0.144
 sky+0.124
 nowhere+0.112
 living+0.108
 twins+0.105
Neg logit contributions
gh-0.185
iding-0.177
 compete-0.172
heit-0.170
 insist-0.168
Token.
Token ID13
Feature activation+8.58e-02

Pos logit contributions
s+0.005
 sky+0.004
 nowhere+0.004
 living+0.003
 twins+0.003
Neg logit contributions
gh-0.013
 som-0.012
 compete-0.012
heit-0.012
 insist-0.012
Token The
Token ID383
Feature activation-4.70e-01

Pos logit contributions
gh+0.003
 som+0.003
 insist+0.003
 compete+0.003
iding+0.003
Neg logit contributions
s-0.002
 sky-0.001
 nowhere-0.001
ls-0.001
 twins-0.001
Token pers
Token ID2774
Feature activation+1.29e+01

Pos logit contributions
s+0.009
 sky+0.009
 nowhere+0.008
 twins+0.007
 living+0.007
Neg logit contributions
gh-0.018
iding-0.017
 insist-0.017
 som-0.017
 compete-0.017
Tokenistant
Token ID10167
Feature activation+3.03e+00

Pos logit contributions
gh+0.257
 som+0.256
 insist+0.250
 compete+0.238
 accompl+0.233
Neg logit contributions
s-0.475
 sky-0.407
 nowhere-0.379
ls-0.371
 pieces-0.360
Token love
Token ID1842
Feature activation-1.93e+00

Pos logit contributions
gh+0.108
iding+0.107
 accompl+0.106
 insist+0.105
 compete+0.103
Neg logit contributions
s-0.067
 sky-0.063
 pieces-0.054
 twins-0.048
 nowhere-0.048
Token of
Token ID286
Feature activation-6.06e-01

Pos logit contributions
s+0.035
 sky+0.026
 nowhere+0.023
 living+0.022
 twins+0.019
Neg logit contributions
gh-0.078
 insist-0.076
 compete-0.076
iding-0.076
heit-0.076
Token their
Token ID511
Feature activation+3.10e-01

Pos logit contributions
 nowhere+0.009
s+0.009
 living+0.009
 sky+0.008
 twins+0.008
Neg logit contributions
gh-0.023
iding-0.023
 boost-0.023
 insist-0.022
rated-0.022
Token parents
Token ID3397
Feature activation-4.52e+00

Pos logit contributions
gh+0.009
iding+0.009
 som+0.009
 insist+0.009
heit+0.009
Neg logit contributions
s-0.009
 sky-0.008
 nowhere-0.007
 living-0.007
 twins-0.007
Token
Token ID198
Feature activation-7.55e-01

Pos logit contributions
s+0.003
ls+0.002
 nowhere+0.002
actus+0.002
 sky+0.002
Neg logit contributions
 insist-0.004
gh-0.004
 compete-0.004
 som-0.004
 plead-0.004
Token
Token ID198
Feature activation+1.95e-01

Pos logit contributions
s+0.012
 sky+0.011
 nowhere+0.010
pill+0.010
 pieces+0.009
Neg logit contributions
gh-0.029
 insist-0.027
iding-0.027
 compete-0.027
 som-0.027
TokenSuddenly
Token ID38582
Feature activation-8.77e-02

Pos logit contributions
gh+0.005
 insist+0.005
 som+0.005
 compete+0.005
iding+0.005
Neg logit contributions
s-0.006
 sky-0.005
 nowhere-0.005
ls-0.004
 twins-0.004
Token,
Token ID11
Feature activation+1.69e+00

Pos logit contributions
s+0.003
 sky+0.002
 nowhere+0.002
pill+0.002
actus+0.002
Neg logit contributions
gh-0.002
 som-0.002
 insist-0.002
 compete-0.002
iding-0.002
Token a
Token ID257
Feature activation+1.40e+00

Pos logit contributions
 insist+0.049
gh+0.048
 som+0.048
 compete+0.047
 plead+0.047
Neg logit contributions
s-0.043
actus-0.037
pill-0.037
 sky-0.035
 nowhere-0.034
Token se
Token ID384
Feature activation+1.29e+01

Pos logit contributions
gh+0.053
iding+0.052
 insist+0.050
 som+0.050
 compete+0.049
Neg logit contributions
s-0.029
 sky-0.026
 nowhere-0.023
 twins-0.020
 living-0.020
Tokenag
Token ID363
Feature activation+7.96e+00

Pos logit contributions
 som+0.299
gh+0.292
 compete+0.289
 insist+0.287
 accompl+0.278
Neg logit contributions
s-0.429
 sky-0.354
 nowhere-0.345
ls-0.336
 living-0.318
Tokenull
Token ID724
Feature activation-3.19e-01

Pos logit contributions
gh+0.197
 som+0.181
 insist+0.177
iding+0.175
 compete+0.173
Neg logit contributions
s-0.261
pill-0.222
 sky-0.218
ls-0.216
 nowhere-0.213
Token came
Token ID1625
Feature activation+1.68e+00

Pos logit contributions
s+0.009
 sky+0.008
 nowhere+0.008
 twins+0.008
ls+0.007
Neg logit contributions
gh-0.008
 som-0.008
 insist-0.008
 compete-0.008
iding-0.007
Token and
Token ID290
Feature activation-2.62e+00

Pos logit contributions
gh+0.054
 insist+0.052
 som+0.052
 compete+0.052
iding+0.051
Neg logit contributions
s-0.041
 sky-0.034
 nowhere-0.034
ls-0.030
pill-0.029
Token landed
Token ID11406
Feature activation-2.20e-01

Pos logit contributions
s+0.081
 sky+0.073
 nowhere+0.069
 twins+0.066
ls+0.064
Neg logit contributions
 insist-0.063
gh-0.063
 som-0.063
 compete-0.061
heit-0.058
Token too
Token ID1165
Feature activation-1.86e+00

Pos logit contributions
s+0.048
 nowhere+0.034
 sky+0.032
ls+0.028
 living+0.027
Neg logit contributions
heit-0.095
 som-0.094
 insist-0.093
gh-0.092
 accompl-0.092
Token.
Token ID13
Feature activation-3.32e-01

Pos logit contributions
s+0.046
 sky+0.035
 nowhere+0.033
ls+0.032
 living+0.029
Neg logit contributions
gh-0.065
 som-0.063
 insist-0.062
 compete-0.062
iding-0.060
Token
Token ID198
Feature activation-9.56e-01

Pos logit contributions
 nowhere+0.008
 sky+0.007
s+0.007
 planets+0.007
armac+0.006
Neg logit contributions
 insist-0.009
 som-0.009
gh-0.009
 compete-0.009
 gob-0.009
Token
Token ID198
Feature activation+5.57e-03

Pos logit contributions
 sky+0.019
 nowhere+0.018
pill+0.017
s+0.017
 moons+0.016
Neg logit contributions
gh-0.032
 insist-0.030
 som-0.029
 compete-0.029
 agree-0.028
TokenThe
Token ID464
Feature activation+1.55e-01

Pos logit contributions
gh+0.000
 som+0.000
 insist+0.000
 compete+0.000
iding+0.000
Neg logit contributions
s-0.000
 sky-0.000
 nowhere-0.000
ls-0.000
 living-0.000
Token se
Token ID384
Feature activation+1.28e+01

Pos logit contributions
gh+0.004
 insist+0.004
 som+0.004
 compete+0.004
 wait+0.003
Neg logit contributions
s-0.005
 nowhere-0.004
 sky-0.004
pill-0.004
ls-0.004
Tokenag
Token ID363
Feature activation+8.29e+00

Pos logit contributions
gh+0.270
 som+0.263
 insist+0.261
 compete+0.255
iding+0.243
Neg logit contributions
s-0.465
 sky-0.400
 nowhere-0.389
ls-0.377
 twins-0.360
Tokenull
Token ID724
Feature activation-9.43e-02

Pos logit contributions
gh+0.169
 som+0.142
iding+0.137
 insist+0.131
 compete+0.127
Neg logit contributions
s-0.299
pill-0.282
 sky-0.265
ls-0.259
 curtains-0.257
Token tried
Token ID3088
Feature activation+3.03e-02

Pos logit contributions
s+0.003
 sky+0.002
 nowhere+0.002
pill+0.002
 living+0.002
Neg logit contributions
gh-0.003
 insist-0.003
 som-0.002
 compete-0.002
iding-0.002
Token to
Token ID284
Feature activation+2.34e+00

Pos logit contributions
gh+0.001
 som+0.001
 insist+0.001
 compete+0.001
 accompl+0.001
Neg logit contributions
s-0.001
 sky-0.001
pill-0.001
 nowhere-0.001
ls-0.001
Token take
Token ID1011
Feature activation+2.81e+00

Pos logit contributions
gh+0.067
iding+0.061
 accompl+0.059
 som+0.058
heit+0.054
Neg logit contributions
s-0.070
 blood-0.059
 nowhere-0.059
 sky-0.057
 lost-0.057
Token books
Token ID3835
Feature activation+2.74e-01

Pos logit contributions
s+0.034
 sky+0.028
 nowhere+0.027
 living+0.025
ls+0.025
Neg logit contributions
gh-0.044
iding-0.042
 som-0.041
 insist-0.041
 compete-0.040
Token first
Token ID717
Feature activation-2.09e-01

Pos logit contributions
gh+0.009
 som+0.009
heit+0.009
 compete+0.009
 insist+0.009
Neg logit contributions
s-0.007
 sky-0.006
 nowhere-0.005
 living-0.005
ls-0.005
Token?"
Token ID1701
Feature activation-1.20e+00

Pos logit contributions
s+0.004
 sky+0.003
 nowhere+0.003
 living+0.003
+0.003
Neg logit contributions
 accompl-0.008
 som-0.008
heit-0.008
gh-0.008
 compete-0.008
Token
Token ID198
Feature activation-3.82e-01

Pos logit contributions
s+0.022
 sky+0.017
 nowhere+0.017
ls+0.016
 pieces+0.014
Neg logit contributions
gh-0.045
 insist-0.045
 compete-0.044
 som-0.044
iding-0.042
Token
Token ID198
Feature activation+4.25e-01

Pos logit contributions
s+0.007
 sky+0.006
 nowhere+0.006
pill+0.005
ls+0.005
Neg logit contributions
gh-0.014
 som-0.014
 insist-0.013
 compete-0.013
iding-0.013
TokenUn
Token ID3118
Feature activation+1.28e+01

Pos logit contributions
gh+0.011
 som+0.011
 insist+0.011
 compete+0.011
iding+0.010
Neg logit contributions
s-0.013
 sky-0.011
 nowhere-0.011
ls-0.010
 living-0.010
Tokencle
Token ID2375
Feature activation-6.22e-01

Pos logit contributions
 som+0.348
gh+0.328
 insist+0.327
 compete+0.325
heit+0.308
Neg logit contributions
s-0.415
 sky-0.328
 nowhere-0.317
ls-0.294
eddy-0.293
Token Tom
Token ID4186
Feature activation+1.25e+00

Pos logit contributions
s+0.017
 sky+0.014
 nowhere+0.013
 twins+0.012
ls+0.012
Neg logit contributions
gh-0.020
 som-0.019
iding-0.019
 insist-0.019
 compete-0.019
Token laughed
Token ID13818
Feature activation-1.56e+00

Pos logit contributions
gh+0.048
 som+0.045
heit+0.045
iding+0.045
 accompl+0.044
Neg logit contributions
s-0.029
 sky-0.022
 nowhere-0.021
 living-0.018
 was-0.018
Token and
Token ID290
Feature activation-2.04e+00

Pos logit contributions
s+0.020
 sky+0.013
 nowhere+0.011
 twins+0.008
 living+0.007
Neg logit contributions
gh-0.075
 som-0.073
 compete-0.072
heit-0.072
 insist-0.072
Token said
Token ID531
Feature activation+4.99e-01

Pos logit contributions
s+0.035
 she+0.023
 sky+0.021
 nowhere+0.021
ls+0.018
Neg logit contributions
gh-0.096
iding-0.092
 compete-0.084
immer-0.083
 insist-0.082
Token welcome
Token ID7062
Feature activation-1.14e+00

Pos logit contributions
 twins+0.046
s+0.044
 living+0.042
 lost+0.042
 nowhere+0.040
Neg logit contributions
gh-0.086
 som-0.082
iding-0.081
heit-0.079
immer-0.077
Token here
Token ID994
Feature activation+2.52e+00

Pos logit contributions
s+0.022
 twins+0.017
 nowhere+0.016
 sky+0.016
 grandma+0.014
Neg logit contributions
 som-0.047
heit-0.043
iding-0.043
gh-0.043
 accompl-0.043
Token."
Token ID526
Feature activation-9.31e-01

Pos logit contributions
 som+0.096
heit+0.093
gh+0.093
 accompl+0.091
iding+0.090
Neg logit contributions
s-0.056
 sky-0.041
 nowhere-0.038
 living-0.038
 twins-0.037
Token
Token ID198
Feature activation-4.15e-01

Pos logit contributions
s+0.020
ls+0.018
pill+0.017
actus+0.017
 sky+0.016
Neg logit contributions
gh-0.028
 insist-0.028
 plead-0.027
 compete-0.027
 agree-0.027
Token
Token ID198
Feature activation+4.69e-01

Pos logit contributions
s+0.008
 sky+0.007
 nowhere+0.006
pill+0.006
ls+0.006
Neg logit contributions
gh-0.015
 insist-0.014
 som-0.014
 compete-0.014
 agree-0.014
TokenUn
Token ID3118
Feature activation+1.28e+01

Pos logit contributions
gh+0.012
 insist+0.011
 som+0.011
 compete+0.011
iding+0.011
Neg logit contributions
s-0.015
 sky-0.013
 nowhere-0.012
ls-0.012
pill-0.012
Tokencle
Token ID2375
Feature activation-3.57e-01

Pos logit contributions
 som+0.325
gh+0.310
 compete+0.307
 insist+0.306
iding+0.288
Neg logit contributions
s-0.425
 sky-0.350
 nowhere-0.347
 twins-0.316
ls-0.314
Token Jack
Token ID3619
Feature activation+1.76e+00

Pos logit contributions
s+0.010
 sky+0.008
 nowhere+0.008
ls+0.007
 living+0.007
Neg logit contributions
gh-0.011
 som-0.010
 insist-0.010
 compete-0.010
iding-0.010
Token gr
Token ID1036
Feature activation+5.55e+00

Pos logit contributions
gh+0.059
 som+0.058
 compete+0.057
iding+0.056
 insist+0.056
Neg logit contributions
s-0.043
 sky-0.035
 nowhere-0.034
ls-0.030
 twins-0.029
Tokenumbled
Token ID11137
Feature activation+9.02e-01

Pos logit contributions
gh+0.181
iding+0.172
 insist+0.165
oving+0.161
 compete+0.159
Neg logit contributions
s-0.136
 sky-0.121
 nowhere-0.114
ls-0.104
 living-0.103
Token and
Token ID290
Feature activation-1.96e+00

Pos logit contributions
heit+0.044
 som+0.044
icious+0.044
gh+0.043
 compete+0.043
Neg logit contributions
s-0.012
 sky-0.007
 and-0.005
 living-0.005
 nowhere-0.005
Token's
Token ID338
Feature activation+1.41e+00

Pos logit contributions
gh+0.116
 som+0.113
 insist+0.113
 compete+0.111
iding+0.110
Neg logit contributions
s-0.043
 sky-0.031
 nowhere-0.029
ls-0.024
 living-0.021
Token silly
Token ID14397
Feature activation+1.03e+00

Pos logit contributions
gh+0.055
iding+0.054
 paddle+0.053
 som+0.053
 compete+0.053
Neg logit contributions
 nowhere-0.020
s-0.019
 twins-0.017
 sky-0.017
 living-0.016
Token!"
Token ID2474
Feature activation-5.82e-01

Pos logit contributions
 accompl+0.037
gh+0.037
 som+0.036
 insist+0.035
heit+0.035
Neg logit contributions
s-0.026
 sky-0.019
 twins-0.018
 living-0.017
 she-0.016
Token
Token ID198
Feature activation+2.73e-01

Pos logit contributions
s+0.007
 sky+0.004
 nowhere+0.003
 twins+0.002
ls+0.002
Neg logit contributions
gh-0.028
 som-0.027
 insist-0.027
 compete-0.027
iding-0.026
Token
Token ID198
Feature activation+8.63e-01

Pos logit contributions
gh+0.012
 som+0.012
 insist+0.012
 compete+0.011
iding+0.011
Neg logit contributions
s-0.004
 sky-0.003
 nowhere-0.002
ls-0.002
pill-0.002
TokenUn
Token ID3118
Feature activation+1.28e+01

Pos logit contributions
 compete+0.027
gh+0.027
 som+0.027
 insist+0.027
 accompl+0.027
Neg logit contributions
s-0.024
 sky-0.018
 living-0.016
 nowhere-0.016
-0.015
Tokencle
Token ID2375
Feature activation-5.39e-01

Pos logit contributions
 som+0.337
 insist+0.324
gh+0.318
 compete+0.311
heit+0.305
Neg logit contributions
s-0.417
 sky-0.336
 nowhere-0.322
 living-0.297
eddy-0.293
Token smiled
Token ID13541
Feature activation-2.66e+00

Pos logit contributions
s+0.014
 sky+0.011
 nowhere+0.011
 twins+0.010
 living+0.009
Neg logit contributions
gh-0.018
 som-0.017
iding-0.017
heit-0.017
 insist-0.017
Token and
Token ID290
Feature activation-1.57e+00

Pos logit contributions
s+0.048
 sky+0.036
 nowhere+0.033
 twins+0.027
 living+0.025
Neg logit contributions
gh-0.112
 som-0.109
 compete-0.107
heit-0.107
 insist-0.106
Token said
Token ID531
Feature activation+7.04e-01

Pos logit contributions
s+0.032
 she+0.022
 sky+0.020
 nowhere+0.020
 was+0.018
Neg logit contributions
gh-0.068
iding-0.064
 compete-0.061
heit-0.060
 accompl-0.059
Token,
Token ID11
Feature activation+4.27e-01

Pos logit contributions
icious+0.028
 insist+0.027
iding+0.027
heit+0.027
 rely+0.027
Neg logit contributions
s-0.016
 she-0.010
ls-0.009
 of-0.008
 living-0.008
Token't
Token ID470
Feature activation-6.73e-01

Pos logit contributions
s+0.004
 sky+0.003
 nowhere+0.003
ls+0.003
 living+0.003
Neg logit contributions
gh-0.009
 som-0.008
 insist-0.008
 compete-0.008
iding-0.008
Token work
Token ID670
Feature activation+2.17e+00

Pos logit contributions
s+0.018
 sky+0.016
 she+0.014
 upon+0.014
 nowhere+0.014
Neg logit contributions
gh-0.021
heit-0.020
 accompl-0.019
iding-0.018
 som-0.018
Token either
Token ID2035
Feature activation-1.22e+00

Pos logit contributions
heit+0.079
 compete+0.079
 insist+0.079
 som+0.078
 boost+0.075
Neg logit contributions
s-0.047
 nowhere-0.036
 sky-0.034
 pieces-0.030
ls-0.030
Token.
Token ID13
Feature activation+5.74e-01

Pos logit contributions
s+0.028
 sky+0.021
 nowhere+0.017
 pieces+0.016
ls+0.016
Neg logit contributions
 som-0.045
gh-0.044
 accompl-0.044
heit-0.044
 insist-0.044
Token The
Token ID383
Feature activation-4.81e-01

Pos logit contributions
gh+0.020
 som+0.020
 compete+0.020
 insist+0.020
iding+0.019
Neg logit contributions
s-0.012
ls-0.009
 nowhere-0.009
 sky-0.009
actus-0.008
Token pr
Token ID778
Feature activation+1.28e+01

Pos logit contributions
s+0.014
 sky+0.013
 nowhere+0.012
 living+0.011
 twins+0.011
Neg logit contributions
gh-0.014
iding-0.013
 som-0.013
 compete-0.013
 insist-0.013
Tokenune
Token ID1726
Feature activation+3.25e+00

Pos logit contributions
gh+0.312
 som+0.296
 insist+0.296
 compete+0.290
iding+0.283
Neg logit contributions
s-0.423
 sky-0.368
 nowhere-0.358
ls-0.336
 living-0.325
Token just
Token ID655
Feature activation+3.26e+00

Pos logit contributions
gh+0.115
 insist+0.111
 som+0.111
 compete+0.109
iding+0.107
Neg logit contributions
s-0.071
 sky-0.057
 nowhere-0.055
ls-0.050
 twins-0.047
Token stayed
Token ID9658
Feature activation+9.71e-01

Pos logit contributions
gh+0.106
iding+0.100
 compete+0.098
 som+0.095
heit+0.094
Neg logit contributions
s-0.087
 nowhere-0.076
 sky-0.075
 living-0.064
 lost-0.062
Token the
Token ID262
Feature activation-2.10e+00

Pos logit contributions
gh+0.034
 compete+0.033
 som+0.033
 insist+0.032
iding+0.031
Neg logit contributions
s-0.022
 nowhere-0.019
 sky-0.019
 living-0.016
ls-0.016
Token same
Token ID976
Feature activation-3.94e-01

Pos logit contributions
 sky+0.047
 living+0.037
s+0.035
 nowhere+0.033
 twins+0.032
Neg logit contributions
iding-0.080
heit-0.077
gh-0.077
 compete-0.074
 som-0.074
Token,
Token ID11
Feature activation+1.89e+00

Pos logit contributions
 accompl+0.023
gh+0.023
oving+0.023
ern+0.021
iding+0.021
Neg logit contributions
s-0.013
 she-0.010
's-0.008
 sky-0.008
 is-0.008
Token why
Token ID1521
Feature activation-1.79e-01

Pos logit contributions
gh+0.051
oving+0.047
heit+0.045
iding+0.045
 accompl+0.043
Neg logit contributions
s-0.059
 sky-0.053
 living-0.053
 she-0.052
 twins-0.050
Token don
Token ID836
Feature activation+1.12e+00

Pos logit contributions
s+0.005
 sky+0.004
 twins+0.004
 living+0.004
 nowhere+0.004
Neg logit contributions
gh-0.005
 som-0.005
iding-0.005
 accompl-0.005
 compete-0.005
Token't
Token ID470
Feature activation+1.55e+00

Pos logit contributions
gh+0.036
 compete+0.035
 insist+0.034
 som+0.033
 wait+0.032
Neg logit contributions
s-0.024
 nowhere-0.022
 sky-0.022
actus-0.021
pill-0.020
Token you
Token ID345
Feature activation+4.65e+00

Pos logit contributions
gh+0.061
 som+0.059
 insist+0.058
iding+0.058
 compete+0.058
Neg logit contributions
s-0.029
 sky-0.022
 nowhere-0.021
ls-0.018
 twins-0.017
Token un
Token ID555
Feature activation+1.28e+01

Pos logit contributions
 accompl+0.150
gh+0.145
 som+0.138
heit+0.137
oving+0.129
Neg logit contributions
s-0.131
 sky-0.111
 lost-0.108
 upon-0.103
 of-0.102
Tokenpack
Token ID8002
Feature activation+3.62e+00

Pos logit contributions
gh+0.314
 som+0.302
 insist+0.297
 compete+0.290
iding+0.284
Neg logit contributions
s-0.426
 sky-0.367
 nowhere-0.357
ls-0.336
 twins-0.327
Token your
Token ID534
Feature activation+1.52e+00

Pos logit contributions
gh+0.121
 som+0.116
 insist+0.115
 compete+0.114
iding+0.111
Neg logit contributions
s-0.085
 sky-0.071
 nowhere-0.067
ls-0.062
pill-0.062
Token things
Token ID1243
Feature activation-1.79e+00

Pos logit contributions
gh+0.054
 insist+0.053
 som+0.052
 compete+0.052
iding+0.050
Neg logit contributions
s-0.033
 sky-0.025
 nowhere-0.024
ls-0.022
pill-0.022
Token and
Token ID290
Feature activation-3.99e-01

Pos logit contributions
s+0.047
 sky+0.038
 nowhere+0.037
 living+0.033
ls+0.033
Neg logit contributions
gh-0.059
 som-0.058
 compete-0.056
 insist-0.056
iding-0.055
Token make
Token ID787
Feature activation+1.97e-01

Pos logit contributions
s+0.013
 sky+0.011
 nowhere+0.011
 living+0.011
 twins+0.010
Neg logit contributions
gh-0.011
iding-0.010
 som-0.010
heit-0.009
 accompl-0.009
Token something
Token ID1223
Feature activation-2.09e+00

Pos logit contributions
s+0.033
 sky+0.025
 nowhere+0.024
ls+0.022
 twins+0.020
Neg logit contributions
gh-0.064
 som-0.062
 insist-0.062
 compete-0.061
iding-0.060
Token extraordinary
Token ID11359
Feature activation-4.26e-01

Pos logit contributions
s+0.051
 sky+0.040
 nowhere+0.039
ls+0.036
 living+0.035
Neg logit contributions
gh-0.071
 insist-0.069
 compete-0.068
iding-0.068
heit-0.067
Token.
Token ID13
Feature activation+2.20e-01

Pos logit contributions
s+0.011
 sky+0.008
 nowhere+0.008
ls+0.007
 living+0.007
Neg logit contributions
gh-0.014
 insist-0.014
 som-0.014
 compete-0.014
iding-0.014
Token On
Token ID1550
Feature activation+4.35e+00

Pos logit contributions
gh+0.008
 som+0.008
 insist+0.008
 compete+0.007
iding+0.007
Neg logit contributions
s-0.004
 nowhere-0.003
ls-0.003
 sky-0.003
 pieces-0.003
Token the
Token ID262
Feature activation+1.45e+00

Pos logit contributions
gh+0.168
 som+0.164
 insist+0.161
 compete+0.160
iding+0.156
Neg logit contributions
s-0.084
 sky-0.061
 nowhere-0.058
ls-0.054
 twins-0.050
Token sw
Token ID1509
Feature activation+1.27e+01

Pos logit contributions
gh+0.055
iding+0.053
 insist+0.052
 som+0.052
 compete+0.051
Neg logit contributions
s-0.031
 sky-0.027
 nowhere-0.022
 pieces-0.020
 living-0.020
Tokenans
Token ID504
Feature activation+2.44e+00

Pos logit contributions
gh+0.413
 insist+0.410
 compete+0.400
 accompl+0.396
 som+0.388
Neg logit contributions
s-0.318
 sky-0.266
ls-0.226
 nowhere-0.222
actus-0.218
Token back
Token ID736
Feature activation+1.29e+00

Pos logit contributions
gh+0.085
 som+0.080
 insist+0.080
 compete+0.079
iding+0.078
Neg logit contributions
s-0.059
 sky-0.047
 nowhere-0.045
ls-0.041
 living-0.039
Token was
Token ID373
Feature activation-5.09e-01

Pos logit contributions
gh+0.041
 som+0.041
 insist+0.041
 compete+0.041
iding+0.040
Neg logit contributions
s-0.029
 nowhere-0.025
 sky-0.023
pill-0.022
 twins-0.022
Token a
Token ID257
Feature activation-6.85e-01

Pos logit contributions
s+0.010
 nowhere+0.010
 sky+0.009
 living+0.008
 twins+0.007
Neg logit contributions
gh-0.018
 insist-0.018
 compete-0.018
heit-0.018
iding-0.018
Token journal
Token ID3989
Feature activation+5.28e-01

Pos logit contributions
s+0.015
 sky+0.014
 nowhere+0.012
 living+0.011
 pieces+0.010
Neg logit contributions
gh-0.024
iding-0.024
 compete-0.023
 accompl-0.023
 insist-0.023
Token
Token ID198
Feature activation-9.57e-01

Pos logit contributions
gh+0.022
 som+0.022
 insist+0.022
iding+0.021
 compete+0.021
Neg logit contributions
s-0.008
 sky-0.006
 nowhere-0.005
 twins-0.004
-0.004
Token
Token ID198
Feature activation-3.71e-02

Pos logit contributions
s+0.014
 sky+0.010
 nowhere+0.009
ls+0.008
pill+0.007
Neg logit contributions
gh-0.041
 som-0.040
 insist-0.040
 compete-0.039
iding-0.039
TokenSuddenly
Token ID38582
Feature activation-3.46e-01

Pos logit contributions
s+0.001
 sky+0.001
 nowhere+0.001
Someone+0.001
+0.001
Neg logit contributions
 insist-0.001
gh-0.001
 appetite-0.001
heit-0.001
 som-0.001
Token,
Token ID11
Feature activation+1.56e+00

Pos logit contributions
s+0.008
 sky+0.007
 nowhere+0.006
ls+0.006
 twins+0.005
Neg logit contributions
 insist-0.012
gh-0.012
iding-0.012
 som-0.011
 compete-0.011
Token a
Token ID257
Feature activation+1.58e+00

Pos logit contributions
gh+0.058
iding+0.056
 insist+0.056
 som+0.056
 compete+0.055
Neg logit contributions
s-0.032
 sky-0.026
 nowhere-0.025
ls-0.022
 twins-0.021
Token se
Token ID384
Feature activation+1.27e+01

Pos logit contributions
iding+0.059
gh+0.059
 insist+0.056
 compete+0.056
 accompl+0.055
Neg logit contributions
s-0.032
 sky-0.030
 nowhere-0.025
 twins-0.023
 living-0.022
Tokenag
Token ID363
Feature activation+7.55e+00

Pos logit contributions
 som+0.266
 insist+0.262
 compete+0.262
 accompl+0.256
gh+0.255
Neg logit contributions
s-0.443
 sky-0.362
 nowhere-0.355
ls-0.347
pill-0.330
Tokenull
Token ID724
Feature activation-4.58e-01

Pos logit contributions
gh+0.186
 som+0.170
iding+0.166
 insist+0.165
 compete+0.163
Neg logit contributions
s-0.251
pill-0.213
 sky-0.212
ls-0.208
 nowhere-0.202
Token flew
Token ID13112
Feature activation+2.71e+00

Pos logit contributions
s+0.014
 sky+0.012
 nowhere+0.012
ls+0.011
 twins+0.010
Neg logit contributions
gh-0.012
 som-0.012
 insist-0.012
 compete-0.011
iding-0.011
Token down
Token ID866
Feature activation+3.87e-02

Pos logit contributions
gh+0.079
 som+0.076
 insist+0.075
 compete+0.074
iding+0.073
Neg logit contributions
s-0.077
 sky-0.065
 nowhere-0.063
ls-0.059
 twins-0.057
Token,
Token ID11
Feature activation-8.25e-01

Pos logit contributions
gh+0.001
 som+0.001
 insist+0.001
 compete+0.001
iding+0.001
Neg logit contributions
s-0.001
 sky-0.001
 nowhere-0.001
ls-0.001
pill-0.001
Token hurt
Token ID5938
Feature activation-4.33e-01

Pos logit contributions
s+0.053
 sky+0.044
 nowhere+0.042
ls+0.039
 living+0.037
Neg logit contributions
gh-0.066
 som-0.063
 insist-0.063
 compete-0.062
iding-0.061
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
s+0.012
 sky+0.010
 nowhere+0.009
ls+0.009
pill+0.009
Neg logit contributions
gh-0.013
 insist-0.013
 som-0.013
 compete-0.012
iding-0.012
Token
Token ID198
Feature activation-8.59e-01

Pos logit contributions
s+0.004
actus+0.004
 nowhere+0.004
ls+0.004
pill+0.004
Neg logit contributions
gh-0.005
 insist-0.005
 compete-0.005
 som-0.005
 plead-0.004
Token
Token ID198
Feature activation+2.05e-01

Pos logit contributions
s+0.017
pill+0.017
 sky+0.016
actus+0.015
 nowhere+0.015
Neg logit contributions
gh-0.027
 insist-0.026
 compete-0.025
 som-0.025
 agree-0.025
TokenThe
Token ID464
Feature activation+7.96e-01

Pos logit contributions
gh+0.006
 insist+0.006
 som+0.005
 compete+0.005
iding+0.005
Neg logit contributions
s-0.006
 sky-0.005
 nowhere-0.005
pill-0.005
ls-0.004
Token sw
Token ID1509
Feature activation+1.26e+01

Pos logit contributions
gh+0.015
 som+0.014
 insist+0.014
 compete+0.014
iding+0.013
Neg logit contributions
s-0.031
 sky-0.027
 nowhere-0.027
ls-0.025
pill-0.025
Tokenan
Token ID272
Feature activation-1.12e-01

Pos logit contributions
gh+0.402
 insist+0.390
 som+0.387
 compete+0.385
iding+0.373
Neg logit contributions
s-0.330
 sky-0.272
 nowhere-0.252
ls-0.244
 twins-0.229
Token is
Token ID318
Feature activation-8.61e-01

Pos logit contributions
s+0.002
 sky+0.002
 nowhere+0.002
eddy+0.002
pill+0.002
Neg logit contributions
 insist-0.004
gh-0.004
 som-0.004
 compete-0.004
heit-0.003
Token angry
Token ID7954
Feature activation-1.38e+00

Pos logit contributions
s+0.021
 sky+0.017
 nowhere+0.016
ls+0.015
pill+0.014
Neg logit contributions
gh-0.029
 insist-0.028
 som-0.028
 compete-0.027
iding-0.027
Token.
Token ID13
Feature activation+1.03e+00

Pos logit contributions
s+0.035
 sky+0.032
pill+0.032
actus+0.032
armac+0.032
Neg logit contributions
iding-0.035
gh-0.035
 som-0.034
 insist-0.034
 compete-0.034
Token It
Token ID632
Feature activation-1.61e+00

Pos logit contributions
gh+0.037
 som+0.036
 insist+0.036
 compete+0.036
iding+0.035
Neg logit contributions
s-0.022
 sky-0.017
 nowhere-0.016
ls-0.015
 living-0.014
Token better
Token ID1365
Feature activation-2.17e+00

Pos logit contributions
s+0.123
 sky+0.105
 nowhere+0.102
ls+0.094
 living+0.092
Neg logit contributions
gh-0.126
 som-0.119
 insist-0.119
 compete-0.118
iding-0.117
Token?"
Token ID1701
Feature activation-1.97e+00

Pos logit contributions
s+0.040
 nowhere+0.030
 sky+0.029
eddy+0.024
+0.024
Neg logit contributions
 som-0.091
gh-0.087
heit-0.087
 accompl-0.086
 seventeen-0.085
Token
Token ID198
Feature activation-8.40e-01

Pos logit contributions
s+0.029
 sky+0.020
 nowhere+0.018
ls+0.014
 living+0.013
Neg logit contributions
gh-0.087
 insist-0.084
 som-0.084
iding-0.083
 compete-0.082
Token
Token ID198
Feature activation+1.54e-02

Pos logit contributions
s+0.009
 sky+0.005
 nowhere+0.004
ls+0.002
 living+0.002
Neg logit contributions
gh-0.040
 insist-0.039
 som-0.039
 compete-0.039
iding-0.039
TokenThe
Token ID464
Feature activation+3.44e-01

Pos logit contributions
gh+0.001
 appetite+0.001
 som+0.001
 insist+0.001
heit+0.001
Neg logit contributions
s-0.000
 sky-0.000
 nowhere-0.000
Someone-0.000
Our-0.000
Token sw
Token ID1509
Feature activation+1.26e+01

Pos logit contributions
gh+0.010
 som+0.010
 insist+0.010
iding+0.010
 compete+0.010
Neg logit contributions
s-0.010
 sky-0.009
 nowhere-0.008
 twins-0.008
ls-0.007
Tokenan
Token ID272
Feature activation+3.96e-01

Pos logit contributions
gh+0.446
 insist+0.438
 compete+0.432
 som+0.428
 accompl+0.427
Neg logit contributions
s-0.285
 sky-0.225
ls-0.199
actus-0.197
 nowhere-0.191
Token looked
Token ID3114
Feature activation+1.66e+00

Pos logit contributions
gh+0.014
 som+0.013
 compete+0.013
iding+0.013
 accompl+0.013
Neg logit contributions
s-0.010
 sky-0.008
 nowhere-0.008
ls-0.007
 living-0.007
Token at
Token ID379
Feature activation+3.52e-02

Pos logit contributions
gh+0.053
 som+0.051
 insist+0.050
 compete+0.050
iding+0.049
Neg logit contributions
s-0.044
 sky-0.036
 nowhere-0.035
ls-0.032
 living-0.031
Token him
Token ID683
Feature activation-9.85e-01

Pos logit contributions
 som+0.001
gh+0.001
 insist+0.001
 compete+0.001
heit+0.001
Neg logit contributions
s-0.001
 sky-0.001
pill-0.001
 nowhere-0.001
 living-0.001
Token and
Token ID290
Feature activation-1.81e+00

Pos logit contributions
s+0.015
 sky+0.009
 nowhere+0.009
 living+0.006
ls+0.006
Neg logit contributions
gh-0.044
 som-0.042
 compete-0.042
 insist-0.042
heit-0.042
Token He
Token ID679
Feature activation+1.86e+00

Pos logit contributions
gh+0.035
 som+0.034
 insist+0.033
 compete+0.033
iding+0.032
Neg logit contributions
s-0.022
 sky-0.018
 nowhere-0.017
 living-0.014
 twins-0.014
Token carefully
Token ID7773
Feature activation+3.39e+00

Pos logit contributions
iding+0.069
gh+0.068
 compete+0.064
icious+0.063
 accompl+0.063
Neg logit contributions
s-0.044
 nowhere-0.032
 sky-0.032
 was-0.030
 pieces-0.029
Token pulled
Token ID5954
Feature activation+3.68e+00

Pos logit contributions
gh+0.111
iding+0.108
icious+0.106
heit+0.105
Deal+0.104
Neg logit contributions
s-0.093
 pieces-0.075
 sky-0.072
 nowhere-0.069
 living-0.065
Token at
Token ID379
Feature activation+2.10e+00

Pos logit contributions
gh+0.144
 insist+0.141
 compete+0.140
 som+0.140
iding+0.138
Neg logit contributions
s-0.072
 sky-0.056
 nowhere-0.052
 pieces-0.049
ls-0.045
Token the
Token ID262
Feature activation-4.98e-01

Pos logit contributions
gh+0.071
 insist+0.069
 som+0.069
 compete+0.068
 accompl+0.065
Neg logit contributions
s-0.050
 sky-0.039
ls-0.036
 nowhere-0.035
pill-0.035
Token st
Token ID336
Feature activation+1.26e+01

Pos logit contributions
s+0.011
 sky+0.011
 living+0.009
 nowhere+0.009
 pieces+0.009
Neg logit contributions
gh-0.017
iding-0.017
 insist-0.016
 som-0.016
 compete-0.016
Tokenalks
Token ID23833
Feature activation-3.38e-01

Pos logit contributions
gh+0.341
 som+0.332
 insist+0.319
iding+0.318
 compete+0.315
Neg logit contributions
s-0.372
 nowhere-0.328
 sky-0.321
ls-0.300
 twins-0.290
Token of
Token ID286
Feature activation-5.66e-02

Pos logit contributions
s+0.007
 sky+0.005
 nowhere+0.005
 pieces+0.004
ls+0.004
Neg logit contributions
gh-0.013
 insist-0.013
 som-0.013
 compete-0.013
heit-0.013
Token cel
Token ID18725
Feature activation+6.80e+00

Pos logit contributions
 nowhere+0.001
s+0.001
 sky+0.001
 pieces+0.001
 living+0.000
Neg logit contributions
gh-0.002
iding-0.002
 insist-0.002
 som-0.002
 compete-0.002
Tokenery
Token ID1924
Feature activation+2.31e+00

Pos logit contributions
 insist+0.188
 compete+0.181
gh+0.179
 som+0.176
 accompl+0.172
Neg logit contributions
s-0.215
 sky-0.179
ls-0.168
 nowhere-0.165
pill-0.160
Token until
Token ID1566
Feature activation-8.17e-01

Pos logit contributions
gh+0.092
 insist+0.090
heit+0.090
 compete+0.088
 accompl+0.087
Neg logit contributions
s-0.050
 sky-0.037
 pieces-0.033
 living-0.028
 nowhere-0.028
Token deep
Token ID2769
Feature activation+5.61e+00

Pos logit contributions
s+0.003
 sky+0.003
 nowhere+0.002
ls+0.002
 twins+0.002
Neg logit contributions
gh-0.003
 som-0.003
 insist-0.003
 compete-0.003
iding-0.003
Token breath
Token ID8033
Feature activation+3.29e-01

Pos logit contributions
gh+0.150
 compete+0.143
 som+0.140
iding+0.139
 accompl+0.138
Neg logit contributions
s-0.174
 sky-0.156
 nowhere-0.151
ls-0.144
 pieces-0.141
Token and
Token ID290
Feature activation-2.58e+00

Pos logit contributions
gh+0.015
 compete+0.014
 som+0.014
 insist+0.014
heit+0.014
Neg logit contributions
s-0.005
 sky-0.003
 nowhere-0.003
ls-0.002
 living-0.002
Token shouted
Token ID17293
Feature activation+1.06e+00

Pos logit contributions
s+0.074
 sky+0.062
 nowhere+0.060
ls+0.056
 living+0.054
Neg logit contributions
gh-0.078
iding-0.073
 compete-0.073
 insist-0.073
 som-0.071
Token "
Token ID366
Feature activation-3.24e-01

Pos logit contributions
 insist+0.042
heit+0.042
 compete+0.041
Deal+0.041
icious+0.040
Neg logit contributions
s-0.021
 she-0.013
 sky-0.013
 living-0.013
ls-0.012
TokenST
Token ID2257
Feature activation+1.26e+01

Pos logit contributions
s+0.009
 sky+0.008
 nowhere+0.007
Someone+0.006
+0.006
Neg logit contributions
gh-0.010
 som-0.010
 accompl-0.010
 insist-0.010
 compete-0.010
TokenOP
Token ID3185
Feature activation+7.38e+00

Pos logit contributions
 insist+0.286
 som+0.282
 accompl+0.278
 convince+0.267
 seek+0.258
Neg logit contributions
s-0.384
 sky-0.336
ane-0.323
pill-0.321
-0.311
Token!"
Token ID2474
Feature activation-1.04e+00

Pos logit contributions
Deal+0.263
 accompl+0.255
 compete+0.254
 spend+0.245
 insist+0.245
Neg logit contributions
s-0.186
-0.136
 sky-0.133
 pieces-0.114
ls-0.112
Token
Token ID220
Feature activation-2.90e-01

Pos logit contributions
s+0.017
 sky+0.013
 nowhere+0.011
 twins+0.009
 living+0.009
Neg logit contributions
gh-0.044
 insist-0.043
 som-0.042
 compete-0.042
iding-0.042
Token
Token ID198
Feature activation-2.36e-01

Pos logit contributions
s+0.004
 sky+0.003
 nowhere+0.003
ls+0.002
 living+0.002
Neg logit contributions
gh-0.012
 insist-0.012
 som-0.012
iding-0.012
 compete-0.012
Token
Token ID198
Feature activation+4.36e-01

Pos logit contributions
s+0.003
 sky+0.002
 nowhere+0.002
ls+0.002
 living+0.002
Neg logit contributions
gh-0.010
 som-0.010
 insist-0.010
 compete-0.010
iding-0.010
Token<|endoftext|>
Token ID50256
Feature activation-5.89e+00

Pos logit contributions
 insist+0.000
 compete+0.000
 agree+0.000
 som+0.000
gh+0.000
Neg logit contributions
s-0.000
ls-0.000
ons-0.000
 nowhere-0.000
 pieces-0.000
TokenAnna
Token ID31160
Feature activation-1.14e+00

Pos logit contributions
s+0.082
 nowhere+0.059
 sky+0.052
ls+0.050
armac+0.048
Neg logit contributions
gh-0.241
 compete-0.229
 insist-0.223
 som-0.223
iding-0.217
Token and
Token ID290
Feature activation-1.31e+00

Pos logit contributions
s+0.023
 sky+0.019
 nowhere+0.018
ls+0.017
pill+0.016
Neg logit contributions
gh-0.040
 insist-0.040
 compete-0.038
 som-0.038
 wait-0.036
Token Ben
Token ID3932
Feature activation+4.10e-01

Pos logit contributions
s+0.037
 sky+0.031
 nowhere+0.030
ls+0.029
pill+0.028
Neg logit contributions
 insist-0.038
gh-0.038
 compete-0.037
 som-0.036
 wait-0.035
Token are
Token ID389
Feature activation-2.42e+00

Pos logit contributions
gh+0.013
 insist+0.013
 som+0.013
 compete+0.012
iding+0.012
Neg logit contributions
s-0.010
 sky-0.009
 nowhere-0.008
ls-0.008
pill-0.007
Token brother
Token ID3956
Feature activation-9.82e+00

Pos logit contributions
s+0.064
 sky+0.053
 nowhere+0.050
ls+0.048
pill+0.046
Neg logit contributions
gh-0.076
 insist-0.073
 som-0.072
 compete-0.071
iding-0.070
Token and
Token ID290
Feature activation-3.00e+00

Pos logit contributions
s+0.219
 sky+0.180
 nowhere+0.172
ls+0.156
pill+0.146
Neg logit contributions
gh-0.338
 som-0.327
 insist-0.326
 compete-0.321
iding-0.317
Token sister
Token ID6621
Feature activation-8.10e+00

Pos logit contributions
s+0.066
 twins+0.051
 sky+0.050
 she+0.049
 living+0.048
Neg logit contributions
gh-0.109
iding-0.108
 som-0.105
heit-0.104
 accompl-0.102
Token.
Token ID13
Feature activation-3.65e-01

Pos logit contributions
s+0.208
 sky+0.175
 nowhere+0.168
ls+0.155
pill+0.146
Neg logit contributions
gh-0.255
 insist-0.246
 som-0.245
 compete-0.241
iding-0.236
Token They
Token ID1119
Feature activation+2.98e-01

Pos logit contributions
s+0.008
 sky+0.006
 nowhere+0.006
ls+0.005
 twins+0.005
Neg logit contributions
gh-0.013
 som-0.013
 insist-0.013
 compete-0.012
iding-0.012
Token like
Token ID588
Feature activation-2.55e+00

Pos logit contributions
gh+0.010
 som+0.009
iding+0.009
 accompl+0.009
heit+0.009
Neg logit contributions
s-0.008
 sky-0.007
 living-0.006
 twins-0.006
 nowhere-0.006
Token<|endoftext|>
Token ID50256
Feature activation-6.09e+00

Pos logit contributions
s+0.013
 nowhere+0.010
ls+0.010
 sky+0.009
pill+0.009
Neg logit contributions
gh-0.025
 compete-0.025
 insist-0.025
 som-0.024
iding-0.023
TokenAnna
Token ID31160
Feature activation-1.22e+00

Pos logit contributions
s+0.088
 nowhere+0.070
 sky+0.056
armac+0.055
ls+0.054
Neg logit contributions
gh-0.240
 compete-0.234
 som-0.224
 insist-0.223
iding-0.217
Token and
Token ID290
Feature activation-1.35e+00

Pos logit contributions
s+0.024
 nowhere+0.019
 sky+0.019
ls+0.017
Someone+0.015
Neg logit contributions
 insist-0.045
gh-0.044
 compete-0.043
 som-0.043
 wait-0.041
Token Ben
Token ID3932
Feature activation+5.26e-01

Pos logit contributions
s+0.035
 sky+0.029
 nowhere+0.028
ls+0.026
pill+0.025
Neg logit contributions
gh-0.042
 insist-0.041
 som-0.041
 compete-0.041
iding-0.039
Token are
Token ID389
Feature activation-2.30e+00

Pos logit contributions
gh+0.017
 som+0.016
 insist+0.016
 compete+0.016
iding+0.016
Neg logit contributions
s-0.014
 sky-0.011
 nowhere-0.011
ls-0.010
 living-0.010
Token sister
Token ID6621
Feature activation-9.77e+00

Pos logit contributions
s+0.061
 sky+0.051
 nowhere+0.049
ls+0.046
pill+0.045
Neg logit contributions
gh-0.070
 insist-0.069
 som-0.067
 compete-0.066
iding-0.065
Token and
Token ID290
Feature activation-2.93e+00

Pos logit contributions
s+0.231
 sky+0.194
 nowhere+0.188
ls+0.169
pill+0.162
Neg logit contributions
gh-0.318
 som-0.308
 insist-0.307
 compete-0.302
iding-0.299
Token brother
Token ID3956
Feature activation-7.51e+00

Pos logit contributions
s+0.066
 sky+0.052
 twins+0.050
 she+0.048
 living+0.048
Neg logit contributions
gh-0.105
iding-0.104
 som-0.101
heit-0.099
 accompl-0.098
Token.
Token ID13
Feature activation-2.40e-01

Pos logit contributions
s+0.195
 sky+0.165
 nowhere+0.160
ls+0.146
pill+0.138
Neg logit contributions
gh-0.233
 insist-0.226
 som-0.225
 compete-0.222
iding-0.216
Token They
Token ID1119
Feature activation+4.00e-01

Pos logit contributions
s+0.005
 sky+0.004
 nowhere+0.004
ls+0.003
 twins+0.003
Neg logit contributions
gh-0.009
 som-0.009
 insist-0.008
 compete-0.008
iding-0.008
Token like
Token ID588
Feature activation-2.59e+00

Pos logit contributions
gh+0.013
iding+0.012
 som+0.012
 accompl+0.012
heit+0.012
Neg logit contributions
s-0.010
 sky-0.009
 living-0.008
 twins-0.008
 nowhere-0.007
TokenL
Token ID43
Feature activation+1.18e+00

Pos logit contributions
s+0.089
 nowhere+0.068
armac+0.057
ls+0.056
 sky+0.054
Neg logit contributions
gh-0.243
 compete-0.231
 som-0.224
 insist-0.223
iding-0.219
Tokenily
Token ID813
Feature activation-1.83e+00

Pos logit contributions
gh+0.031
ern+0.027
 insist+0.026
iding+0.025
 wait+0.024
Neg logit contributions
s-0.034
 sky-0.033
 nowhere-0.031
pill-0.030
Someone-0.030
Token and
Token ID290
Feature activation-1.29e+00

Pos logit contributions
s+0.035
 sky+0.027
 nowhere+0.026
ls+0.023
 living+0.021
Neg logit contributions
gh-0.070
 som-0.068
 insist-0.068
 compete-0.067
iding-0.066
Token Ben
Token ID3932
Feature activation+5.96e-01

Pos logit contributions
s+0.036
 sky+0.030
 nowhere+0.029
ls+0.028
pill+0.027
Neg logit contributions
 insist-0.038
gh-0.038
 compete-0.037
 som-0.036
 wait-0.035
Token are
Token ID389
Feature activation-2.12e+00

Pos logit contributions
gh+0.021
 som+0.020
iding+0.020
 insist+0.019
 compete+0.019
Neg logit contributions
s-0.014
 sky-0.011
 nowhere-0.011
 living-0.010
ls-0.009
Token brother
Token ID3956
Feature activation-9.40e+00

Pos logit contributions
s+0.059
 sky+0.050
 nowhere+0.047
ls+0.045
pill+0.045
Neg logit contributions
gh-0.062
 insist-0.061
 som-0.058
 compete-0.058
iding-0.057
Token and
Token ID290
Feature activation-2.63e+00

Pos logit contributions
s+0.185
 sky+0.146
 nowhere+0.138
ls+0.122
 living+0.113
Neg logit contributions
gh-0.353
 som-0.342
 insist-0.342
 compete-0.337
iding-0.332
Token sister
Token ID6621
Feature activation-7.59e+00

Pos logit contributions
s+0.060
 twins+0.046
 sky+0.045
 living+0.043
 she+0.043
Neg logit contributions
gh-0.094
iding-0.093
 som-0.091
heit-0.088
 accompl-0.087
Token.
Token ID13
Feature activation-2.35e-01

Pos logit contributions
s+0.192
 sky+0.159
 nowhere+0.153
ls+0.140
 living+0.134
Neg logit contributions
gh-0.246
 som-0.236
 insist-0.236
 compete-0.233
iding-0.228
Token They
Token ID1119
Feature activation+4.30e-01

Pos logit contributions
s+0.005
 sky+0.004
 nowhere+0.003
 twins+0.003
 living+0.003
Neg logit contributions
gh-0.009
 som-0.009
heit-0.009
iding-0.009
 insist-0.009
Token like
Token ID588
Feature activation-2.46e+00

Pos logit contributions
gh+0.014
 som+0.013
iding+0.013
 accompl+0.013
heit+0.012
Neg logit contributions
s-0.012
 sky-0.010
 living-0.009
 twins-0.009
 nowhere-0.008
TokenL
Token ID43
Feature activation+1.33e+00

Pos logit contributions
s+0.091
 nowhere+0.071
armac+0.064
ls+0.062
 sky+0.058
Neg logit contributions
gh-0.225
 compete-0.216
 som-0.207
 insist-0.205
iding-0.198
Tokenily
Token ID813
Feature activation-1.61e+00

Pos logit contributions
gh+0.033
 insist+0.028
iding+0.028
ern+0.027
 som+0.027
Neg logit contributions
s-0.041
 nowhere-0.038
 sky-0.038
pill-0.036
Someone-0.034
Token and
Token ID290
Feature activation-1.18e+00

Pos logit contributions
s+0.031
 sky+0.024
 nowhere+0.022
ls+0.020
 twins+0.018
Neg logit contributions
gh-0.062
 insist-0.060
 som-0.060
 compete-0.059
iding-0.058
Token Ben
Token ID3932
Feature activation+6.72e-01

Pos logit contributions
s+0.032
 sky+0.026
 nowhere+0.025
ls+0.024
pill+0.023
Neg logit contributions
gh-0.036
 insist-0.036
 compete-0.035
 som-0.035
 wait-0.034
Token are
Token ID389
Feature activation-2.25e+00

Pos logit contributions
gh+0.024
 som+0.022
iding+0.022
 accompl+0.022
 compete+0.021
Neg logit contributions
s-0.016
 sky-0.013
 nowhere-0.012
 living-0.011
 twins-0.011
Token brother
Token ID3956
Feature activation-9.37e+00

Pos logit contributions
s+0.061
 sky+0.053
 nowhere+0.051
ls+0.047
pill+0.046
Neg logit contributions
gh-0.066
 insist-0.064
 som-0.062
 compete-0.061
iding-0.061
Token and
Token ID290
Feature activation-2.62e+00

Pos logit contributions
s+0.203
 sky+0.165
 nowhere+0.158
ls+0.141
 living+0.132
Neg logit contributions
gh-0.330
 som-0.320
 insist-0.319
 compete-0.315
iding-0.310
Token sister
Token ID6621
Feature activation-7.62e+00

Pos logit contributions
s+0.073
 sky+0.058
 twins+0.057
 living+0.054
 she+0.054
Neg logit contributions
gh-0.081
iding-0.081
 som-0.078
heit-0.076
 accompl-0.075
Token.
Token ID13
Feature activation-2.09e-01

Pos logit contributions
s+0.200
 sky+0.172
 nowhere+0.166
ls+0.153
pill+0.146
Neg logit contributions
gh-0.231
 insist-0.226
 som-0.223
 compete-0.220
iding-0.214
Token They
Token ID1119
Feature activation+3.77e-01

Pos logit contributions
s+0.004
 sky+0.003
 nowhere+0.003
 twins+0.002
 living+0.002
Neg logit contributions
gh-0.009
 som-0.008
heit-0.008
iding-0.008
 insist-0.008
Token like
Token ID588
Feature activation-2.54e+00

Pos logit contributions
gh+0.012
 som+0.011
iding+0.011
 accompl+0.011
heit+0.011
Neg logit contributions
s-0.010
 sky-0.009
 living-0.008
 twins-0.008
 nowhere-0.007
Token be
Token ID307
Feature activation+5.95e-01

Pos logit contributions
s+0.089
 nowhere+0.075
 sky+0.074
 living+0.069
 twins+0.066
Neg logit contributions
gh-0.095
iding-0.091
 som-0.088
 insist-0.086
heit-0.085
Token scared
Token ID12008
Feature activation-2.91e+00

Pos logit contributions
gh+0.021
 som+0.020
 insist+0.020
 compete+0.020
iding+0.020
Neg logit contributions
s-0.013
 nowhere-0.012
 sky-0.011
 twins-0.009
 living-0.009
Token of
Token ID286
Feature activation-2.44e+00

Pos logit contributions
s+0.062
 sky+0.049
 nowhere+0.047
ls+0.041
 living+0.041
Neg logit contributions
gh-0.108
 som-0.104
 insist-0.103
 compete-0.102
iding-0.101
Token getting
Token ID1972
Feature activation-7.24e-01

Pos logit contributions
s+0.054
 sky+0.043
 nowhere+0.043
 living+0.038
ls+0.037
Neg logit contributions
gh-0.087
 insist-0.084
 som-0.083
iding-0.083
 compete-0.082
Token lost
Token ID2626
Feature activation-2.68e+00

Pos logit contributions
s+0.016
 sky+0.013
 nowhere+0.012
ls+0.011
 living+0.010
Neg logit contributions
gh-0.026
 som-0.025
 insist-0.025
iding-0.025
 compete-0.025
Token anymore
Token ID7471
Feature activation-9.32e+00

Pos logit contributions
s+0.063
 sky+0.051
 nowhere+0.050
ls+0.044
 living+0.043
Neg logit contributions
gh-0.092
 insist-0.090
 som-0.090
 compete-0.088
iding-0.087
Token.
Token ID13
Feature activation-3.60e-01

Pos logit contributions
s+0.215
 nowhere+0.166
 sky+0.164
ls+0.146
 living+0.142
Neg logit contributions
gh-0.328
 insist-0.326
 som-0.322
 compete-0.316
iding-0.314
Token Max
Token ID5436
Feature activation-1.01e-01

Pos logit contributions
ls+0.009
ymes+0.009
s+0.009
 nowhere+0.008
 pieces+0.008
Neg logit contributions
 som-0.009
gh-0.008
 insist-0.008
 thank-0.008
 spend-0.008
Token's
Token ID338
Feature activation+1.42e+00

Pos logit contributions
s+0.002
 sky+0.002
 nowhere+0.002
ls+0.001
Someone+0.001
Neg logit contributions
gh-0.004
 insist-0.004
 som-0.004
 compete-0.004
iding-0.003
Token distant
Token ID12899
Feature activation+1.67e+00

Pos logit contributions
gh+0.039
 insist+0.038
 som+0.037
 compete+0.037
 deal+0.035
Neg logit contributions
s-0.044
ls-0.035
pill-0.034
 sky-0.034
 nowhere-0.033
Token memory
Token ID4088
Feature activation-4.30e+00

Pos logit contributions
gh+0.049
 som+0.047
 insist+0.047
 compete+0.046
iding+0.045
Neg logit contributions
s-0.048
 sky-0.041
 nowhere-0.039
ls-0.037
pill-0.035
Token<|endoftext|>
Token ID50256
Feature activation-5.92e+00

Pos logit contributions
s+0.002
 nowhere+0.002
ls+0.002
 pieces+0.002
armac+0.002
Neg logit contributions
 insist-0.003
 compete-0.003
gh-0.003
 agree-0.003
 som-0.002
TokenTom
Token ID13787
Feature activation-3.90e-01

Pos logit contributions
s+0.089
 nowhere+0.065
armac+0.061
ls+0.059
 sky+0.056
Neg logit contributions
gh-0.232
 compete-0.220
 som-0.211
 insist-0.209
iding-0.205
Token and
Token ID290
Feature activation-1.49e+00

Pos logit contributions
s+0.008
 sky+0.006
 nowhere+0.006
ls+0.006
pill+0.005
Neg logit contributions
gh-0.014
 insist-0.014
 som-0.014
 compete-0.014
iding-0.013
Token Lily
Token ID20037
Feature activation-1.13e+00

Pos logit contributions
s+0.039
 sky+0.033
 nowhere+0.031
ls+0.028
 twins+0.028
Neg logit contributions
gh-0.048
 som-0.046
 insist-0.045
iding-0.045
 compete-0.045
Token are
Token ID389
Feature activation-1.97e+00

Pos logit contributions
s+0.030
 sky+0.025
 nowhere+0.023
ls+0.022
 living+0.021
Neg logit contributions
gh-0.036
 som-0.034
iding-0.034
 insist-0.033
 compete-0.033
Token brother
Token ID3956
Feature activation-9.32e+00

Pos logit contributions
s+0.056
 sky+0.049
 nowhere+0.046
pill+0.045
ls+0.045
Neg logit contributions
gh-0.055
 insist-0.054
 compete-0.051
iding-0.051
 som-0.051
Token and
Token ID290
Feature activation-2.65e+00

Pos logit contributions
s+0.208
 sky+0.176
 nowhere+0.170
ls+0.153
pill+0.147
Neg logit contributions
gh-0.310
 som-0.301
 insist-0.299
 compete-0.295
iding-0.290
Token sister
Token ID6621
Feature activation-7.46e+00

Pos logit contributions
s+0.058
 twins+0.044
 sky+0.043
 she+0.041
 living+0.041
Neg logit contributions
gh-0.098
iding-0.096
 som-0.093
heit-0.092
 accompl-0.091
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
s+0.196
 sky+0.172
 nowhere+0.167
ls+0.154
pill+0.147
Neg logit contributions
gh-0.222
 insist-0.217
 som-0.214
 compete-0.211
iding-0.205
Token They
Token ID1119
Feature activation+4.03e-01

Pos logit contributions
s+0.005
 sky+0.004
 nowhere+0.004
 twins+0.003
+0.003
Neg logit contributions
gh-0.010
 som-0.010
heit-0.010
iding-0.010
 insist-0.009
Token like
Token ID588
Feature activation-2.45e+00

Pos logit contributions
gh+0.014
 som+0.013
iding+0.012
 accompl+0.012
heit+0.012
Neg logit contributions
s-0.011
 sky-0.009
 living-0.008
 twins-0.008
 nowhere-0.007
Token<|endoftext|>
Token ID50256
Feature activation-6.03e+00

Pos logit contributions
s+0.004
ls+0.003
 nowhere+0.003
 pieces+0.003
 sky+0.003
Neg logit contributions
 insist-0.006
 compete-0.005
gh-0.005
 wait-0.005
 som-0.005
TokenTim
Token ID14967
Feature activation+7.13e-01

Pos logit contributions
s+0.082
 nowhere+0.061
 sky+0.052
armac+0.049
ls+0.049
Neg logit contributions
gh-0.247
 compete-0.237
 insist-0.232
 som-0.231
iding-0.224
Token and
Token ID290
Feature activation-1.26e+00

Pos logit contributions
gh+0.027
 insist+0.027
 som+0.026
 compete+0.026
iding+0.026
Neg logit contributions
s-0.014
 sky-0.011
 nowhere-0.010
ls-0.009
 twins-0.008
Token Sue
Token ID26089
Feature activation-1.35e+00

Pos logit contributions
s+0.034
 sky+0.029
 nowhere+0.027
ls+0.026
 living+0.024
Neg logit contributions
gh-0.039
 insist-0.037
 som-0.037
 compete-0.037
iding-0.036
Token are
Token ID389
Feature activation-2.04e+00

Pos logit contributions
s+0.035
 sky+0.030
 nowhere+0.029
ls+0.027
pill+0.025
Neg logit contributions
gh-0.041
 insist-0.041
 som-0.040
 compete-0.040
iding-0.038
Token brother
Token ID3956
Feature activation-9.29e+00

Pos logit contributions
s+0.060
 sky+0.052
pill+0.048
 nowhere+0.048
ls+0.047
Neg logit contributions
gh-0.057
 insist-0.055
 som-0.053
 compete-0.053
iding-0.052
Token and
Token ID290
Feature activation-2.47e+00

Pos logit contributions
s+0.191
 sky+0.148
 nowhere+0.137
 twins+0.123
ls+0.123
Neg logit contributions
gh-0.357
 som-0.344
 insist-0.344
 compete-0.339
iding-0.334
Token sister
Token ID6621
Feature activation-7.47e+00

Pos logit contributions
s+0.059
 she+0.047
 twins+0.045
 sky+0.045
 living+0.042
Neg logit contributions
iding-0.089
gh-0.086
heit-0.085
icious-0.083
 som-0.083
Token.
Token ID13
Feature activation-3.51e-01

Pos logit contributions
s+0.180
 sky+0.140
 nowhere+0.132
 twins+0.124
 living+0.122
Neg logit contributions
gh-0.264
 som-0.255
 insist-0.248
 compete-0.248
iding-0.247
Token They
Token ID1119
Feature activation+3.31e-01

Pos logit contributions
s+0.007
 sky+0.005
 nowhere+0.005
 twins+0.004
+0.004
Neg logit contributions
gh-0.014
 som-0.014
heit-0.013
iding-0.013
 insist-0.013
Token like
Token ID588
Feature activation-2.52e+00

Pos logit contributions
gh+0.011
iding+0.010
 som+0.010
 accompl+0.010
heit+0.010
Neg logit contributions
s-0.009
 sky-0.007
 living-0.007
 twins-0.007
 nowhere-0.007
TokenL
Token ID43
Feature activation+1.71e+00

Pos logit contributions
s+0.083
 nowhere+0.060
ls+0.055
 sky+0.053
armac+0.049
Neg logit contributions
gh-0.235
 compete-0.225
 som-0.218
 insist-0.217
iding-0.212
Tokenily
Token ID813
Feature activation-1.10e+00

Pos logit contributions
gh+0.045
 insist+0.039
 som+0.038
iding+0.037
ern+0.037
Neg logit contributions
s-0.052
 sky-0.049
pill-0.045
 nowhere-0.044
Someone-0.042
Token and
Token ID290
Feature activation-1.24e+00

Pos logit contributions
s+0.022
 sky+0.017
 nowhere+0.016
ls+0.015
 twins+0.014
Neg logit contributions
gh-0.041
 insist-0.040
 som-0.040
 compete-0.039
iding-0.038
Token Tom
Token ID4186
Feature activation+2.28e-01

Pos logit contributions
s+0.037
 sky+0.032
ls+0.030
pill+0.030
 nowhere+0.030
Neg logit contributions
 insist-0.034
gh-0.033
 compete-0.033
 wait-0.032
 som-0.032
Token are
Token ID389
Feature activation-1.82e+00

Pos logit contributions
gh+0.008
 insist+0.007
 som+0.007
 compete+0.007
iding+0.007
Neg logit contributions
s-0.005
 sky-0.005
 nowhere-0.004
ls-0.004
 twins-0.004
Token brother
Token ID3956
Feature activation-9.22e+00

Pos logit contributions
s+0.048
 sky+0.041
 nowhere+0.039
ls+0.037
pill+0.036
Neg logit contributions
gh-0.056
 insist-0.054
 som-0.053
 compete-0.052
iding-0.052
Token and
Token ID290
Feature activation-2.46e+00

Pos logit contributions
s+0.188
 sky+0.152
 nowhere+0.145
ls+0.129
pill+0.120
Neg logit contributions
gh-0.334
 som-0.324
 insist-0.324
 compete-0.320
iding-0.314
Token sister
Token ID6621
Feature activation-7.10e+00

Pos logit contributions
s+0.056
 twins+0.044
 she+0.043
 sky+0.041
 living+0.039
Neg logit contributions
iding-0.091
gh-0.089
 som-0.087
heit-0.086
 accompl-0.085
Token.
Token ID13
Feature activation-2.98e-01

Pos logit contributions
s+0.176
 sky+0.142
 nowhere+0.135
ls+0.123
 twins+0.121
Neg logit contributions
gh-0.239
 som-0.231
 insist-0.227
 compete-0.226
iding-0.223
Token They
Token ID1119
Feature activation+3.83e-01

Pos logit contributions
s+0.006
 sky+0.005
 nowhere+0.004
 twins+0.004
 living+0.004
Neg logit contributions
gh-0.012
 som-0.011
iding-0.011
heit-0.011
 insist-0.011
Token like
Token ID588
Feature activation-2.31e+00

Pos logit contributions
gh+0.013
 som+0.012
iding+0.012
 accompl+0.012
heit+0.012
Neg logit contributions
s-0.010
 sky-0.008
 living-0.007
 twins-0.007
 nowhere-0.007
TokenS
Token ID50
Feature activation+2.82e+00

Pos logit contributions
s+0.096
 nowhere+0.081
armac+0.080
ls+0.068
Someone+0.067
Neg logit contributions
gh-0.202
 compete-0.195
 som-0.182
 insist-0.182
 skate-0.173
Tokenara
Token ID3301
Feature activation-2.31e-01

Pos logit contributions
gh+0.053
 insist+0.047
 som+0.044
 compete+0.043
 wait+0.042
Neg logit contributions
s-0.101
 nowhere-0.096
 sky-0.092
pill-0.091
 living-0.089
Token and
Token ID290
Feature activation-1.15e+00

Pos logit contributions
s+0.005
 nowhere+0.004
 sky+0.004
ls+0.004
Someone+0.004
Neg logit contributions
 insist-0.008
gh-0.007
 compete-0.007
 som-0.007
 wait-0.007
Token Ben
Token ID3932
Feature activation+8.76e-01

Pos logit contributions
s+0.031
 sky+0.026
 nowhere+0.025
pill+0.024
ls+0.024
Neg logit contributions
 insist-0.035
 compete-0.034
gh-0.034
 wait-0.033
 som-0.033
Token are
Token ID389
Feature activation-1.97e+00

Pos logit contributions
gh+0.028
 insist+0.027
 som+0.027
 compete+0.027
iding+0.026
Neg logit contributions
s-0.022
 sky-0.018
 nowhere-0.018
ls-0.016
pill-0.015
Token brother
Token ID3956
Feature activation-9.18e+00

Pos logit contributions
s+0.054
 sky+0.047
 nowhere+0.045
ls+0.042
pill+0.042
Neg logit contributions
gh-0.056
 insist-0.055
 compete-0.053
 som-0.052
iding-0.052
Token and
Token ID290
Feature activation-2.51e+00

Pos logit contributions
s+0.206
 sky+0.179
 nowhere+0.174
pill+0.150
ls+0.150
Neg logit contributions
gh-0.294
 som-0.286
 insist-0.286
 compete-0.282
iding-0.279
Token sister
Token ID6621
Feature activation-7.42e+00

Pos logit contributions
s+0.063
 sky+0.051
 nowhere+0.048
 twins+0.047
 living+0.046
Neg logit contributions
gh-0.083
iding-0.080
 som-0.080
 insist-0.077
heit-0.076
Token.
Token ID13
Feature activation-1.88e-01

Pos logit contributions
s+0.204
 sky+0.188
 nowhere+0.186
pill+0.170
ls+0.168
Neg logit contributions
 insist-0.197
gh-0.194
 som-0.186
 compete-0.186
iding-0.179
Token They
Token ID1119
Feature activation+4.66e-01

Pos logit contributions
s+0.004
 sky+0.003
 nowhere+0.003
 twins+0.002
 living+0.002
Neg logit contributions
gh-0.007
 som-0.007
iding-0.007
 insist-0.007
 compete-0.007
Token are
Token ID389
Feature activation-1.94e+00

Pos logit contributions
gh+0.015
 som+0.014
iding+0.014
 accompl+0.014
heit+0.013
Neg logit contributions
s-0.012
 sky-0.011
 living-0.010
 twins-0.009
 nowhere-0.009
TokenS
Token ID50
Feature activation+2.74e+00

Pos logit contributions
s+0.084
 nowhere+0.063
ls+0.052
armac+0.050
 sky+0.050
Neg logit contributions
gh-0.235
 compete-0.226
 som-0.218
 insist-0.216
iding-0.210
Tokenara
Token ID3301
Feature activation-1.47e-01

Pos logit contributions
gh+0.079
 insist+0.073
 som+0.069
 wait+0.067
 compete+0.067
Neg logit contributions
s-0.067
 nowhere-0.066
Someone-0.061
pill-0.061
 sky-0.061
Token and
Token ID290
Feature activation-1.35e+00

Pos logit contributions
s+0.003
 nowhere+0.003
 sky+0.003
ls+0.002
Someone+0.002
Neg logit contributions
 insist-0.005
gh-0.005
 compete-0.005
 som-0.005
 wait-0.005
Token Ben
Token ID3932
Feature activation+1.01e+00

Pos logit contributions
s+0.034
 sky+0.028
pill+0.026
 nowhere+0.026
ls+0.026
Neg logit contributions
 insist-0.043
 wait-0.042
 compete-0.041
 spend-0.041
 som-0.040
Token are
Token ID389
Feature activation-1.76e+00

Pos logit contributions
gh+0.033
 som+0.032
 insist+0.032
 compete+0.031
iding+0.031
Neg logit contributions
s-0.025
 sky-0.021
 nowhere-0.020
ls-0.018
 living-0.017
Token brother
Token ID3956
Feature activation-9.08e+00

Pos logit contributions
s+0.048
 sky+0.040
 nowhere+0.039
pill+0.036
ls+0.036
Neg logit contributions
gh-0.052
 insist-0.051
iding-0.049
 som-0.049
 compete-0.048
Token and
Token ID290
Feature activation-2.41e+00

Pos logit contributions
s+0.218
 sky+0.180
 nowhere+0.172
ls+0.157
 living+0.149
Neg logit contributions
gh-0.304
 som-0.293
 insist-0.293
 compete-0.289
iding-0.284
Token sister
Token ID6621
Feature activation-7.25e+00

Pos logit contributions
s+0.051
 sky+0.040
 nowhere+0.038
 twins+0.035
 living+0.034
Neg logit contributions
gh-0.089
 som-0.086
iding-0.085
 insist-0.084
 compete-0.083
Token.
Token ID13
Feature activation-3.34e-01

Pos logit contributions
s+0.185
 sky+0.153
 nowhere+0.146
ls+0.134
 living+0.129
Neg logit contributions
gh-0.235
 som-0.226
 insist-0.225
 compete-0.222
iding-0.218
Token They
Token ID1119
Feature activation+5.41e-01

Pos logit contributions
s+0.006
 sky+0.005
 twins+0.004
 nowhere+0.004
 living+0.004
Neg logit contributions
gh-0.014
 som-0.013
iding-0.013
heit-0.013
 compete-0.013
Token live
Token ID2107
Feature activation-1.04e-01

Pos logit contributions
gh+0.018
 som+0.017
iding+0.017
 accompl+0.017
heit+0.017
Neg logit contributions
s-0.013
 sky-0.012
 living-0.011
 twins-0.010
 nowhere-0.010
Token<|endoftext|>
Token ID50256
Feature activation-5.86e+00

Pos logit contributions
s+0.009
ls+0.007
 nowhere+0.007
 sky+0.007
actus+0.006
Neg logit contributions
gh-0.017
 compete-0.017
 insist-0.016
 som-0.016
iding-0.016
TokenTom
Token ID13787
Feature activation+1.46e-02

Pos logit contributions
s+0.087
 nowhere+0.065
ls+0.058
armac+0.056
 sky+0.054
Neg logit contributions
gh-0.229
 compete-0.219
 som-0.210
 insist-0.209
iding-0.202
Token and
Token ID290
Feature activation-1.25e+00

Pos logit contributions
gh+0.001
 insist+0.001
 som+0.001
 compete+0.001
iding+0.000
Neg logit contributions
s-0.000
 sky-0.000
 nowhere-0.000
ls-0.000
pill-0.000
Token Lily
Token ID20037
Feature activation-7.99e-01

Pos logit contributions
s+0.034
 sky+0.029
 nowhere+0.027
ls+0.026
pill+0.025
Neg logit contributions
gh-0.038
 insist-0.037
 som-0.037
 compete-0.037
 boost-0.034
Token are
Token ID389
Feature activation-1.77e+00

Pos logit contributions
s+0.021
 sky+0.018
 nowhere+0.017
ls+0.016
 living+0.015
Neg logit contributions
gh-0.025
 som-0.024
 insist-0.024
 compete-0.023
iding-0.023
Token brother
Token ID3956
Feature activation-9.07e+00

Pos logit contributions
s+0.051
 sky+0.044
pill+0.041
 nowhere+0.041
ls+0.040
Neg logit contributions
gh-0.049
 insist-0.049
 compete-0.046
iding-0.045
 som-0.045
Token and
Token ID290
Feature activation-2.28e+00

Pos logit contributions
s+0.218
 sky+0.184
 nowhere+0.177
ls+0.161
pill+0.153
Neg logit contributions
gh-0.294
 insist-0.284
 som-0.284
 compete-0.280
iding-0.274
Token sister
Token ID6621
Feature activation-7.36e+00

Pos logit contributions
s+0.056
 sky+0.043
 twins+0.043
 she+0.041
 living+0.041
Neg logit contributions
gh-0.078
iding-0.077
 som-0.075
heit-0.073
 accompl-0.073
Token.
Token ID13
Feature activation-1.96e-01

Pos logit contributions
s+0.190
 sky+0.161
 nowhere+0.155
ls+0.143
pill+0.135
Neg logit contributions
gh-0.231
 insist-0.223
 som-0.222
 compete-0.219
iding-0.214
Token They
Token ID1119
Feature activation+5.38e-01

Pos logit contributions
s+0.004
 sky+0.003
 twins+0.002
 nowhere+0.002
 living+0.002
Neg logit contributions
gh-0.008
 som-0.008
heit-0.008
iding-0.008
 insist-0.007
Token like
Token ID588
Feature activation-2.36e+00

Pos logit contributions
gh+0.018
 som+0.017
iding+0.017
 accompl+0.016
heit+0.016
Neg logit contributions
s-0.014
 sky-0.012
 living-0.011
 twins-0.010
 nowhere-0.010
Token<|endoftext|>
Token ID50256
Feature activation-5.51e+00

Pos logit contributions
s+0.004
ls+0.003
 nowhere+0.003
 pieces+0.003
 sky+0.003
Neg logit contributions
 compete-0.004
 insist-0.004
gh-0.004
 som-0.004
 accompl-0.004
TokenTom
Token ID13787
Feature activation+4.56e-01

Pos logit contributions
s+0.078
 nowhere+0.058
ls+0.051
 sky+0.050
armac+0.046
Neg logit contributions
gh-0.222
 compete-0.214
 som-0.206
 insist-0.206
iding-0.201
Token and
Token ID290
Feature activation-1.14e+00

Pos logit contributions
 insist+0.016
gh+0.016
 compete+0.016
 som+0.015
iding+0.015
Neg logit contributions
s-0.009
 sky-0.007
 nowhere-0.007
ls-0.007
pill-0.006
Token Anna
Token ID11735
Feature activation+3.73e-01

Pos logit contributions
s+0.028
 sky+0.024
 nowhere+0.023
ls+0.021
 living+0.020
Neg logit contributions
gh-0.038
 som-0.036
 insist-0.036
 compete-0.036
iding-0.035
Token are
Token ID389
Feature activation-1.48e+00

Pos logit contributions
gh+0.014
 som+0.013
iding+0.013
 insist+0.013
 compete+0.013
Neg logit contributions
s-0.008
 sky-0.006
 nowhere-0.006
 living-0.005
ls-0.005
Token brother
Token ID3956
Feature activation-9.07e+00

Pos logit contributions
s+0.040
 sky+0.033
 nowhere+0.032
ls+0.031
pill+0.031
Neg logit contributions
gh-0.044
 insist-0.044
 som-0.042
 compete-0.042
iding-0.042
Token and
Token ID290
Feature activation-2.29e+00

Pos logit contributions
s+0.209
 sky+0.171
 nowhere+0.164
ls+0.149
 living+0.139
Neg logit contributions
gh-0.310
 som-0.299
 insist-0.299
 compete-0.295
iding-0.289
Token sister
Token ID6621
Feature activation-7.18e+00

Pos logit contributions
s+0.051
 she+0.040
 twins+0.039
 sky+0.038
 living+0.037
Neg logit contributions
iding-0.085
gh-0.084
heit-0.081
 som-0.080
icious-0.080
Token.
Token ID13
Feature activation-2.68e-01

Pos logit contributions
s+0.177
 sky+0.141
 nowhere+0.132
 living+0.122
 twins+0.121
Neg logit contributions
gh-0.247
 som-0.237
 insist-0.233
 compete-0.232
iding-0.231
Token They
Token ID1119
Feature activation+5.04e-01

Pos logit contributions
s+0.006
 sky+0.005
 nowhere+0.004
ls+0.004
 twins+0.004
Neg logit contributions
gh-0.010
 som-0.009
 insist-0.009
 compete-0.009
iding-0.009
Token like
Token ID588
Feature activation-2.31e+00

Pos logit contributions
gh+0.017
iding+0.016
 som+0.015
 accompl+0.015
heit+0.015
Neg logit contributions
s-0.013
 sky-0.011
 living-0.010
 twins-0.010
 nowhere-0.009
Token<|endoftext|>
Token ID50256
Feature activation-5.88e+00

Pos logit contributions
gh+0.006
 insist+0.006
 compete+0.006
 som+0.006
iding+0.005
Neg logit contributions
s-0.004
ls-0.003
 nowhere-0.003
 sky-0.003
 pieces-0.003
TokenTom
Token ID13787
Feature activation+7.70e-02

Pos logit contributions
s+0.084
 nowhere+0.058
ls+0.053
 sky+0.050
armac+0.048
Neg logit contributions
gh-0.241
 compete-0.229
 som-0.224
 insist-0.223
iding-0.218
Token and
Token ID290
Feature activation-1.29e+00

Pos logit contributions
gh+0.003
 insist+0.003
 som+0.003
 compete+0.003
iding+0.003
Neg logit contributions
s-0.002
 sky-0.001
 nowhere-0.001
ls-0.001
pill-0.001
Token Lily
Token ID20037
Feature activation-8.00e-01

Pos logit contributions
s+0.035
 sky+0.030
 nowhere+0.029
ls+0.027
 living+0.025
Neg logit contributions
gh-0.039
 som-0.037
 insist-0.037
 compete-0.037
iding-0.036
Token are
Token ID389
Feature activation-1.76e+00

Pos logit contributions
s+0.022
 sky+0.019
 nowhere+0.018
ls+0.017
pill+0.016
Neg logit contributions
gh-0.024
 insist-0.023
 som-0.023
 compete-0.023
iding-0.022
Token brother
Token ID3956
Feature activation-9.06e+00

Pos logit contributions
s+0.048
 sky+0.041
 nowhere+0.039
ls+0.038
pill+0.037
Neg logit contributions
gh-0.051
 insist-0.050
iding-0.047
 som-0.047
 compete-0.047
Token and
Token ID290
Feature activation-2.51e+00

Pos logit contributions
s+0.200
 sky+0.163
 nowhere+0.156
ls+0.140
pill+0.131
Neg logit contributions
gh-0.317
 som-0.306
 insist-0.305
 compete-0.301
iding-0.297
Token sister
Token ID6621
Feature activation-7.43e+00

Pos logit contributions
s+0.054
 sky+0.041
 twins+0.041
 living+0.038
 nowhere+0.038
Neg logit contributions
gh-0.092
iding-0.091
 som-0.089
heit-0.087
 accompl-0.086
Token.
Token ID13
Feature activation-1.94e-01

Pos logit contributions
s+0.194
 sky+0.167
 nowhere+0.162
ls+0.150
pill+0.143
Neg logit contributions
gh-0.223
 insist-0.219
 som-0.215
 compete-0.213
iding-0.208
Token They
Token ID1119
Feature activation+5.96e-01

Pos logit contributions
s+0.004
 sky+0.003
 nowhere+0.003
 twins+0.003
 living+0.002
Neg logit contributions
gh-0.008
 som-0.007
iding-0.007
heit-0.007
 insist-0.007
Token like
Token ID588
Feature activation-2.33e+00

Pos logit contributions
gh+0.019
 som+0.017
iding+0.017
 accompl+0.017
heit+0.017
Neg logit contributions
s-0.016
 sky-0.014
 living-0.013
 nowhere-0.013
 twins-0.012
TokenS
Token ID50
Feature activation+2.84e+00

Pos logit contributions
s+0.093
 nowhere+0.077
armac+0.071
ls+0.066
Someone+0.061
Neg logit contributions
gh-0.215
 compete-0.204
 som-0.193
 insist-0.191
iding-0.184
Tokenara
Token ID3301
Feature activation-1.28e-01

Pos logit contributions
gh+0.078
 insist+0.070
 som+0.068
 compete+0.065
 wait+0.064
Neg logit contributions
s-0.075
 nowhere-0.072
 sky-0.068
pill-0.067
 shadows-0.067
Token and
Token ID290
Feature activation-1.19e+00

Pos logit contributions
s+0.003
 nowhere+0.002
 sky+0.002
ls+0.002
Someone+0.002
Neg logit contributions
 insist-0.004
gh-0.004
 compete-0.004
 som-0.004
 wait-0.004
Token Tom
Token ID4186
Feature activation+2.25e-01

Pos logit contributions
s+0.030
 sky+0.025
 nowhere+0.024
pill+0.023
ls+0.023
Neg logit contributions
 insist-0.037
 compete-0.036
 wait-0.036
gh-0.036
 som-0.035
Token are
Token ID389
Feature activation-1.84e+00

Pos logit contributions
gh+0.007
 insist+0.007
 som+0.007
 compete+0.007
iding+0.007
Neg logit contributions
s-0.006
 sky-0.005
 nowhere-0.005
ls-0.004
pill-0.004
Token brother
Token ID3956
Feature activation-9.03e+00

Pos logit contributions
s+0.050
 sky+0.044
 nowhere+0.042
pill+0.040
ls+0.039
Neg logit contributions
gh-0.054
 insist-0.052
iding-0.050
 compete-0.049
 som-0.049
Token and
Token ID290
Feature activation-2.47e+00

Pos logit contributions
s+0.216
 sky+0.184
 nowhere+0.179
ls+0.160
pill+0.153
Neg logit contributions
gh-0.290
 som-0.280
 insist-0.279
 compete-0.276
iding-0.271
Token sister
Token ID6621
Feature activation-7.33e+00

Pos logit contributions
s+0.057
 sky+0.043
 twins+0.042
 nowhere+0.040
 she+0.038
Neg logit contributions
gh-0.088
iding-0.088
 som-0.086
heit-0.083
 accompl-0.083
Token.
Token ID13
Feature activation-1.85e-01

Pos logit contributions
s+0.194
 sky+0.170
 nowhere+0.166
ls+0.152
pill+0.146
Neg logit contributions
gh-0.216
 insist-0.212
 som-0.208
 compete-0.206
iding-0.200
Token They
Token ID1119
Feature activation+4.66e-01

Pos logit contributions
s+0.004
 sky+0.003
 nowhere+0.002
 twins+0.002
+0.002
Neg logit contributions
gh-0.008
 som-0.007
iding-0.007
heit-0.007
 insist-0.007
Token like
Token ID588
Feature activation-2.43e+00

Pos logit contributions
gh+0.015
 som+0.014
iding+0.014
 accompl+0.014
heit+0.014
Neg logit contributions
s-0.012
 sky-0.011
 living-0.010
 twins-0.009
 nowhere-0.009
Token and
Token ID290
Feature activation+2.08e-01

Pos logit contributions
s+0.022
 sky+0.020
 nowhere+0.020
ls+0.020
pill+0.019
Neg logit contributions
 insist-0.025
 som-0.024
gh-0.024
 repeat-0.023
 wait-0.023
Token Tom
Token ID4186
Feature activation+6.19e-02

Pos logit contributions
gh+0.006
 som+0.006
 insist+0.006
iding+0.006
 compete+0.006
Neg logit contributions
s-0.006
 sky-0.005
 nowhere-0.005
ls-0.004
 twins-0.004
Token agreed
Token ID4987
Feature activation+4.56e-01

Pos logit contributions
gh+0.002
 insist+0.002
 som+0.002
 compete+0.002
iding+0.002
Neg logit contributions
s-0.002
 sky-0.001
 nowhere-0.001
ls-0.001
 living-0.001
Token and
Token ID290
Feature activation-7.20e-01

Pos logit contributions
gh+0.018
 som+0.018
 compete+0.018
heit+0.018
 insist+0.018
Neg logit contributions
s-0.009
 sky-0.006
 nowhere-0.006
 twins-0.005
 living-0.005
Token hugged
Token ID41130
Feature activation-1.85e+00

Pos logit contributions
s+0.017
 sky+0.013
 nowhere+0.012
 twins+0.012
 she+0.011
Neg logit contributions
gh-0.027
iding-0.026
heit-0.025
 som-0.025
 compete-0.024
Token mom
Token ID1995
Feature activation-9.00e+00

Pos logit contributions
s+0.043
 sky+0.035
 nowhere+0.033
ls+0.030
 twins+0.029
Neg logit contributions
gh-0.065
 som-0.063
 insist-0.062
 compete-0.061
iding-0.061
Token.
Token ID13
Feature activation-2.31e-01

Pos logit contributions
s+0.211
 sky+0.186
 nowhere+0.184
ls+0.166
pill+0.163
Neg logit contributions
gh-0.283
 insist-0.279
 som-0.269
 compete-0.268
iding-0.264
Token They
Token ID1119
Feature activation-3.12e-01

Pos logit contributions
s+0.007
 nowhere+0.007
ls+0.006
pill+0.006
ons+0.006
Neg logit contributions
 insist-0.005
 compete-0.005
 agree-0.005
gh-0.005
 som-0.005
Token all
Token ID477
Feature activation-2.96e-01

Pos logit contributions
s+0.007
 sky+0.006
 nowhere+0.006
ls+0.005
 twins+0.005
Neg logit contributions
gh-0.011
 som-0.010
 insist-0.010
 compete-0.010
iding-0.010
Token went
Token ID1816
Feature activation+2.66e+00

Pos logit contributions
s+0.008
 sky+0.006
 nowhere+0.006
ls+0.005
 twins+0.005
Neg logit contributions
gh-0.010
 som-0.009
 compete-0.009
 insist-0.009
iding-0.009
Token to
Token ID284
Feature activation+1.41e+00

Pos logit contributions
gh+0.087
 insist+0.084
 som+0.084
 compete+0.083
iding+0.080
Neg logit contributions
s-0.063
 sky-0.053
 nowhere-0.052
pill-0.047
ls-0.046
Token<|endoftext|>
Token ID50256
Feature activation-5.85e+00

Pos logit contributions
gh+0.001
 som+0.001
 compete+0.001
 insist+0.001
iding+0.001
Neg logit contributions
s-0.000
 nowhere-0.000
ls-0.000
 sky-0.000
 pieces-0.000
TokenTom
Token ID13787
Feature activation+1.56e-01

Pos logit contributions
s+0.095
 nowhere+0.080
armac+0.073
ls+0.069
Someone+0.064
Neg logit contributions
gh-0.210
 compete-0.199
 som-0.189
 insist-0.187
iding-0.181
Token and
Token ID290
Feature activation-1.21e+00

Pos logit contributions
gh+0.006
 insist+0.006
 som+0.006
 compete+0.006
iding+0.005
Neg logit contributions
s-0.003
 sky-0.002
 nowhere-0.002
ls-0.002
pill-0.002
Token Lily
Token ID20037
Feature activation-6.94e-01

Pos logit contributions
s+0.034
 sky+0.029
 nowhere+0.028
ls+0.026
pill+0.026
Neg logit contributions
gh-0.035
 insist-0.035
 compete-0.034
 som-0.034
 wait-0.032
Token are
Token ID389
Feature activation-1.65e+00

Pos logit contributions
s+0.018
 sky+0.015
 nowhere+0.013
 living+0.013
ls+0.012
Neg logit contributions
gh-0.023
 som-0.022
iding-0.022
 compete-0.021
 insist-0.021
Token brother
Token ID3956
Feature activation-8.97e+00

Pos logit contributions
s+0.046
 sky+0.040
 nowhere+0.037
pill+0.037
ls+0.036
Neg logit contributions
gh-0.046
 insist-0.046
iding-0.043
 compete-0.043
 som-0.043
Token and
Token ID290
Feature activation-2.30e+00

Pos logit contributions
s+0.191
 sky+0.166
 nowhere+0.160
ls+0.140
pill+0.139
Neg logit contributions
gh-0.297
 som-0.290
 insist-0.290
 compete-0.284
iding-0.281
Token sister
Token ID6621
Feature activation-7.16e+00

Pos logit contributions
s+0.057
 sky+0.044
 twins+0.042
 nowhere+0.041
 living+0.040
Neg logit contributions
gh-0.079
iding-0.077
 som-0.076
heit-0.073
 accompl-0.073
Token.
Token ID13
Feature activation-7.03e-02

Pos logit contributions
s+0.193
 sky+0.172
 nowhere+0.168
ls+0.155
pill+0.152
Neg logit contributions
 insist-0.202
gh-0.201
 som-0.195
 compete-0.193
iding-0.187
Token They
Token ID1119
Feature activation+6.19e-01

Pos logit contributions
s+0.001
 sky+0.001
 twins+0.001
 nowhere+0.001
+0.001
Neg logit contributions
gh-0.003
 som-0.003
heit-0.003
iding-0.003
 insist-0.003
Token like
Token ID588
Feature activation-2.28e+00

Pos logit contributions
gh+0.020
 som+0.018
iding+0.018
 accompl+0.018
heit+0.018
Neg logit contributions
s-0.017
 sky-0.014
 living-0.013
 twins-0.013
 nowhere-0.013
Token<|endoftext|>
Token ID50256
Feature activation-6.09e+00

Pos logit contributions
s+0.010
 nowhere+0.009
 sky+0.008
ls+0.008
actus+0.008
Neg logit contributions
 insist-0.018
gh-0.018
 compete-0.018
 som-0.017
iding-0.017
TokenTom
Token ID13787
Feature activation-6.65e-02

Pos logit contributions
s+0.089
 nowhere+0.074
armac+0.060
 sky+0.059
ls+0.056
Neg logit contributions
gh-0.237
 compete-0.228
 insist-0.220
 som-0.219
iding-0.212
Token and
Token ID290
Feature activation-1.26e+00

Pos logit contributions
s+0.001
 sky+0.001
 nowhere+0.001
ls+0.001
pill+0.001
Neg logit contributions
gh-0.003
 insist-0.003
 som-0.002
 compete-0.002
iding-0.002
Token Lily
Token ID20037
Feature activation-8.50e-01

Pos logit contributions
s+0.036
 sky+0.031
 nowhere+0.029
ls+0.028
pill+0.027
Neg logit contributions
gh-0.036
 insist-0.036
 compete-0.035
 som-0.035
 wait-0.033
Token were
Token ID547
Feature activation-2.05e+00

Pos logit contributions
s+0.022
 sky+0.018
 nowhere+0.016
 living+0.015
ls+0.015
Neg logit contributions
gh-0.028
 som-0.027
iding-0.026
 accompl-0.026
 compete-0.026
Token brother
Token ID3956
Feature activation-8.94e+00

Pos logit contributions
s+0.057
 sky+0.048
 nowhere+0.045
pill+0.044
ls+0.043
Neg logit contributions
gh-0.059
 insist-0.058
iding-0.054
 compete-0.054
 som-0.053
Token and
Token ID290
Feature activation-2.56e+00

Pos logit contributions
s+0.212
 sky+0.183
 nowhere+0.177
ls+0.160
pill+0.156
Neg logit contributions
gh-0.282
 insist-0.275
 som-0.273
 compete-0.269
iding-0.265
Token sister
Token ID6621
Feature activation-7.40e+00

Pos logit contributions
s+0.069
 sky+0.056
 nowhere+0.055
 twins+0.054
 living+0.052
Neg logit contributions
gh-0.080
iding-0.078
 som-0.077
heit-0.074
 compete-0.073
Token.
Token ID13
Feature activation-2.93e-01

Pos logit contributions
s+0.197
 sky+0.172
 nowhere+0.166
ls+0.154
pill+0.149
Neg logit contributions
gh-0.217
 insist-0.214
 som-0.208
 compete-0.207
iding-0.201
Token They
Token ID1119
Feature activation+3.79e-01

Pos logit contributions
s+0.006
 sky+0.005
 nowhere+0.004
 twins+0.004
 living+0.004
Neg logit contributions
gh-0.012
 som-0.011
iding-0.011
heit-0.011
 insist-0.011
Token lived
Token ID5615
Feature activation-2.26e+00

Pos logit contributions
gh+0.015
 som+0.015
iding+0.014
 accompl+0.014
 compete+0.014
Neg logit contributions
s-0.007
 sky-0.006
 nowhere-0.005
 living-0.004
 twins-0.004
Token<|endoftext|>
Token ID50256
Feature activation-5.92e+00

Pos logit contributions
s+0.013
ls+0.012
 nowhere+0.012
ons+0.011
 pieces+0.011
Neg logit contributions
 insist-0.020
gh-0.019
 som-0.019
 compete-0.019
 boost-0.018
TokenTim
Token ID14967
Feature activation+9.19e-01

Pos logit contributions
s+0.091
 nowhere+0.073
armac+0.063
ls+0.063
 sky+0.056
Neg logit contributions
gh-0.224
 compete-0.216
 insist-0.206
 som-0.205
iding-0.199
Token and
Token ID290
Feature activation-1.02e+00

Pos logit contributions
gh+0.036
 insist+0.035
 som+0.035
 compete+0.035
iding+0.034
Neg logit contributions
s-0.016
 sky-0.012
 nowhere-0.012
ls-0.010
 living-0.009
Token Mia
Token ID32189
Feature activation+7.29e-01

Pos logit contributions
s+0.029
 sky+0.024
 nowhere+0.023
ls+0.022
pill+0.022
Neg logit contributions
gh-0.030
 insist-0.029
 compete-0.029
 som-0.029
 wait-0.027
Token are
Token ID389
Feature activation-1.69e+00

Pos logit contributions
gh+0.025
 som+0.024
 insist+0.024
iding+0.024
 compete+0.024
Neg logit contributions
s-0.017
 sky-0.014
 nowhere-0.013
ls-0.012
 living-0.011
Token brother
Token ID3956
Feature activation-8.94e+00

Pos logit contributions
s+0.050
 sky+0.042
 nowhere+0.041
pill+0.040
ls+0.039
Neg logit contributions
 insist-0.045
gh-0.044
iding-0.042
 compete-0.042
 wait-0.041
Token and
Token ID290
Feature activation-2.32e+00

Pos logit contributions
s+0.201
 sky+0.165
 nowhere+0.158
ls+0.142
pill+0.134
Neg logit contributions
gh-0.306
 som-0.297
 insist-0.297
 compete-0.292
iding-0.288
Token sister
Token ID6621
Feature activation-7.29e+00

Pos logit contributions
s+0.060
 sky+0.048
 twins+0.046
 nowhere+0.045
 living+0.044
Neg logit contributions
gh-0.076
iding-0.074
 som-0.073
heit-0.071
 accompl-0.070
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
s+0.188
 sky+0.159
 nowhere+0.153
ls+0.141
pill+0.133
Neg logit contributions
gh-0.228
 insist-0.221
 som-0.220
 compete-0.217
iding-0.212
Token They
Token ID1119
Feature activation+6.09e-01

Pos logit contributions
s+0.003
 sky+0.002
 nowhere+0.002
 twins+0.002
 living+0.002
Neg logit contributions
gh-0.005
 som-0.005
iding-0.005
heit-0.005
 insist-0.005
Token live
Token ID2107
Feature activation-1.01e-01

Pos logit contributions
gh+0.020
 som+0.018
iding+0.018
 accompl+0.018
heit+0.018
Neg logit contributions
s-0.016
 sky-0.014
 living-0.013
 twins-0.012
 nowhere-0.012
Token<|endoftext|>
Token ID50256
Feature activation-5.87e+00

Pos logit contributions
 insist+0.006
gh+0.006
 compete+0.006
 som+0.006
iding+0.005
Neg logit contributions
s-0.004
 nowhere-0.003
 sky-0.003
ls-0.003
 pieces-0.003
TokenTom
Token ID13787
Feature activation-4.22e-02

Pos logit contributions
s+0.090
 nowhere+0.069
armac+0.063
ls+0.060
 sky+0.060
Neg logit contributions
gh-0.226
 compete-0.214
 som-0.206
 insist-0.204
iding-0.201
Token and
Token ID290
Feature activation-1.45e+00

Pos logit contributions
s+0.001
 sky+0.001
 nowhere+0.001
ls+0.000
 living+0.000
Neg logit contributions
gh-0.002
 som-0.002
 compete-0.002
 insist-0.002
iding-0.002
Token Lily
Token ID20037
Feature activation-8.30e-01

Pos logit contributions
s+0.039
 sky+0.033
 nowhere+0.032
ls+0.029
 living+0.028
Neg logit contributions
gh-0.044
 insist-0.043
 som-0.043
 compete-0.042
iding-0.041
Token are
Token ID389
Feature activation-1.68e+00

Pos logit contributions
s+0.022
 sky+0.018
 nowhere+0.017
 living+0.016
ls+0.016
Neg logit contributions
gh-0.027
 som-0.025
iding-0.025
 compete-0.024
 accompl-0.024
Token brother
Token ID3956
Feature activation-8.92e+00

Pos logit contributions
s+0.048
 sky+0.042
 nowhere+0.039
pill+0.038
ls+0.037
Neg logit contributions
gh-0.048
 insist-0.046
iding-0.044
 compete-0.044
 som-0.043
Token and
Token ID290
Feature activation-2.42e+00

Pos logit contributions
s+0.206
 sky+0.183
 nowhere+0.177
ls+0.157
pill+0.157
Neg logit contributions
gh-0.276
 som-0.269
 insist-0.269
 compete-0.263
iding-0.260
Token sister
Token ID6621
Feature activation-7.10e+00

Pos logit contributions
s+0.057
 sky+0.044
 twins+0.042
 nowhere+0.041
 living+0.041
Neg logit contributions
gh-0.085
iding-0.083
 som-0.081
 accompl-0.078
heit-0.078
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
s+0.190
 sky+0.169
 nowhere+0.165
ls+0.152
pill+0.148
Neg logit contributions
gh-0.203
 insist-0.202
 som-0.196
 compete-0.194
iding-0.187
Token They
Token ID1119
Feature activation+4.82e-01

Pos logit contributions
s+0.003
 sky+0.002
 nowhere+0.002
 twins+0.002
 living+0.002
Neg logit contributions
gh-0.006
 som-0.005
heit-0.005
iding-0.005
 insist-0.005
Token like
Token ID588
Feature activation-2.29e+00

Pos logit contributions
gh+0.017
 som+0.016
iding+0.016
 accompl+0.015
heit+0.015
Neg logit contributions
s-0.012
 sky-0.010
 living-0.009
 twins-0.009
 nowhere-0.008
Token Lily
Token ID20037
Feature activation-9.28e-01

Pos logit contributions
s+0.009
 sky+0.006
 nowhere+0.006
ls+0.006
actus+0.005
Neg logit contributions
gh-0.017
 compete-0.017
 som-0.017
 insist-0.017
iding-0.016
Token and
Token ID290
Feature activation+1.34e-01

Pos logit contributions
s+0.020
 sky+0.016
 nowhere+0.015
ls+0.014
pill+0.013
Neg logit contributions
gh-0.033
 insist-0.032
 som-0.032
 compete-0.032
iding-0.031
Token Max
Token ID5436
Feature activation+2.60e-01

Pos logit contributions
gh+0.004
 insist+0.004
 som+0.004
 compete+0.004
iding+0.004
Neg logit contributions
s-0.004
 sky-0.003
 nowhere-0.003
ls-0.003
 living-0.002
Token were
Token ID547
Feature activation-2.06e+00

Pos logit contributions
gh+0.010
iding+0.010
 accompl+0.010
heit+0.010
 som+0.009
Neg logit contributions
s-0.006
 sky-0.004
 nowhere-0.004
 lost-0.003
 twins-0.003
Token normal
Token ID3487
Feature activation-2.75e+00

Pos logit contributions
s+0.061
 sky+0.049
 nowhere+0.047
ls+0.047
pill+0.045
Neg logit contributions
gh-0.059
 som-0.058
 insist-0.057
 compete-0.057
 accompl-0.055
Token brother
Token ID3956
Feature activation-8.90e+00

Pos logit contributions
s+0.059
 sky+0.047
 nowhere+0.044
 twins+0.040
ls+0.040
Neg logit contributions
gh-0.103
 som-0.099
 insist-0.098
 compete-0.097
iding-0.096
Token and
Token ID290
Feature activation-2.03e+00

Pos logit contributions
s+0.183
 sky+0.143
 nowhere+0.135
ls+0.120
 twins+0.115
Neg logit contributions
gh-0.334
 som-0.323
 insist-0.322
 compete-0.318
iding-0.313
Token sister
Token ID6621
Feature activation-6.70e+00

Pos logit contributions
s+0.046
 sky+0.036
 nowhere+0.034
 living+0.034
 twins+0.033
Neg logit contributions
gh-0.074
iding-0.073
 som-0.070
heit-0.070
 compete-0.069
Token again
Token ID757
Feature activation-2.05e+00

Pos logit contributions
s+0.154
 sky+0.117
 nowhere+0.110
 living+0.104
 twins+0.103
Neg logit contributions
gh-0.245
 som-0.235
iding-0.232
heit-0.232
 insist-0.232
Token.
Token ID13
Feature activation-5.92e-02

Pos logit contributions
s+0.037
 living+0.024
 sky+0.021
 twins+0.021
+0.020
Neg logit contributions
heit-0.094
gh-0.093
 boost-0.086
ern-0.086
 som-0.085
Token<|endoftext|>
Token ID50256
Feature activation-5.62e+00

Pos logit contributions
s+0.001
ls+0.001
ons+0.001
 nowhere+0.001
actus+0.001
Neg logit contributions
 insist-0.002
 compete-0.002
gh-0.002
 som-0.001
 agree-0.001
Tokenâ„¢
Token ID8151
Feature activation+3.20e+00

Pos logit contributions
gh+0.097
 insist+0.096
 som+0.094
iding+0.091
 accompl+0.091
Neg logit contributions
s-0.111
 sky-0.092
 nowhere-0.087
ls-0.082
-0.081
Tokens
Token ID82
Feature activation+8.01e-01

Pos logit contributions
gh+0.133
 som+0.131
 insist+0.130
 compete+0.129
iding+0.127
Neg logit contributions
s-0.052
 sky-0.036
 nowhere-0.033
ls-0.029
 living-0.025
Token like
Token ID588
Feature activation-2.55e+00

Pos logit contributions
gh+0.030
 accompl+0.029
iding+0.029
 som+0.029
 compete+0.028
Neg logit contributions
s-0.017
 sky-0.014
 living-0.012
 twins-0.011
 nowhere-0.011
Token that
Token ID326
Feature activation-2.29e+00

Pos logit contributions
s+0.038
 sky+0.034
 she+0.029
 nowhere+0.029
 living+0.028
Neg logit contributions
iding-0.107
gh-0.103
 insist-0.103
oving-0.102
rated-0.101
Token.
Token ID13
Feature activation+7.05e-01

Pos logit contributions
s+0.054
 sky+0.042
 she+0.035
 living+0.034
 twins+0.033
Neg logit contributions
 accompl-0.084
gh-0.084
iding-0.083
icious-0.080
heit-0.079
Tokenâ
Token ID22940
Feature activation+7.82e+00

Pos logit contributions
gh+0.029
 som+0.027
 insist+0.026
heit+0.025
iding+0.025
Neg logit contributions
s-0.014
 sky-0.012
-0.009
 twins-0.009
pill-0.009
Token€
Token ID26391
Feature activation+4.21e+00

Pos logit contributions
 som+0.158
gh+0.154
 paddle+0.139
iding+0.138
 insist+0.136
Neg logit contributions
s-0.283
 sky-0.262
-0.236
 nowhere-0.222
actus-0.218
Token
Token ID198
Feature activation-6.36e-01

Pos logit contributions
gh+0.123
 som+0.118
 insist+0.118
 compete+0.116
iding+0.113
Neg logit contributions
s-0.119
 sky-0.101
 nowhere-0.098
ls-0.091
 living-0.087
Token
Token ID198
Feature activation+3.05e-01

Pos logit contributions
s+0.007
 sky+0.004
 nowhere+0.003
ls+0.002
 living+0.002
Neg logit contributions
gh-0.030
 insist-0.029
 som-0.029
 compete-0.029
iding-0.029
TokenJane
Token ID41083
Feature activation+5.24e-01

Pos logit contributions
gh+0.010
 som+0.010
 insist+0.009
 compete+0.009
iding+0.009
Neg logit contributions
s-0.008
 sky-0.007
 nowhere-0.006
 living-0.006
Someone-0.005
Token was
Token ID373
Feature activation-3.17e-01

Pos logit contributions
gh+0.020
 som+0.019
iding+0.019
 compete+0.019
 accompl+0.019
Neg logit contributions
s-0.011
 sky-0.008
 nowhere-0.007
ls-0.006
 living-0.006
Token a
Token ID257
Feature activation+2.71e-01

Pos logit contributions
gh+0.079
 som+0.078
 insist+0.077
 compete+0.076
iding+0.074
Neg logit contributions
s-0.046
 sky-0.036
 nowhere-0.034
ls-0.030
 living-0.029
Token few
Token ID1178
Feature activation-9.85e-01

Pos logit contributions
gh+0.009
 accompl+0.009
 compete+0.009
oving+0.008
icious+0.008
Neg logit contributions
s-0.007
 sky-0.006
 pieces-0.005
 nowhere-0.005
ls-0.005
Token shells
Token ID19679
Feature activation+1.06e+00

Pos logit contributions
s+0.024
 sky+0.020
ls+0.019
 nowhere+0.019
 pieces+0.018
Neg logit contributions
gh-0.034
 insist-0.033
 compete-0.032
iding-0.032
 som-0.032
Token and
Token ID290
Feature activation-1.22e+00

Pos logit contributions
gh+0.042
 som+0.040
 insist+0.040
 compete+0.040
iding+0.039
Neg logit contributions
s-0.020
 sky-0.015
 nowhere-0.014
ls-0.012
 living-0.011
Token some
Token ID617
Feature activation-1.03e+00

Pos logit contributions
s+0.036
 sky+0.030
 nowhere+0.029
ls+0.027
 pieces+0.027
Neg logit contributions
gh-0.036
iding-0.034
 insist-0.034
 compete-0.034
 som-0.033
Token seaw
Token ID32085
Feature activation+9.50e+00

Pos logit contributions
s+0.026
 sky+0.022
 nowhere+0.019
 pieces+0.019
ls+0.019
Neg logit contributions
gh-0.035
 insist-0.035
iding-0.034
 compete-0.033
 accompl-0.033
Tokeneed
Token ID2308
Feature activation+4.75e+00

Pos logit contributions
 insist+0.274
 accompl+0.252
 compete+0.250
 argue+0.237
rated+0.235
Neg logit contributions
s-0.313
ls-0.248
 sky-0.242
actus-0.238
 pieces-0.225
Token and
Token ID290
Feature activation-8.23e-01

Pos logit contributions
gh+0.186
 insist+0.181
 som+0.178
 compete+0.178
 accompl+0.175
Neg logit contributions
s-0.099
 sky-0.071
 nowhere-0.063
ls-0.063
 living-0.057
Token built
Token ID3170
Feature activation+2.34e+00

Pos logit contributions
s+0.023
 sky+0.019
 nowhere+0.019
 pieces+0.018
ls+0.017
Neg logit contributions
gh-0.026
iding-0.025
 insist-0.024
 compete-0.024
 accompl-0.024
Token a
Token ID257
Feature activation+6.44e-01

Pos logit contributions
gh+0.093
 insist+0.093
iding+0.090
 compete+0.090
 som+0.088
Neg logit contributions
s-0.041
 sky-0.033
 nowhere-0.028
ls-0.026
 pieces-0.025
Token castle
Token ID16669
Feature activation+1.29e+00

Pos logit contributions
iding+0.022
ern+0.022
gh+0.021
 accompl+0.021
 compete+0.021
Neg logit contributions
s-0.016
 sky-0.013
 living-0.012
 pieces-0.011
ls-0.011
Token!
Token ID0
Feature activation+1.40e+00

Pos logit contributions
s+0.015
 sky+0.010
 nowhere+0.010
 living+0.010
 twins+0.010
Neg logit contributions
gh-0.022
 som-0.022
 accompl-0.021
 insist-0.021
 compete-0.021
Token Please
Token ID4222
Feature activation+4.14e+00

Pos logit contributions
gh+0.050
 som+0.048
 insist+0.047
 compete+0.046
iding+0.045
Neg logit contributions
s-0.032
 sky-0.027
 nowhere-0.025
 living-0.022
 twins-0.022
Token help
Token ID1037
Feature activation+4.17e+00

Pos logit contributions
 accompl+0.118
 som+0.117
gh+0.116
heit+0.108
oving+0.106
Neg logit contributions
s-0.118
 sky-0.103
 upon-0.095
 twins-0.092
 was-0.092
Token me
Token ID502
Feature activation+3.48e+00

Pos logit contributions
 accompl+0.158
gh+0.155
 som+0.153
 compete+0.149
 insist+0.148
Neg logit contributions
s-0.085
 sky-0.061
 living-0.058
 nowhere-0.056
 twins-0.055
Token!
Token ID0
Feature activation+1.05e+00

Pos logit contributions
gh+0.118
Deal+0.114
heit+0.113
 accompl+0.113
 som+0.110
Neg logit contributions
s-0.082
 sky-0.066
 of-0.065
 living-0.064
 curtains-0.061
Tokenâ
Token ID22940
Feature activation+7.73e+00

Pos logit contributions
gh+0.041
 som+0.039
 insist+0.037
iding+0.037
heit+0.037
Neg logit contributions
s-0.022
 sky-0.018
 nowhere-0.016
 living-0.016
-0.015
Token€
Token ID26391
Feature activation+4.43e+00

Pos logit contributions
 som+0.170
gh+0.152
heit+0.149
 paddle+0.146
iding+0.142
Neg logit contributions
s-0.252
 sky-0.247
 nowhere-0.230
-0.217
 living-0.215
Token
Token ID198
Feature activation-4.53e-01

Pos logit contributions
gh+0.115
 som+0.110
 insist+0.109
 compete+0.109
iding+0.104
Neg logit contributions
s-0.139
 sky-0.120
 nowhere-0.117
ls-0.112
 living-0.105
Token
Token ID198
Feature activation+4.53e-01

Pos logit contributions
s+0.006
 sky+0.004
 nowhere+0.004
ls+0.003
 twins+0.003
Neg logit contributions
gh-0.020
 som-0.019
 insist-0.019
 compete-0.019
iding-0.019
TokenThe
Token ID464
Feature activation+2.87e-01

Pos logit contributions
gh+0.018
 som+0.017
 insist+0.017
 compete+0.017
heit+0.017
Neg logit contributions
s-0.009
 sky-0.006
 nowhere-0.006
 living-0.005
Someone-0.005
Token machine
Token ID4572
Feature activation+3.10e+00

Pos logit contributions
gh+0.009
 insist+0.009
 som+0.009
 compete+0.009
iding+0.008
Neg logit contributions
s-0.008
 sky-0.006
 nowhere-0.006
ls-0.006
pill-0.005
Token she
Token ID673
Feature activation+1.02e+00

Pos logit contributions
s+0.005
 sky+0.004
pill+0.003
actus+0.003
ls+0.003
Neg logit contributions
 som-0.008
gh-0.008
 insist-0.008
 compete-0.008
 accompl-0.008
Token had
Token ID550
Feature activation-1.27e+00

Pos logit contributions
 insist+0.027
gh+0.026
 compete+0.024
 wait+0.023
 som+0.023
Neg logit contributions
s-0.028
 sky-0.027
pill-0.026
ls-0.025
armac-0.024
Token to
Token ID284
Feature activation+2.78e+00

Pos logit contributions
s+0.027
 sky+0.022
 nowhere+0.021
ls+0.019
 living+0.017
Neg logit contributions
gh-0.046
 som-0.045
 insist-0.045
 compete-0.044
iding-0.043
Token help
Token ID1037
Feature activation+2.41e+00

Pos logit contributions
 accompl+0.099
 seventeen+0.094
heit+0.092
iding+0.091
gh+0.090
Neg logit contributions
 and-0.049
 lost-0.049
 of-0.046
 the-0.043
s-0.042
Token the
Token ID262
Feature activation-1.47e+00

Pos logit contributions
gh+0.097
 som+0.094
 insist+0.094
 compete+0.093
iding+0.092
Neg logit contributions
s-0.043
 sky-0.032
 nowhere-0.030
ls-0.026
 living-0.024
Token sw
Token ID1509
Feature activation+1.05e+01

Pos logit contributions
s+0.053
 sky+0.046
 nowhere+0.046
ls+0.043
pill+0.043
Neg logit contributions
gh-0.031
 insist-0.030
 som-0.030
 compete-0.029
iding-0.028
Tokenan
Token ID272
Feature activation-2.22e+00

Pos logit contributions
gh+0.343
 insist+0.332
 som+0.328
 compete+0.327
 accompl+0.325
Neg logit contributions
s-0.268
 sky-0.213
ls-0.194
 nowhere-0.194
 twins-0.179
Token,
Token ID11
Feature activation-6.84e-01

Pos logit contributions
s+0.058
 sky+0.041
 living+0.038
ls+0.038
 nowhere+0.037
Neg logit contributions
gh-0.078
heit-0.073
 som-0.072
 accompl-0.072
 compete-0.070
Token so
Token ID523
Feature activation+3.78e-01

Pos logit contributions
s+0.018
 sky+0.015
 nowhere+0.015
ls+0.013
 living+0.013
Neg logit contributions
gh-0.022
 som-0.020
 insist-0.020
 compete-0.020
iding-0.020
Token she
Token ID673
Feature activation+7.36e-01

Pos logit contributions
 som+0.015
gh+0.015
 insist+0.015
 compete+0.014
 wait+0.014
Neg logit contributions
s-0.006
 sky-0.004
 nowhere-0.004
pill-0.004
actus-0.003
Token carefully
Token ID7773
Feature activation+2.72e+00

Pos logit contributions
gh+0.023
iding+0.022
 som+0.022
 compete+0.021
 accompl+0.021
Neg logit contributions
s-0.021
 nowhere-0.017
 sky-0.017
ls-0.016
 pieces-0.015
Tokenspeaking
Token ID25159
Feature activation+4.58e+00

Pos logit contributions
gh+0.213
 insist+0.209
 som+0.208
 compete+0.203
heit+0.200
Neg logit contributions
s-0.166
 sky-0.128
 nowhere-0.120
ls-0.114
pill-0.107
Token friend
Token ID1545
Feature activation-2.79e+00

Pos logit contributions
 insist+0.171
gh+0.170
 som+0.167
heit+0.166
 accompl+0.165
Neg logit contributions
s-0.093
 sky-0.084
 twins-0.073
 nowhere-0.068
 living-0.063
Token said
Token ID531
Feature activation+2.97e-01

Pos logit contributions
s+0.068
 sky+0.050
 nowhere+0.044
 was+0.043
 of+0.043
Neg logit contributions
gh-0.103
 accompl-0.099
heit-0.098
iding-0.097
 som-0.096
Token,
Token ID11
Feature activation+1.34e-01

Pos logit contributions
icious+0.012
rated+0.011
 insist+0.011
heit+0.011
iding+0.011
Neg logit contributions
s-0.006
 she-0.005
 sky-0.004
 nowhere-0.004
 living-0.004
Token "
Token ID366
Feature activation+8.48e-03

Pos logit contributions
gh+0.006
heit+0.005
 insist+0.005
 appetite+0.005
 som+0.005
Neg logit contributions
s-0.002
 sky-0.002
-0.002
 she-0.002
 nowhere-0.002
TokenSpe
Token ID5248
Feature activation+8.69e+00

Pos logit contributions
gh+0.000
 som+0.000
 insist+0.000
iding+0.000
heit+0.000
Neg logit contributions
s-0.000
 sky-0.000
 nowhere-0.000
pill-0.000
Someone-0.000
Tokenak
Token ID461
Feature activation+2.13e+00

Pos logit contributions
gh+0.169
 insist+0.169
 accompl+0.163
 som+0.162
 appetite+0.159
Neg logit contributions
s-0.328
 nowhere-0.257
ls-0.255
 sky-0.242
pill-0.238
Token slow
Token ID3105
Feature activation+3.13e+00

Pos logit contributions
gh+0.088
 accompl+0.087
 insist+0.083
iding+0.083
 compete+0.083
Neg logit contributions
s-0.042
 sky-0.026
ls-0.021
 living-0.020
 twins-0.019
Token and
Token ID290
Feature activation-1.93e-01

Pos logit contributions
gh+0.113
 accompl+0.110
icious+0.106
 insist+0.104
 compete+0.103
Neg logit contributions
s-0.084
 sky-0.058
ls-0.051
 pieces-0.051
 living-0.047
Token I
Token ID314
Feature activation+2.47e+00

Pos logit contributions
s+0.005
 sky+0.004
 living+0.004
 she+0.004
 nowhere+0.004
Neg logit contributions
gh-0.006
iding-0.006
immer-0.006
ern-0.005
icious-0.005
Token will
Token ID481
Feature activation+2.22e+00

Pos logit contributions
gh+0.084
 accompl+0.081
iding+0.076
 som+0.076
heit+0.075
Neg logit contributions
s-0.070
 upon-0.047
 lost-0.046
 sky-0.046
 was-0.046
Token fast
Token ID3049
Feature activation+3.64e-02

Pos logit contributions
gh+0.037
 som+0.035
 insist+0.035
 compete+0.034
iding+0.034
Neg logit contributions
s-0.034
 sky-0.028
 nowhere-0.027
ls-0.025
 living-0.024
Token."
Token ID526
Feature activation-1.70e+00

Pos logit contributions
gh+0.001
 som+0.001
 insist+0.001
iding+0.001
 accompl+0.001
Neg logit contributions
s-0.001
 sky-0.001
 nowhere-0.001
 living-0.000
 pieces-0.000
Token
Token ID198
Feature activation-5.55e-01

Pos logit contributions
s+0.028
 sky+0.021
 nowhere+0.019
ls+0.015
 twins+0.015
Neg logit contributions
gh-0.072
 som-0.069
 insist-0.069
iding-0.068
 compete-0.068
Token
Token ID198
Feature activation+1.59e-01

Pos logit contributions
s+0.008
 sky+0.006
 nowhere+0.005
ls+0.004
 living+0.004
Neg logit contributions
gh-0.024
 insist-0.023
 som-0.023
 compete-0.023
iding-0.022
TokenSam
Token ID16305
Feature activation+3.29e+00

Pos logit contributions
gh+0.006
 som+0.005
 insist+0.005
 compete+0.005
 accompl+0.005
Neg logit contributions
s-0.004
 sky-0.003
 nowhere-0.003
Someone-0.003
 twins-0.002
Token came
Token ID1625
Feature activation+1.96e+00

Pos logit contributions
gh+0.134
 accompl+0.126
 som+0.126
iding+0.126
 compete+0.123
Neg logit contributions
s-0.069
 sky-0.051
 nowhere-0.044
 living-0.041
 was-0.038
Token to
Token ID284
Feature activation+7.52e-01

Pos logit contributions
gh+0.064
 som+0.061
 insist+0.061
 compete+0.060
iding+0.059
Neg logit contributions
s-0.050
 sky-0.041
 nowhere-0.040
ls-0.036
 living-0.035
Token the
Token ID262
Feature activation-1.84e+00

Pos logit contributions
gh+0.033
iding+0.031
 som+0.031
heit+0.030
 insist+0.030
Neg logit contributions
s-0.011
 nowhere-0.009
 sky-0.008
 living-0.006
 twins-0.006
Token window
Token ID4324
Feature activation-5.83e-01

Pos logit contributions
s+0.041
 sky+0.032
 nowhere+0.031
ls+0.029
pill+0.027
Neg logit contributions
gh-0.065
 insist-0.063
 som-0.063
 compete-0.062
iding-0.060
Token too
Token ID1165
Feature activation-7.46e-01

Pos logit contributions
s+0.010
 sky+0.007
 nowhere+0.007
 living+0.005
 twins+0.005
Neg logit contributions
gh-0.024
 som-0.023
 insist-0.023
 compete-0.023
heit-0.023
Token.
Token ID13
Feature activation+1.11e+00

Pos logit contributions
s+0.019
 sky+0.015
 nowhere+0.014
ls+0.013
 twins+0.013
Neg logit contributions
gh-0.025
 som-0.024
 insist-0.024
 compete-0.024
iding-0.023
TokenIt
Token ID1026
Feature activation+7.39e-01

Pos logit contributions
gh+0.010
 insist+0.010
 som+0.010
iding+0.009
 compete+0.009
Neg logit contributions
s-0.006
 sky-0.005
 nowhere-0.005
pill-0.004
 living-0.004
Token looks
Token ID3073
Feature activation+1.48e+00

Pos logit contributions
gh+0.030
 insist+0.030
 som+0.029
 compete+0.029
iding+0.029
Neg logit contributions
s-0.012
 sky-0.009
 nowhere-0.009
ls-0.007
pill-0.006
Token like
Token ID588
Feature activation-3.92e+00

Pos logit contributions
gh+0.050
iding+0.050
 compete+0.048
 insist+0.047
ern+0.047
Neg logit contributions
s-0.035
 nowhere-0.029
 sky-0.028
 everywhere-0.026
 upon-0.026
Token you
Token ID345
Feature activation+1.36e+00

Pos logit contributions
s+0.061
 sky+0.053
 nowhere+0.051
 living+0.042
 twins+0.041
Neg logit contributions
gh-0.159
iding-0.157
 insist-0.157
 som-0.151
 compete-0.151
Token are
Token ID389
Feature activation-1.30e+00

Pos logit contributions
gh+0.044
 som+0.043
 insist+0.042
iding+0.041
 compete+0.041
Neg logit contributions
s-0.035
 sky-0.029
 nowhere-0.027
 living-0.025
ls-0.025
Token going
Token ID1016
Feature activation+6.01e+00

Pos logit contributions
s+0.030
 sky+0.026
 nowhere+0.025
 twins+0.023
 living+0.023
Neg logit contributions
gh-0.044
 som-0.044
 insist-0.043
iding-0.042
heit-0.042
Token to
Token ID284
Feature activation+1.32e+00

Pos logit contributions
gh+0.253
 som+0.250
 insist+0.248
iding+0.248
 accompl+0.244
Neg logit contributions
s-0.099
 sky-0.076
 nowhere-0.068
ls-0.054
 living-0.053
Token have
Token ID423
Feature activation-3.26e+00

Pos logit contributions
iding+0.045
gh+0.043
heit+0.041
oving+0.040
Deal+0.040
Neg logit contributions
 sky-0.029
s-0.028
 nowhere-0.025
 twins-0.024
 living-0.023
Token a
Token ID257
Feature activation+5.78e-01

Pos logit contributions
s+0.067
 nowhere+0.054
 sky+0.054
 living+0.045
ls+0.044
Neg logit contributions
gh-0.119
 insist-0.119
iding-0.118
 compete-0.115
 som-0.115
Token very
Token ID845
Feature activation+4.35e+00

Pos logit contributions
iding+0.018
ern+0.017
gh+0.017
 som+0.017
 accompl+0.016
Neg logit contributions
s-0.016
 sky-0.014
 nowhere-0.013
 living-0.012
 twins-0.012
Token special
Token ID2041
Feature activation+2.01e+00

Pos logit contributions
gh+0.157
iding+0.154
 som+0.153
 accompl+0.150
 compete+0.149
Neg logit contributions
s-0.096
 sky-0.073
ls-0.071
 nowhere-0.063
 twins-0.060
Token loved
Token ID6151
Feature activation-3.44e+00

Pos logit contributions
gh+0.026
 insist+0.025
 som+0.025
 compete+0.024
 wait+0.023
Neg logit contributions
s-0.019
 sky-0.017
 nowhere-0.015
ls-0.015
pill-0.014
Token to
Token ID284
Feature activation+1.58e+00

Pos logit contributions
s+0.074
 sky+0.059
 nowhere+0.056
ls+0.052
pill+0.047
Neg logit contributions
gh-0.125
 som-0.121
 insist-0.120
 compete-0.119
iding-0.115
Token look
Token ID804
Feature activation-7.75e-01

Pos logit contributions
 accompl+0.050
heit+0.049
gh+0.048
iding+0.048
oving+0.045
Neg logit contributions
s-0.041
 sky-0.038
 she-0.033
 flowers-0.032
 stars-0.031
Token at
Token ID379
Feature activation-9.26e-01

Pos logit contributions
s+0.022
 sky+0.018
 nowhere+0.018
ls+0.017
 living+0.016
Neg logit contributions
gh-0.023
 som-0.022
 insist-0.022
 compete-0.022
iding-0.021
Token.
Token ID13
Feature activation-4.20e-01

Pos logit contributions
s+0.026
pill+0.023
Someone+0.023
ls+0.021
armac+0.021
Neg logit contributions
 som-0.021
gh-0.021
 insist-0.020
 compete-0.019
et-0.019
Token One
Token ID1881
Feature activation+2.16e+00

Pos logit contributions
s+0.013
 nowhere+0.011
ls+0.011
 sky+0.011
 pieces+0.010
Neg logit contributions
 insist-0.010
 som-0.010
 compete-0.010
gh-0.010
 boost-0.009
Token day
Token ID1110
Feature activation+1.43e-01

Pos logit contributions
 insist+0.040
gh+0.039
 wait+0.037
 exercise+0.035
 spend+0.033
Neg logit contributions
s-0.078
pill-0.076
ls-0.074
 nowhere-0.069
 sky-0.067
Token,
Token ID11
Feature activation+5.78e-01

Pos logit contributions
gh+0.003
 som+0.003
 insist+0.002
 compete+0.002
iding+0.002
Neg logit contributions
 nowhere-0.005
 sky-0.005
s-0.005
armac-0.005
pill-0.005
Token Lily
Token ID20037
Feature activation-3.32e-01

Pos logit contributions
 wait+0.016
 som+0.016
gh+0.016
 insist+0.016
 exercise+0.015
Neg logit contributions
s-0.014
armac-0.014
pill-0.014
actus-0.013
 sky-0.013
Token's
Token ID338
Feature activation+2.07e+00

Pos logit contributions
s+0.008
pill+0.008
 sky+0.008
ls+0.008
 nowhere+0.008
Neg logit contributions
 insist-0.009
gh-0.008
 wait-0.008
 spend-0.008
 gob-0.007
Token little
Token ID1310
Feature activation-2.63e+00

Pos logit contributions
gh+0.058
 insist+0.056
 wait+0.053
 som+0.053
 deal+0.053
Neg logit contributions
s-0.059
pill-0.050
ls-0.048
 nowhere-0.048
 sky-0.045
Token went
Token ID1816
Feature activation+2.84e+00

Pos logit contributions
s+0.023
 sky+0.018
 nowhere+0.017
ls+0.015
 living+0.014
Neg logit contributions
gh-0.044
 insist-0.042
 som-0.042
 compete-0.041
iding-0.041
Token around
Token ID1088
Feature activation-3.02e+00

Pos logit contributions
gh+0.088
 insist+0.085
 som+0.084
iding+0.083
 compete+0.082
Neg logit contributions
s-0.078
 sky-0.066
 nowhere-0.062
ls-0.057
 living-0.055
Token and
Token ID290
Feature activation-2.51e+00

Pos logit contributions
s+0.058
 sky+0.047
 nowhere+0.044
 living+0.038
ls+0.036
Neg logit contributions
gh-0.116
 insist-0.112
 som-0.111
iding-0.110
 compete-0.109
Token around
Token ID1088
Feature activation-1.81e+00

Pos logit contributions
s+0.050
 sky+0.039
 nowhere+0.036
 living+0.031
ls+0.031
Neg logit contributions
gh-0.098
iding-0.094
 insist-0.092
 som-0.092
 compete-0.091
Token the
Token ID262
Feature activation-1.13e+00

Pos logit contributions
s+0.039
 sky+0.032
 nowhere+0.030
 living+0.027
ls+0.025
Neg logit contributions
gh-0.066
 insist-0.063
 som-0.062
iding-0.062
 compete-0.062
Token thick
Token ID6546
Feature activation+5.08e+00

Pos logit contributions
s+0.032
 nowhere+0.026
pill+0.026
ls+0.025
 sky+0.024
Neg logit contributions
 som-0.032
 compete-0.031
gh-0.031
 insist-0.031
 wait-0.029
Token stone
Token ID7815
Feature activation+3.02e-01

Pos logit contributions
gh+0.159
 som+0.157
 compete+0.154
 insist+0.152
iding+0.147
Neg logit contributions
s-0.130
 nowhere-0.104
 sky-0.100
ls-0.097
pill-0.093
Token walls
Token ID7714
Feature activation-1.57e+00

Pos logit contributions
gh+0.010
 insist+0.010
 som+0.010
 compete+0.010
heit+0.010
Neg logit contributions
s-0.007
 sky-0.006
 nowhere-0.005
 living-0.005
ls-0.005
Token.
Token ID13
Feature activation+6.99e-01

Pos logit contributions
s+0.039
 sky+0.032
 nowhere+0.031
ls+0.028
 twins+0.027
Neg logit contributions
gh-0.052
 som-0.050
 insist-0.049
 compete-0.049
iding-0.048
Token Everyone
Token ID11075
Feature activation-3.65e+00

Pos logit contributions
gh+0.025
 som+0.024
 insist+0.024
 compete+0.024
iding+0.023
Neg logit contributions
s-0.015
 sky-0.012
 nowhere-0.012
ls-0.011
 twins-0.010
Token was
Token ID373
Feature activation-1.02e+00

Pos logit contributions
s+0.073
 sky+0.064
 nowhere+0.059
pill+0.057
ls+0.055
Neg logit contributions
gh-0.125
 som-0.125
 insist-0.125
 compete-0.124
iding-0.119
Token found
Token ID1043
Feature activation-1.17e+00

Pos logit contributions
gh+0.094
 som+0.092
 insist+0.092
 compete+0.091
iding+0.090
Neg logit contributions
s-0.036
 sky-0.026
 nowhere-0.024
ls-0.021
 living-0.019
Token them
Token ID606
Feature activation-1.27e+00

Pos logit contributions
s+0.026
 sky+0.021
 nowhere+0.019
ls+0.018
pill+0.017
Neg logit contributions
gh-0.042
 som-0.040
 insist-0.040
 compete-0.039
iding-0.038
Token.
Token ID13
Feature activation+4.01e-01

Pos logit contributions
s+0.028
 nowhere+0.021
 sky+0.020
ls+0.018
 living+0.018
Neg logit contributions
gh-0.047
 som-0.047
 compete-0.047
 insist-0.046
heit-0.045
Token
Token ID198
Feature activation-4.19e-01

Pos logit contributions
gh+0.015
 som+0.014
 insist+0.014
 compete+0.014
iding+0.014
Neg logit contributions
s-0.008
 sky-0.006
 nowhere-0.006
ls-0.006
 living-0.005
Token
Token ID198
Feature activation+4.70e-01

Pos logit contributions
s+0.007
 sky+0.006
 nowhere+0.005
pill+0.005
ls+0.005
Neg logit contributions
gh-0.016
 som-0.015
 insist-0.015
iding-0.015
 compete-0.015
TokenThey
Token ID2990
Feature activation+1.91e+00

Pos logit contributions
gh+0.014
 som+0.014
 insist+0.014
 compete+0.014
iding+0.013
Neg logit contributions
s-0.013
 sky-0.011
 nowhere-0.010
ls-0.010
 living-0.009
Token woke
Token ID19092
Feature activation+4.58e-01

Pos logit contributions
gh+0.064
iding+0.061
 som+0.060
 compete+0.060
 insist+0.060
Neg logit contributions
s-0.048
 sky-0.039
 nowhere-0.039
ls-0.034
 twins-0.033
Token up
Token ID510
Feature activation-2.52e+00

Pos logit contributions
gh+0.016
 som+0.015
 insist+0.015
 compete+0.015
iding+0.015
Neg logit contributions
s-0.010
 sky-0.009
 nowhere-0.008
pill-0.008
 living-0.007
Token and
Token ID290
Feature activation-1.95e+00

Pos logit contributions
s+0.050
 sky+0.040
 nowhere+0.038
pill+0.036
ls+0.034
Neg logit contributions
gh-0.091
 som-0.090
 insist-0.089
 compete-0.087
iding-0.086
Token saw
Token ID2497
Feature activation-2.27e+00

Pos logit contributions
s+0.049
 sky+0.041
 nowhere+0.039
ls+0.036
pill+0.035
Neg logit contributions
gh-0.063
 insist-0.061
 som-0.061
 compete-0.060
iding-0.058
Token the
Token ID262
Feature activation-1.59e+00

Pos logit contributions
s+0.061
 sky+0.048
pill+0.047
actus+0.047
 nowhere+0.045
Neg logit contributions
 som-0.064
 compete-0.059
gh-0.058
 insist-0.058
 thank-0.057
Token.
Token ID13
Feature activation-4.82e-02

Pos logit contributions
s+0.017
 sky+0.014
 nowhere+0.013
pill+0.013
ls+0.013
Neg logit contributions
gh-0.020
 insist-0.019
 compete-0.019
 som-0.019
 wait-0.019
Token She
Token ID1375
Feature activation+1.56e-01

Pos logit contributions
s+0.001
ls+0.001
 nowhere+0.001
 pieces+0.001
 sky+0.001
Neg logit contributions
 compete-0.002
 insist-0.002
gh-0.002
 som-0.002
 accompl-0.002
Token dreamed
Token ID27947
Feature activation-1.80e-01

Pos logit contributions
 som+0.004
 insist+0.004
gh+0.004
 compete+0.004
 wait+0.004
Neg logit contributions
s-0.004
ls-0.004
 sky-0.004
eddy-0.003
 nowhere-0.003
Token of
Token ID286
Feature activation-1.06e+00

Pos logit contributions
s+0.004
 nowhere+0.003
armac+0.002
 sky+0.002
Our+0.002
Neg logit contributions
gh-0.006
 som-0.006
 compete-0.006
 insist-0.006
iding-0.006
Token being
Token ID852
Feature activation+9.58e-01

Pos logit contributions
s+0.026
 sky+0.020
 nowhere+0.019
ls+0.019
actus+0.017
Neg logit contributions
gh-0.035
 som-0.034
 compete-0.034
 insist-0.033
 accompl-0.032
Token flexible
Token ID12846
Feature activation-1.93e-02

Pos logit contributions
gh+0.030
 som+0.029
 insist+0.028
 compete+0.028
 accompl+0.027
Neg logit contributions
s-0.025
 sky-0.020
 nowhere-0.019
ls-0.018
pill-0.017
Token,
Token ID11
Feature activation-1.25e+00

Pos logit contributions
s+0.000
 sky+0.000
 nowhere+0.000
ls+0.000
 living+0.000
Neg logit contributions
gh-0.001
 som-0.001
 insist-0.001
 compete-0.001
iding-0.001
Token kind
Token ID1611
Feature activation-2.28e+00

Pos logit contributions
s+0.035
 sky+0.027
ls+0.026
 nowhere+0.025
actus+0.025
Neg logit contributions
 som-0.037
gh-0.036
 insist-0.035
 compete-0.035
 accompl-0.033
Token and
Token ID290
Feature activation-2.28e+00

Pos logit contributions
s+0.050
 nowhere+0.042
ls+0.038
 sky+0.036
Someone+0.035
Neg logit contributions
 compete-0.073
gh-0.072
 insist-0.072
 som-0.071
iding-0.069
Token helpful
Token ID7613
Feature activation+7.00e-02

Pos logit contributions
s+0.063
 sky+0.055
 nowhere+0.052
 living+0.050
 twins+0.047
Neg logit contributions
gh-0.070
iding-0.065
 som-0.065
 insist-0.065
 compete-0.063
Token.
Token ID13
Feature activation+5.11e-02

Pos logit contributions
gh+0.002
 insist+0.002
 som+0.002
 compete+0.002
iding+0.002
Neg logit contributions
s-0.002
 sky-0.001
 nowhere-0.001
ls-0.001
pill-0.001
Token
Token ID198
Feature activation-6.61e-01

Pos logit contributions
gh+0.043
 som+0.042
 insist+0.041
 compete+0.041
iding+0.041
Neg logit contributions
s-0.012
 sky-0.008
 nowhere-0.008
ls-0.005
 living-0.005
Token
Token ID198
Feature activation+9.60e-02

Pos logit contributions
s+0.007
 sky+0.004
 nowhere+0.003
ls+0.002
+0.002
Neg logit contributions
 som-0.031
 insist-0.031
gh-0.031
 compete-0.030
iding-0.030
TokenF
Token ID37
Feature activation+1.06e+01

Pos logit contributions
 som+0.003
 appetite+0.003
 insist+0.003
gh+0.003
 deal+0.003
Neg logit contributions
s-0.002
 nowhere-0.002
Someone-0.002
 sky-0.002
-0.002
Tokenritz
Token ID29574
Feature activation+8.65e-01

Pos logit contributions
gh+0.288
 som+0.285
 insist+0.271
 compete+0.268
 boost+0.251
Neg logit contributions
s-0.330
 nowhere-0.276
 sky-0.276
ls-0.253
pill-0.246
Token bark
Token ID21405
Feature activation+4.03e+00

Pos logit contributions
gh+0.031
iding+0.031
 som+0.031
 compete+0.030
 accompl+0.030
Neg logit contributions
s-0.019
 nowhere-0.015
 sky-0.015
ls-0.012
 was-0.012
Tokened
Token ID276
Feature activation-1.92e+00

Pos logit contributions
 insist+0.196
 compete+0.194
 som+0.193
gh+0.192
 deal+0.191
Neg logit contributions
s-0.049
 sky-0.021
 nowhere-0.017
ls-0.015
 gasped-0.005
Token again
Token ID757
Feature activation-1.68e+00

Pos logit contributions
s+0.042
 nowhere+0.027
 sky+0.026
 she+0.024
 and+0.024
Neg logit contributions
gh-0.076
icious-0.075
 som-0.074
heit-0.073
 compete-0.071
Token and
Token ID290
Feature activation-1.56e+00

Pos logit contributions
s+0.030
 sky+0.019
 she+0.017
 and+0.016
+0.015
Neg logit contributions
heit-0.074
gh-0.074
icious-0.071
Deal-0.070
 som-0.069
Token pointed
Token ID6235
Feature activation+2.14e+00

Pos logit contributions
s+0.045
 nowhere+0.036
 sky+0.035
ls+0.032
 she+0.031
Neg logit contributions
gh-0.050
iding-0.047
 som-0.045
 insist-0.044
 compete-0.044
Token at
Token ID379
Feature activation+1.32e+00

Pos logit contributions
gh+0.085
 som+0.080
 insist+0.080
 compete+0.079
 accompl+0.079
Neg logit contributions
s-0.047
 sky-0.032
 nowhere-0.030
ls-0.029
 upon-0.025
Token the
Token ID262
Feature activation-1.66e+00

Pos logit contributions
gh+0.046
 som+0.045
 insist+0.045
 compete+0.045
iding+0.043
Neg logit contributions
s-0.029
 sky-0.023
 nowhere-0.022
ls-0.020
 twins-0.019
Token<|endoftext|>
Token ID50256
Feature activation-5.68e+00

Pos logit contributions
ls+0.004
 nowhere+0.004
ymes+0.003
s+0.003
 pieces+0.003
Neg logit contributions
 insist-0.004
 thank-0.004
 spend-0.004
 som-0.004
 compete-0.004
TokenOnce
Token ID7454
Feature activation-1.73e-01

Pos logit contributions
s+0.113
ls+0.097
pill+0.091
 nowhere+0.086
armac+0.086
Neg logit contributions
gh-0.192
 compete-0.178
 insist-0.172
 som-0.170
iding-0.161
Token there
Token ID612
Feature activation-3.46e-01

Pos logit contributions
pill+0.004
Someone+0.004
Our+0.004
armac+0.004
 sky+0.003
Neg logit contributions
 insist-0.005
gh-0.005
iding-0.005
 spend-0.004
 agree-0.004
Token was
Token ID373
Feature activation-5.82e-01

Pos logit contributions
pill+0.007
s+0.007
ls+0.007
 sky+0.007
armac+0.006
Neg logit contributions
gh-0.012
 insist-0.011
 compete-0.010
 som-0.010
 wait-0.010
Token a
Token ID257
Feature activation-1.18e+00

Pos logit contributions
s+0.018
ls+0.015
actus+0.015
 sky+0.014
armac+0.014
Neg logit contributions
gh-0.014
 exercise-0.014
 wait-0.013
 som-0.013
 insist-0.013
Token horse
Token ID8223
Feature activation-1.96e+00

Pos logit contributions
s+0.021
 sky+0.016
 nowhere+0.014
 twins+0.013
 living+0.013
Neg logit contributions
gh-0.048
 som-0.046
 compete-0.045
 insist-0.045
iding-0.045
Token who
Token ID508
Feature activation-2.56e+00

Pos logit contributions
s+0.059
 sky+0.050
 nowhere+0.049
ls+0.045
 living+0.044
Neg logit contributions
gh-0.054
 som-0.052
 insist-0.052
 compete-0.051
iding-0.050
Token loved
Token ID6151
Feature activation-2.95e+00

Pos logit contributions
s+0.060
 nowhere+0.054
 sky+0.053
ls+0.049
 twins+0.045
Neg logit contributions
gh-0.081
 insist-0.080
 som-0.079
 compete-0.076
 rely-0.071
Token to
Token ID284
Feature activation+1.72e+00

Pos logit contributions
s+0.056
 sky+0.043
 nowhere+0.040
 living+0.035
ls+0.034
Neg logit contributions
gh-0.116
 insist-0.112
iding-0.112
 som-0.111
 compete-0.110
Token listen
Token ID6004
Feature activation-5.50e-01

Pos logit contributions
 accompl+0.055
icious+0.053
bek+0.053
iding+0.051
heit+0.051
Neg logit contributions
s-0.042
 sky-0.042
 she-0.038
 flowers-0.038
 living-0.036
Token.
Token ID13
Feature activation-2.14e-01

Pos logit contributions
s+0.010
 sky+0.006
 living+0.005
 nowhere+0.005
ls+0.005
Neg logit contributions
gh-0.024
 insist-0.023
 compete-0.023
 accompl-0.023
heit-0.022
Token the
Token ID262
Feature activation-1.08e+00

Pos logit contributions
gh+0.071
 insist+0.069
 som+0.068
 compete+0.068
iding+0.068
Neg logit contributions
s-0.027
 sky-0.020
 nowhere-0.019
ls-0.015
 twins-0.014
Token desk
Token ID6915
Feature activation+9.36e-01

Pos logit contributions
s+0.029
 nowhere+0.024
 sky+0.024
pill+0.023
ls+0.022
Neg logit contributions
gh-0.033
 som-0.031
 insist-0.031
 compete-0.029
iding-0.029
Token.
Token ID13
Feature activation+3.36e-02

Pos logit contributions
heit+0.041
gh+0.040
 insist+0.040
 som+0.040
 compete+0.039
Neg logit contributions
s-0.015
 sky-0.011
 nowhere-0.008
 pieces-0.008
 living-0.007
Token But
Token ID887
Feature activation+1.94e+00

Pos logit contributions
gh+0.001
 insist+0.001
iding+0.001
 som+0.001
 compete+0.001
Neg logit contributions
s-0.001
 sky-0.000
 nowhere-0.000
-0.000
ls-0.000
Token,
Token ID11
Feature activation+1.60e+00

Pos logit contributions
gh+0.079
iding+0.078
 insist+0.076
 som+0.076
heit+0.076
Neg logit contributions
s-0.034
 nowhere-0.027
 sky-0.026
 she-0.021
 upon-0.018
Token the
Token ID262
Feature activation+4.08e-01

Pos logit contributions
iding+0.067
gh+0.066
heit+0.064
icious+0.063
 insist+0.063
Neg logit contributions
s-0.025
 nowhere-0.020
 sky-0.019
 she-0.018
 pieces-0.015
Token desk
Token ID6915
Feature activation+1.72e+00

Pos logit contributions
gh+0.014
 som+0.013
 insist+0.013
 compete+0.013
iding+0.013
Neg logit contributions
s-0.010
 sky-0.008
 nowhere-0.008
ls-0.007
 living-0.007
Token was
Token ID373
Feature activation-1.25e+00

Pos logit contributions
gh+0.072
 som+0.071
 insist+0.071
iding+0.071
 compete+0.071
Neg logit contributions
s-0.027
 sky-0.019
 nowhere-0.017
ls-0.015
 pieces-0.013
Token not
Token ID407
Feature activation-3.14e+00

Pos logit contributions
s+0.025
 nowhere+0.025
 sky+0.022
 living+0.019
 pieces+0.018
Neg logit contributions
 compete-0.045
gh-0.045
heit-0.044
iding-0.044
 insist-0.043
Token clean
Token ID3424
Feature activation+2.78e+00

Pos logit contributions
 nowhere+0.060
s+0.059
 pieces+0.055
 twins+0.054
 sky+0.052
Neg logit contributions
heit-0.115
gh-0.113
 compete-0.109
 insist-0.107
 som-0.107
Token.
Token ID13
Feature activation-2.49e-01

Pos logit contributions
gh+0.105
 compete+0.105
 som+0.105
heit+0.104
 insist+0.103
Neg logit contributions
s-0.059
 sky-0.044
 nowhere-0.039
 pieces-0.037
 twins-0.036
Token He
Token ID679
Feature activation+8.08e-01

Pos logit contributions
gh+0.022
 insist+0.021
 som+0.021
iding+0.020
 compete+0.020
Neg logit contributions
s-0.014
 sky-0.011
 nowhere-0.010
 twins-0.009
 living-0.009
Token hugged
Token ID41130
Feature activation-1.38e+00

Pos logit contributions
gh+0.024
 som+0.024
 insist+0.024
 compete+0.023
iding+0.022
Neg logit contributions
s-0.021
 sky-0.018
 nowhere-0.017
ls-0.016
pill-0.016
Token Lily
Token ID20037
Feature activation-4.02e+00

Pos logit contributions
s+0.033
 sky+0.027
 nowhere+0.026
ls+0.023
 living+0.022
Neg logit contributions
gh-0.047
 som-0.045
 insist-0.045
 compete-0.045
iding-0.044
Token and
Token ID290
Feature activation-2.34e+00

Pos logit contributions
s+0.074
 sky+0.059
 nowhere+0.056
ls+0.050
pill+0.047
Neg logit contributions
gh-0.154
 insist-0.150
 som-0.149
 compete-0.147
iding-0.146
Token thanked
Token ID26280
Feature activation-1.06e+00

Pos logit contributions
s+0.058
 sky+0.047
 nowhere+0.045
ls+0.042
 twins+0.040
Neg logit contributions
gh-0.079
 som-0.075
 insist-0.075
iding-0.075
 compete-0.075
Token her
Token ID607
Feature activation-5.96e-01

Pos logit contributions
s+0.018
 sky+0.013
 nowhere+0.013
 twins+0.010
ls+0.010
Neg logit contributions
gh-0.044
iding-0.043
 som-0.042
 insist-0.042
 compete-0.042
Token.
Token ID13
Feature activation+4.64e-01

Pos logit contributions
s+0.014
 sky+0.010
 twins+0.010
 living+0.009
ls+0.009
Neg logit contributions
gh-0.022
heit-0.022
 som-0.022
 insist-0.021
 accompl-0.021
Token He
Token ID679
Feature activation+7.75e-01

Pos logit contributions
gh+0.016
 som+0.015
 insist+0.015
 compete+0.015
iding+0.014
Neg logit contributions
s-0.011
 sky-0.009
 nowhere-0.009
ls-0.008
 twins-0.008
Token put
Token ID1234
Feature activation+1.25e+00

Pos logit contributions
gh+0.022
 insist+0.022
 som+0.022
 compete+0.021
iding+0.020
Neg logit contributions
s-0.021
 sky-0.018
 nowhere-0.018
ls-0.016
pill-0.016
Token on
Token ID319
Feature activation+2.31e+00

Pos logit contributions
gh+0.042
 som+0.040
 insist+0.039
 compete+0.039
 boost+0.038
Neg logit contributions
s-0.029
 sky-0.023
 nowhere-0.022
pill-0.022
ls-0.020
Token the
Token ID262
Feature activation-7.95e-01

Pos logit contributions
gh+0.069
 som+0.066
 insist+0.064
 compete+0.063
iding+0.060
Neg logit contributions
s-0.064
 sky-0.054
 nowhere-0.053
ls-0.049
pill-0.048
Token the
Token ID262
Feature activation-1.24e+00

Pos logit contributions
s+0.040
 sky+0.032
 nowhere+0.031
ls+0.028
 living+0.026
Neg logit contributions
gh-0.068
 som-0.066
 insist-0.066
 compete-0.065
iding-0.064
Token water
Token ID1660
Feature activation+2.52e+00

Pos logit contributions
s+0.031
 sky+0.027
 nowhere+0.025
 twins+0.023
 living+0.023
Neg logit contributions
gh-0.041
 insist-0.039
iding-0.039
 som-0.039
 compete-0.038
Token.
Token ID13
Feature activation+2.66e-01

Pos logit contributions
gh+0.089
 som+0.085
 insist+0.085
 compete+0.084
iding+0.083
Neg logit contributions
s-0.059
 sky-0.048
 nowhere-0.044
ls-0.041
 living-0.040
Token They
Token ID1119
Feature activation+2.79e-01

Pos logit contributions
 insist+0.006
 compete+0.006
 som+0.006
 wait+0.006
 thank+0.006
Neg logit contributions
s-0.007
 nowhere-0.007
ons-0.007
ls-0.007
 pieces-0.007
Token are
Token ID389
Feature activation-2.04e+00

Pos logit contributions
gh+0.008
iding+0.008
 som+0.008
 accompl+0.007
 insist+0.007
Neg logit contributions
s-0.008
 sky-0.007
 nowhere-0.006
ls-0.006
 living-0.006
Token happy
Token ID3772
Feature activation-5.72e+00

Pos logit contributions
s+0.058
 sky+0.047
 nowhere+0.045
pill+0.044
ls+0.043
Neg logit contributions
gh-0.059
 insist-0.058
 som-0.058
 compete-0.056
iding-0.055
Token.
Token ID13
Feature activation-6.75e-01

Pos logit contributions
s+0.157
pill+0.136
 sky+0.135
 nowhere+0.134
armac+0.131
Neg logit contributions
 som-0.142
 compete-0.139
 insist-0.137
 wait-0.135
gh-0.135
Token<|endoftext|>
Token ID50256
Feature activation-5.92e+00

Pos logit contributions
s+0.016
 nowhere+0.015
ls+0.015
ons+0.015
 pieces+0.014
Neg logit contributions
 insist-0.019
 compete-0.018
gh-0.018
 wait-0.018
 som-0.018
TokenS
Token ID50
Feature activation+2.74e+00

Pos logit contributions
s+0.098
 nowhere+0.086
armac+0.077
ls+0.074
pill+0.068
Neg logit contributions
gh-0.209
 compete-0.200
 insist-0.187
 som-0.186
 skate-0.179
Tokenara
Token ID3301
Feature activation-2.18e-01

Pos logit contributions
gh+0.070
 insist+0.064
 wait+0.059
 som+0.059
 spend+0.057
Neg logit contributions
s-0.077
 nowhere-0.076
pill-0.074
 sky-0.071
Someone-0.070
Token liked
Token ID8288
Feature activation-3.15e+00

Pos logit contributions
s+0.005
 nowhere+0.004
 sky+0.004
Someone+0.004
pill+0.004
Neg logit contributions
 insist-0.007
gh-0.007
 compete-0.007
 wait-0.007
 som-0.006
Token and
Token ID290
Feature activation-1.12e-01

Pos logit contributions
gh+0.003
 insist+0.003
 som+0.003
 compete+0.003
 gob+0.003
Neg logit contributions
s-0.002
 sky-0.002
 nowhere-0.002
pill-0.002
ls-0.002
Token Sam
Token ID3409
Feature activation+5.58e-01

Pos logit contributions
s+0.003
 sky+0.003
 nowhere+0.003
 twins+0.002
 living+0.002
Neg logit contributions
gh-0.004
iding-0.003
 som-0.003
 insist-0.003
 compete-0.003
Token were
Token ID547
Feature activation-1.38e+00

Pos logit contributions
gh+0.018
 insist+0.018
 som+0.017
 compete+0.017
iding+0.017
Neg logit contributions
s-0.014
 sky-0.011
 nowhere-0.011
ls-0.010
pill-0.010
Token not
Token ID407
Feature activation-2.32e+00

Pos logit contributions
s+0.036
pill+0.029
 sky+0.029
actus+0.026
ls+0.025
Neg logit contributions
gh-0.043
 insist-0.042
 som-0.041
 compete-0.040
 accompl-0.039
Token happy
Token ID3772
Feature activation-3.94e+00

Pos logit contributions
s+0.044
 nowhere+0.039
 twins+0.037
 sky+0.035
 living+0.034
Neg logit contributions
gh-0.086
 som-0.085
heit-0.083
 insist-0.082
 compete-0.081
Token anymore
Token ID7471
Feature activation-6.68e+00

Pos logit contributions
s+0.091
 sky+0.071
 nowhere+0.069
 twins+0.062
ls+0.060
Neg logit contributions
gh-0.141
heit-0.136
 insist-0.136
 som-0.136
iding-0.134
Token.
Token ID13
Feature activation+6.49e-02

Pos logit contributions
s+0.150
 nowhere+0.112
 sky+0.111
 twins+0.099
 living+0.097
Neg logit contributions
gh-0.245
 insist-0.240
 som-0.237
heit-0.232
 compete-0.231
Token<|endoftext|>
Token ID50256
Feature activation-5.71e+00

Pos logit contributions
gh+0.002
 compete+0.002
 som+0.002
 insist+0.002
 accompl+0.002
Neg logit contributions
s-0.002
pill-0.001
ls-0.001
 nowhere-0.001
 sky-0.001
TokenOnce
Token ID7454
Feature activation-3.48e-01

Pos logit contributions
s+0.093
 nowhere+0.068
ls+0.066
pill+0.061
 sky+0.059
Neg logit contributions
gh-0.221
 compete-0.208
 som-0.201
 insist-0.200
iding-0.192
Token upon
Token ID2402
Feature activation-2.26e+00

Pos logit contributions
pill+0.009
Someone+0.007
Our+0.007
 sky+0.007
armac+0.006
Neg logit contributions
gh-0.011
 insist-0.010
iding-0.010
 agree-0.010
 thank-0.010
Token a
Token ID257
Feature activation+1.05e+00

Pos logit contributions
s+0.077
ls+0.072
pill+0.071
actus+0.069
ays+0.069
Neg logit contributions
gh-0.049
 som-0.044
 wait-0.043
 compete-0.042
 chew-0.041
Token
Token ID198
Feature activation-8.71e-01

Pos logit contributions
s+0.017
 sky+0.013
 nowhere+0.013
ls+0.012
 pieces+0.010
Neg logit contributions
gh-0.042
iding-0.041
 compete-0.041
 insist-0.040
 som-0.040
Token
Token ID198
Feature activation+1.48e-03

Pos logit contributions
s+0.015
 sky+0.011
 nowhere+0.010
ls+0.010
pill+0.008
Neg logit contributions
gh-0.035
 som-0.034
 compete-0.034
 insist-0.033
iding-0.033
TokenThe
Token ID464
Feature activation-1.77e-01

Pos logit contributions
gh+0.000
 som+0.000
 insist+0.000
 compete+0.000
iding+0.000
Neg logit contributions
s-0.000
 sky-0.000
 nowhere-0.000
ls-0.000
 living-0.000
Token End
Token ID5268
Feature activation-5.29e+00

Pos logit contributions
s+0.005
 sky+0.004
 nowhere+0.004
ls+0.004
pill+0.004
Neg logit contributions
gh-0.005
 insist-0.005
 compete-0.005
 som-0.005
 accompl-0.005
Token.
Token ID13
Feature activation+9.61e-01

Pos logit contributions
s+0.128
 sky+0.101
 nowhere+0.098
ls+0.088
 twins+0.085
Neg logit contributions
gh-0.181
 insist-0.176
 som-0.174
 compete-0.172
iding-0.170
Token<|endoftext|>
Token ID50256
Feature activation-5.36e+00

Pos logit contributions
 compete+0.033
gh+0.033
 insist+0.033
iding+0.032
 som+0.032
Neg logit contributions
s-0.019
ls-0.016
 sky-0.014
actus-0.013
 nowhere-0.013
TokenOnce
Token ID7454
Feature activation-2.03e-01

Pos logit contributions
s+0.076
 nowhere+0.056
ls+0.054
 sky+0.046
 blood+0.041
Neg logit contributions
gh-0.213
 compete-0.207
 insist-0.201
 som-0.201
iding-0.197
Token upon
Token ID2402
Feature activation-2.56e+00

Pos logit contributions
pill+0.005
Someone+0.005
Our+0.004
 sky+0.004
armac+0.004
Neg logit contributions
 insist-0.006
gh-0.006
iding-0.006
 spend-0.005
 agree-0.005
Token a
Token ID257
Feature activation+8.35e-01

Pos logit contributions
s+0.077
ls+0.067
 sky+0.061
actus+0.061
ays+0.059
Neg logit contributions
gh-0.072
 som-0.069
 compete-0.066
 insist-0.065
 wait-0.065
Token time
Token ID640
Feature activation+9.62e-01

Pos logit contributions
gh+0.021
 som+0.020
 compete+0.020
 insist+0.020
iding+0.019
Neg logit contributions
s-0.027
 sky-0.023
 nowhere-0.023
ls-0.021
 living-0.021
Token there
Token ID612
Feature activation-4.14e-01

Pos logit contributions
gh+0.023
 compete+0.021
iding+0.021
 insist+0.020
 som+0.020
Neg logit contributions
s-0.031
 sky-0.029
 nowhere-0.027
actus-0.027
pill-0.027
Tokenipped
Token ID3949
Feature activation+2.17e+00

Pos logit contributions
 insist+0.214
 som+0.206
 compete+0.200
gh+0.199
rated+0.193
Neg logit contributions
s-0.165
 nowhere-0.133
ls-0.131
 sky-0.130
 upon-0.114
Token right
Token ID826
Feature activation+3.29e+00

Pos logit contributions
 insist+0.082
gh+0.082
iding+0.080
 compete+0.079
icious+0.079
Neg logit contributions
s-0.046
 sky-0.037
 nowhere-0.032
 pieces-0.029
ls-0.029
Token back
Token ID736
Feature activation-1.50e+00

Pos logit contributions
 compete+0.115
gh+0.114
 som+0.114
 insist+0.112
icious+0.110
Neg logit contributions
s-0.083
 sky-0.065
 nowhere-0.063
ls-0.058
 everywhere-0.053
Token to
Token ID284
Feature activation+1.81e+00

Pos logit contributions
s+0.029
 sky+0.021
 nowhere+0.019
ls+0.017
 living+0.017
Neg logit contributions
gh-0.061
 som-0.059
 insist-0.058
 compete-0.057
iding-0.057
Token his
Token ID465
Feature activation+2.25e-01

Pos logit contributions
iding+0.074
gh+0.073
icious+0.071
heit+0.070
immer+0.069
Neg logit contributions
 living-0.026
 nowhere-0.025
 sky-0.025
s-0.025
 shadows-0.021
Token family
Token ID1641
Feature activation-4.31e+00

Pos logit contributions
gh+0.008
iding+0.007
 som+0.007
 insist+0.007
 compete+0.007
Neg logit contributions
s-0.005
 sky-0.005
 nowhere-0.004
 living-0.004
 twins-0.004
Token and
Token ID290
Feature activation-2.26e+00

Pos logit contributions
s+0.089
 sky+0.065
 living+0.059
 nowhere+0.059
 twins+0.053
Neg logit contributions
gh-0.171
heit-0.167
 som-0.164
 insist-0.160
 accompl-0.158
Token his
Token ID465
Feature activation+1.49e+00

Pos logit contributions
s+0.060
 sky+0.047
 living+0.046
 twins+0.044
 she+0.043
Neg logit contributions
gh-0.074
iding-0.072
icious-0.069
 som-0.067
immer-0.066
Token home
Token ID1363
Feature activation-5.33e-01

Pos logit contributions
gh+0.050
 som+0.049
 insist+0.048
iding+0.048
 compete+0.048
Neg logit contributions
s-0.035
 sky-0.030
 nowhere-0.029
 living-0.026
ls-0.026
Token in
Token ID287
Feature activation+1.64e+00

Pos logit contributions
s+0.011
 sky+0.008
 nowhere+0.007
 living+0.007
 twins+0.006
Neg logit contributions
gh-0.020
 insist-0.020
heit-0.020
 som-0.020
 compete-0.020
Token the
Token ID262
Feature activation-1.84e+00

Pos logit contributions
gh+0.065
iding+0.063
 insist+0.063
 som+0.062
 compete+0.061
Neg logit contributions
s-0.029
 nowhere-0.025
 sky-0.024
 living-0.019
 twins-0.018
Token
Token ID198
Feature activation-6.65e-01

Pos logit contributions
gh+0.034
 som+0.032
 insist+0.032
 compete+0.032
iding+0.031
Neg logit contributions
s-0.014
 sky-0.011
 nowhere-0.008
 living-0.008
 twins-0.007
Token
Token ID198
Feature activation+9.62e-02

Pos logit contributions
s+0.010
 sky+0.007
 nowhere+0.006
ls+0.005
 living+0.005
Neg logit contributions
gh-0.029
 insist-0.028
 som-0.028
 compete-0.028
iding-0.027
TokenThe
Token ID464
Feature activation+2.79e-01

Pos logit contributions
gh+0.004
 som+0.004
 insist+0.004
 compete+0.004
 appetite+0.004
Neg logit contributions
s-0.002
 sky-0.001
 nowhere-0.001
 living-0.001
Someone-0.001
Token end
Token ID886
Feature activation-3.12e+00

Pos logit contributions
iding+0.011
gh+0.011
 som+0.010
 insist+0.010
 compete+0.010
Neg logit contributions
s-0.005
 sky-0.005
 nowhere-0.005
 twins-0.004
 living-0.004
Token.
Token ID13
Feature activation+8.13e-01

Pos logit contributions
s+0.063
 sky+0.043
 living+0.042
 nowhere+0.036
+0.036
Neg logit contributions
heit-0.123
 som-0.123
gh-0.122
 insist-0.122
 compete-0.121
Token<|endoftext|>
Token ID50256
Feature activation-4.81e+00

Pos logit contributions
 insist+0.030
gh+0.030
 compete+0.029
 som+0.029
iding+0.029
Neg logit contributions
s-0.015
ls-0.012
 sky-0.011
 nowhere-0.010
 pieces-0.009
TokenOnce
Token ID7454
Feature activation+1.19e-01

Pos logit contributions
s+0.066
 nowhere+0.048
ls+0.044
 sky+0.039
armac+0.032
Neg logit contributions
gh-0.198
 compete-0.191
 insist-0.188
 som-0.188
iding-0.181
Token upon
Token ID2402
Feature activation-2.07e+00

Pos logit contributions
 insist+0.003
gh+0.003
iding+0.003
 please+0.003
 spend+0.003
Neg logit contributions
pill-0.003
Someone-0.003
Our-0.003
armac-0.003
 sky-0.002
Token a
Token ID257
Feature activation+1.15e+00

Pos logit contributions
s+0.067
ls+0.059
ays+0.054
actus+0.054
 sky+0.053
Neg logit contributions
gh-0.054
 som-0.050
 wait-0.049
 compete-0.048
 insist-0.047
Token time
Token ID640
Feature activation+1.30e+00

Pos logit contributions
 som+0.030
 compete+0.030
gh+0.030
 insist+0.029
 accompl+0.029
Neg logit contributions
s-0.035
 nowhere-0.030
 sky-0.029
 living-0.027
ls-0.026
Token there
Token ID612
Feature activation-1.18e-01

Pos logit contributions
gh+0.030
iding+0.027
 compete+0.026
 insist+0.025
 som+0.025
Neg logit contributions
s-0.043
 sky-0.041
 nowhere-0.038
actus-0.038
armac-0.038