TOP ACTIVATIONS
MAX = 0.120

the prince and princess sealed their marriage with a kiss .
branches . The bears used their strong arms to clear away
The friends used their numbers to try and make
. Sam and Sara used their creative minds and made up
Lucy and her mom completed their mission . They had found
animals in the forest have their own tw igs that shine
Lily realized that everyone has their own talents and things to
Max and Ma isy used their enthusiastic energy to play together
Bunny and Jay each had their own special tail . They
. They tied their rope around the pu ,
tomorrow . We will pack our bags and drive there .
how to fly and use their wings to soar . Soon
give the farmer some of their fruits and vegetables for free
Lily learned that everyone has their own style and it 's
people 's hopes of restoring their freedom were shattered . The
bird and his friends put their plan to work . The
Joe and Sally put their shells on the scale ,
The cats put their paws up to each other
teacher . We will use our imagination ." They
So the kids collected their umb rell as and went

MIN ACTIVATIONS
MIN = -0.156

" I want to c uddle with you , mom .
the bird suddenly began to yawn with joy .
they began to carefully ch isel the rock . They kept
he tried to take deep breaths to calm down . Tim
you go , my d arl ings . Enjoy your lunch
't want to go to bed yet . I want to
not want to go to bed . She wanted to play
were both too young to argue over the television .
opinions . They start to argue . They say , "
and hide - and - seek . The monkey was very
she had to go to bed with no chalk . <|endoftext|>
her eyes and took deep breaths . Soon , she felt
Anna and Ben start to argue . Anna says Ben has
, and they started to argue . Their mom said ,
. She climbs up the steps and sits on the top
get across the wet p uddle without getting wet .
big tree and decided to lean against it . The taller
to play in the p uddle . One day , D
She stood up and started sway ing to the music .
ily and Ben start to argue . They shout and pull

INTERVAL 0.051 - 0.120
CONTAINS 11.396%

lady and helped her until the ambulance came . He told
" Where are the toys ?" Tom cried .
lot of fun with the big steel car .
saw a cute bunny . The bunny had an adorable little
Tommy noticed something strange . The grass was starting to look

INTERVAL -0.018 - 0.051
CONTAINS 50.155%

mad at Tim , but he also felt sorry for him
catch fish ." " Wow , Tom , that
. Now he was known as the brav est boy in
was so happy to see it soar ! <|endoftext|> Once upon
upon a time there was a little girl named Sue .

INTERVAL -0.087 - -0.018
CONTAINS 38.328%

. Tom had a special shield that was very tough .
, they saw a big slide in the park . Tom
. One day , Anna wants to ride the
had a very long journey ahead of him . He took
it has to go home ," Ben says .

INTERVAL -0.156 - -0.087
CONTAINS 0.120%

. He would take big breaths of the fresh air and
you . We can c uddle and sn uggle and keep
with Max and accidentally tri pped on a cable . She
the comb and started to massage Anna 's hair too .
. The farmer tried to cheer him up , but nothing
Token the
Token ID262
Feature activation+8.64e-02

Pos logit contributions
 This+0.014
to+0.012
 Playing+0.012
ore+0.012
anging+0.011
Neg logit contributions
 way-0.021
 promise-0.020
 forgot-0.019
 passengers-0.018
 forget-0.018
Token prince
Token ID19716
Feature activation+2.84e-02

Pos logit contributions
 promise+0.099
ode+0.098
 forgot+0.092
 hood+0.087
 way+0.085
Neg logit contributions
 This-0.166
 late-0.152
 here-0.147
-0.142
 You-0.137
Token and
Token ID290
Feature activation+3.18e-02

Pos logit contributions
 way+0.042
 promise+0.042
 tears+0.037
 passengers+0.037
ode+0.036
Neg logit contributions
 This-0.049
to-0.047
ore-0.045
-0.044
 Playing-0.043
Token princess
Token ID21752
Feature activation+3.59e-02

Pos logit contributions
 promise+0.058
 way+0.054
ode+0.053
 forgot+0.052
 hood+0.049
Neg logit contributions
 This-0.049
to-0.041
 Playing-0.041
ges-0.040
ore-0.040
Token sealed
Token ID15283
Feature activation-2.60e-02

Pos logit contributions
 way+0.052
 promise+0.052
ode+0.048
 tears+0.047
 hood+0.046
Neg logit contributions
 This-0.060
to-0.059
ore-0.057
ges-0.056
-0.054
Token their
Token ID511
Feature activation+1.19e-01

Pos logit contributions
 This+0.029
to+0.025
ore+0.024
 Playing+0.022
ges+0.022
Neg logit contributions
 promise-0.059
 forgot-0.058
 way-0.057
 forget-0.056
ode-0.055
Token marriage
Token ID4845
Feature activation+9.89e-03

Pos logit contributions
 forgot+0.145
 forget+0.129
ode+0.128
 passengers+0.127
 way+0.123
Neg logit contributions
 This-0.242
 Playing-0.207
to-0.203
ore-0.202
ires-0.196
Token with
Token ID351
Feature activation+3.06e-02

Pos logit contributions
 forgot+0.023
 passengers+0.022
 promise+0.022
 way+0.022
 forget+0.022
Neg logit contributions
 This-0.009
ore-0.007
to-0.007
 Playing-0.006
-0.006
Token a
Token ID257
Feature activation+7.74e-02

Pos logit contributions
ode+0.056
 forgot+0.055
 promise+0.055
 way+0.054
 forget+0.051
Neg logit contributions
 This-0.043
 him-0.038
 Playing-0.035
 late-0.035
ges-0.034
Token kiss
Token ID9245
Feature activation-1.70e-02

Pos logit contributions
ode+0.120
 heads+0.115
 forgot+0.112
 way+0.110
 passengers+0.109
Neg logit contributions
 This-0.122
ore-0.116
 late-0.113
to-0.109
-0.107
Token.
Token ID13
Feature activation-3.65e-02

Pos logit contributions
 This+0.018
to+0.016
ore+0.016
 Playing+0.015
ges+0.014
Neg logit contributions
 way-0.039
 promise-0.038
 forgot-0.037
 forget-0.035
 passengers-0.035
Token branches
Token ID13737
Feature activation-2.44e-02

Pos logit contributions
 This+0.016
 Playing+0.015
ore+0.015
to+0.015
ges+0.015
Neg logit contributions
 promise-0.012
 forgot-0.011
 forget-0.011
 way-0.011
 passengers-0.009
Token.
Token ID13
Feature activation-4.21e-02

Pos logit contributions
 This+0.028
to+0.025
ore+0.025
 Playing+0.024
ges+0.023
Neg logit contributions
 way-0.053
 promise-0.053
 forgot-0.050
 passengers-0.049
 forget-0.048
Token The
Token ID383
Feature activation+8.23e-02

Pos logit contributions
 This+0.041
to+0.040
ore+0.039
 Playing+0.037
ges+0.035
Neg logit contributions
 way-0.097
 promise-0.091
 forgot-0.090
 tears-0.087
 passengers-0.086
Token bears
Token ID13062
Feature activation+3.43e-02

Pos logit contributions
 promise+0.144
 forgot+0.137
 hood+0.124
 way+0.123
 forget+0.123
Neg logit contributions
-0.114
 Playing-0.099
 This-0.098
 late-0.093
 Next-0.090
Token used
Token ID973
Feature activation+1.30e-03

Pos logit contributions
 way+0.056
 passengers+0.054
 promise+0.054
 scar+0.050
 hood+0.049
Neg logit contributions
ore-0.049
 This-0.048
to-0.048
ges-0.048
anging-0.047
Token their
Token ID511
Feature activation+1.18e-01

Pos logit contributions
 promise+0.003
 forgot+0.003
 way+0.003
 forget+0.003
ode+0.003
Neg logit contributions
 This-0.001
to-0.001
ges-0.001
ore-0.001
 late-0.001
Token strong
Token ID1913
Feature activation+4.77e-02

Pos logit contributions
 forgot+0.145
 forget+0.128
 promise+0.123
 captain+0.121
 passengers+0.118
Neg logit contributions
 This-0.231
to-0.205
ore-0.200
-0.196
 Playing-0.194
Token arms
Token ID5101
Feature activation-3.68e-02

Pos logit contributions
 forgot+0.054
 promise+0.049
 forget+0.046
 way+0.044
 passengers+0.042
Neg logit contributions
 This-0.103
to-0.091
 Playing-0.090
 Today-0.090
ore-0.089
Token to
Token ID284
Feature activation+2.35e-02

Pos logit contributions
 This+0.046
to+0.042
 Playing+0.041
ore+0.040
anging+0.037
Neg logit contributions
 way-0.078
 promise-0.076
 forgot-0.072
 passengers-0.069
 forget-0.069
Token clear
Token ID1598
Feature activation-7.25e-03

Pos logit contributions
 forgot+0.033
 way+0.032
 promise+0.031
 passengers+0.028
ode+0.028
Neg logit contributions
 This-0.044
to-0.039
ore-0.039
ges-0.038
anging-0.036
Token away
Token ID1497
Feature activation-2.62e-02

Pos logit contributions
 This+0.011
ore+0.009
to+0.009
 Playing+0.009
ges+0.009
Neg logit contributions
 promise-0.014
 forgot-0.014
 way-0.013
 forget-0.013
 passengers-0.012
Token
Token ID198
Feature activation-1.67e-02

Pos logit contributions
to+0.027
ore+0.026
 This+0.026
uttering+0.026
ges+0.025
Neg logit contributions
 way-0.041
 promise-0.039
 forgot-0.039
 forget-0.036
 bit-0.035
Token
Token ID198
Feature activation-1.78e-02

Pos logit contributions
 This+0.023
elt+0.023
used+0.022
anging+0.022
ges+0.022
Neg logit contributions
 way-0.031
 promise-0.030
 other-0.028
 tears-0.027
 forgot-0.027
TokenThe
Token ID464
Feature activation+7.84e-02

Pos logit contributions
 This+0.024
to+0.022
 Playing+0.022
ore+0.021
 late+0.020
Neg logit contributions
 way-0.037
 promise-0.036
 forgot-0.033
 tears-0.033
 passengers-0.032
Token friends
Token ID2460
Feature activation+2.47e-02

Pos logit contributions
 forgot+0.117
 promise+0.108
ode+0.104
 way+0.103
 scar+0.102
Neg logit contributions
 This-0.150
 Playing-0.135
-0.126
ore-0.123
 You-0.123
Token used
Token ID973
Feature activation+2.67e-03

Pos logit contributions
 way+0.036
 tears+0.033
 scar+0.032
 passengers+0.032
 promise+0.032
Neg logit contributions
 This-0.044
ore-0.042
to-0.040
ges-0.040
used-0.039
Token their
Token ID511
Feature activation+1.16e-01

Pos logit contributions
 promise+0.006
 forgot+0.006
 way+0.006
 forget+0.006
ode+0.006
Neg logit contributions
 This-0.003
to-0.003
ges-0.002
ore-0.002
 Playing-0.002
Token numbers
Token ID3146
Feature activation-1.90e-02

Pos logit contributions
 promise+0.149
 way+0.147
 forgot+0.145
 forget+0.132
 passengers+0.131
Neg logit contributions
 This-0.240
to-0.215
 Playing-0.213
ore-0.205
anging-0.204
Token to
Token ID284
Feature activation+2.34e-02

Pos logit contributions
 This+0.023
to+0.021
 Playing+0.020
ore+0.020
anging+0.018
Neg logit contributions
 way-0.041
 promise-0.040
 forgot-0.038
 passengers-0.037
 forget-0.037
Token try
Token ID1949
Feature activation-4.70e-02

Pos logit contributions
 way+0.031
 forgot+0.031
 promise+0.030
 tears+0.027
 passengers+0.026
Neg logit contributions
 This-0.047
to-0.041
ore-0.040
 Playing-0.040
anging-0.039
Token and
Token ID290
Feature activation+2.29e-02

Pos logit contributions
 This+0.076
 Playing+0.072
ore+0.072
elt+0.071
to+0.070
Neg logit contributions
 way-0.085
 promise-0.075
 other-0.071
 passengers-0.069
 tears-0.068
Token make
Token ID787
Feature activation-1.82e-02

Pos logit contributions
 promise+0.031
 way+0.030
 forgot+0.028
 passengers+0.027
 tears+0.026
Neg logit contributions
 This-0.045
to-0.042
 Playing-0.039
ore-0.038
used-0.037
Token.
Token ID13
Feature activation-3.51e-02

Pos logit contributions
 This+0.038
to+0.033
 Playing+0.032
ore+0.032
anging+0.028
Neg logit contributions
 way-0.086
 promise-0.083
 forgot-0.080
 passengers-0.077
 forget-0.077
Token Sam
Token ID3409
Feature activation+6.28e-02

Pos logit contributions
 This+0.033
to+0.027
 Playing+0.027
ore+0.026
anging+0.022
Neg logit contributions
 way-0.088
 promise-0.087
 forgot-0.083
 passengers-0.080
 forget-0.080
Token and
Token ID290
Feature activation+1.82e-02

Pos logit contributions
 promise+0.097
ode+0.092
 way+0.092
 passengers+0.090
 tears+0.085
Neg logit contributions
 This-0.102
to-0.102
 Playing-0.094
anging-0.094
ore-0.092
Token Sara
Token ID24799
Feature activation+6.54e-02

Pos logit contributions
 promise+0.042
 way+0.041
 forgot+0.039
ode+0.038
 passengers+0.038
Neg logit contributions
 This-0.020
to-0.017
 Playing-0.017
ges-0.015
ore-0.015
Token used
Token ID973
Feature activation+1.02e-02

Pos logit contributions
 way+0.101
ode+0.099
 passengers+0.096
 tears+0.094
 hood+0.094
Neg logit contributions
to-0.094
 This-0.093
ges-0.093
anging-0.091
ed-0.091
Token their
Token ID511
Feature activation+1.16e-01

Pos logit contributions
 promise+0.023
 forgot+0.022
 way+0.022
 forget+0.022
ode+0.021
Neg logit contributions
 This-0.011
to-0.010
ore-0.009
ges-0.009
 Playing-0.009
Token creative
Token ID7325
Feature activation+6.07e-02

Pos logit contributions
ode+0.165
 forgot+0.158
 promise+0.158
 way+0.155
 passengers+0.152
Neg logit contributions
 This-0.210
 Playing-0.193
ore-0.185
to-0.179
uttering-0.174
Token minds
Token ID9017
Feature activation-1.42e-02

Pos logit contributions
 forgot+0.085
ode+0.082
 promise+0.080
 way+0.076
 passengers+0.075
Neg logit contributions
 This-0.113
 Playing-0.100
to-0.096
ore-0.095
 Today-0.094
Token and
Token ID290
Feature activation+3.46e-02

Pos logit contributions
 This+0.015
to+0.013
 Playing+0.013
ore+0.012
anging+0.011
Neg logit contributions
 way-0.034
 promise-0.033
 forgot-0.031
 passengers-0.030
 forget-0.030
Token made
Token ID925
Feature activation-2.15e-02

Pos logit contributions
 promise+0.055
ode+0.055
 way+0.048
 hood+0.046
 difference+0.044
Neg logit contributions
 This-0.054
to-0.051
 Playing-0.049
ges-0.049
 spending-0.049
Token up
Token ID510
Feature activation-6.94e-03

Pos logit contributions
 This+0.030
to+0.028
 Playing+0.026
ore+0.026
anging+0.024
Neg logit contributions
 promise-0.043
 way-0.042
 forgot-0.040
 forget-0.039
ode-0.038
Token Lucy
Token ID22162
Feature activation+6.39e-02

Pos logit contributions
 This+0.010
ore+0.007
 That+0.007
 Playing+0.006
to+0.006
Neg logit contributions
ode-0.020
 promise-0.020
 passengers-0.020
 way-0.020
 forgot-0.019
Token and
Token ID290
Feature activation+1.60e-02

Pos logit contributions
 promise+0.117
 way+0.116
 passengers+0.109
 tears+0.108
 matter+0.104
Neg logit contributions
 This-0.091
to-0.087
anging-0.080
 Playing-0.079
elt-0.078
Token her
Token ID607
Feature activation+7.15e-02

Pos logit contributions
 way+0.039
 promise+0.039
 forgot+0.037
 passengers+0.036
 forget+0.036
Neg logit contributions
 This-0.015
to-0.013
 Playing-0.012
ore-0.012
ges-0.011
Token mom
Token ID1995
Feature activation+4.48e-02

Pos logit contributions
ode+0.132
 forgot+0.116
 bit+0.111
 forget+0.109
 matter+0.108
Neg logit contributions
 This-0.096
 Playing-0.086
-0.083
 playing-0.083
 Today-0.082
Token completed
Token ID5668
Feature activation-1.27e-02

Pos logit contributions
 promise+0.074
 tears+0.074
 way+0.071
 surge+0.068
 feelings+0.066
Neg logit contributions
elt-0.065
to-0.064
anging-0.063
ing-0.062
 This-0.061
Token their
Token ID511
Feature activation+1.15e-01

Pos logit contributions
 This+0.016
to+0.014
 Playing+0.013
ore+0.013
ges+0.012
Neg logit contributions
 promise-0.027
 way-0.027
 forgot-0.026
 forget-0.025
 passengers-0.025
Token mission
Token ID4365
Feature activation-2.84e-02

Pos logit contributions
 forgot+0.134
 captain+0.117
 surge+0.115
 promise+0.115
 passengers+0.115
Neg logit contributions
 This-0.245
to-0.216
 Playing-0.207
 Today-0.201
ore-0.198
Token.
Token ID13
Feature activation-3.05e-02

Pos logit contributions
 This+0.027
to+0.023
ore+0.022
 Playing+0.020
anging+0.020
Neg logit contributions
 promise-0.067
 way-0.065
 forgot-0.065
 passengers-0.063
ode-0.063
Token They
Token ID1119
Feature activation+5.78e-02

Pos logit contributions
to+0.032
 This+0.031
ore+0.031
anging+0.029
 Playing+0.028
Neg logit contributions
 way-0.068
 promise-0.063
 forgot-0.061
 tears-0.060
 passengers-0.059
Token had
Token ID550
Feature activation+3.57e-02

Pos logit contributions
 way+0.096
 tears+0.094
 promise+0.092
 difference+0.091
 feelings+0.090
Neg logit contributions
 This-0.073
to-0.072
 at-0.071
 him-0.069
anging-0.067
Token found
Token ID1043
Feature activation+4.85e-03

Pos logit contributions
 promise+0.073
ode+0.064
 surge+0.062
 forget+0.061
 eye+0.060
Neg logit contributions
 This-0.051
to-0.045
 spending-0.044
 late-0.044
elt-0.039
Token animals
Token ID4695
Feature activation+3.10e-02

Pos logit contributions
 windshield+0.106
 doorstep+0.105
 hood+0.104
 dashboard+0.101
 forgot+0.100
Neg logit contributions
-0.097
 spending-0.084
 exploring-0.080
 hopping-0.080
 Playing-0.078
Token in
Token ID287
Feature activation+1.80e-02

Pos logit contributions
 way+0.050
 promise+0.048
 tears+0.045
 passengers+0.045
 forgot+0.044
Neg logit contributions
 This-0.051
ore-0.050
to-0.048
 Playing-0.047
ges-0.045
Token the
Token ID262
Feature activation+6.52e-02

Pos logit contributions
 way+0.034
 promise+0.033
 forgot+0.031
 passengers+0.030
 forget+0.030
Neg logit contributions
 This-0.027
to-0.025
 Playing-0.024
ore-0.024
anging-0.022
Token forest
Token ID8222
Feature activation-2.69e-02

Pos logit contributions
 forgot+0.113
 promise+0.109
 passengers+0.103
 tears+0.097
 passports+0.096
Neg logit contributions
 This-0.101
-0.100
 Playing-0.088
ore-0.086
 late-0.082
Token have
Token ID423
Feature activation+4.20e-02

Pos logit contributions
 This+0.051
to+0.046
ore+0.046
 Playing+0.046
anging+0.044
Neg logit contributions
 way-0.038
 promise-0.038
 forgot-0.034
 tears-0.034
 passengers-0.033
Token their
Token ID511
Feature activation+1.15e-01

Pos logit contributions
 promise+0.082
 way+0.078
 forgot+0.073
 forget+0.073
 passengers+0.071
Neg logit contributions
 This-0.061
to-0.055
 Playing-0.051
ore-0.049
 late-0.049
Token own
Token ID898
Feature activation+8.88e-02

Pos logit contributions
 forgot+0.159
 passengers+0.142
 officer+0.142
 way+0.137
 tears+0.134
Neg logit contributions
 This-0.209
-0.192
ore-0.188
to-0.185
 Playing-0.185
Token tw
Token ID665
Feature activation+1.63e-02

Pos logit contributions
 forgot+0.104
 promise+0.098
 way+0.095
 passengers+0.093
 forget+0.091
Neg logit contributions
 This-0.176
to-0.164
ore-0.163
-0.160
 Playing-0.157
Tokenigs
Token ID9235
Feature activation-1.43e-02

Pos logit contributions
 way+0.022
 promise+0.021
 forgot+0.019
 passengers+0.018
 forget+0.018
Neg logit contributions
 This-0.033
to-0.032
ore-0.031
 Playing-0.031
anging-0.030
Token that
Token ID326
Feature activation+2.41e-02

Pos logit contributions
 This+0.019
to+0.017
ore+0.017
 Playing+0.017
anging+0.015
Neg logit contributions
 way-0.029
 promise-0.028
 forgot-0.027
 passengers-0.026
 tears-0.026
Token shine
Token ID18340
Feature activation-3.64e-02

Pos logit contributions
 promise+0.039
 way+0.037
 tears+0.035
 passengers+0.035
 forgot+0.035
Neg logit contributions
 This-0.042
ore-0.038
to-0.038
 Playing-0.037
ges-0.035
Token Lily
Token ID20037
Feature activation+5.04e-02

Pos logit contributions
uttering+0.028
ore+0.027
to+0.027
anging+0.027
used+0.025
Neg logit contributions
 way-0.060
 promise-0.057
 forgot-0.056
 other-0.055
 forget-0.054
Token realized
Token ID6939
Feature activation-1.35e-02

Pos logit contributions
 passengers+0.082
 promise+0.081
 way+0.080
 hood+0.077
ode+0.077
Neg logit contributions
 This-0.075
 Playing-0.073
to-0.073
anging-0.069
ing-0.065
Token that
Token ID326
Feature activation-9.32e-03

Pos logit contributions
 This+0.019
to+0.018
ore+0.017
 Playing+0.017
anging+0.016
Neg logit contributions
 way-0.027
 promise-0.025
 forgot-0.024
 tears-0.023
 passengers-0.023
Token everyone
Token ID2506
Feature activation+2.91e-02

Pos logit contributions
 This+0.010
 Playing+0.009
to+0.009
ore+0.009
ges+0.008
Neg logit contributions
 way-0.021
 promise-0.021
 forgot-0.020
 passengers-0.019
 bit-0.019
Token has
Token ID468
Feature activation+4.98e-02

Pos logit contributions
 way+0.044
 promise+0.043
 passengers+0.039
 forgot+0.038
 scar+0.037
Neg logit contributions
 This-0.054
 Playing-0.050
ore-0.050
to-0.050
anging-0.046
Token their
Token ID511
Feature activation+1.14e-01

Pos logit contributions
 promise+0.079
ode+0.074
 way+0.070
 hood+0.069
 passengers+0.069
Neg logit contributions
 This-0.087
to-0.076
 Playing-0.074
 late-0.073
 spending-0.073
Token own
Token ID898
Feature activation+8.98e-02

Pos logit contributions
 forgot+0.141
ode+0.141
 passengers+0.135
 hood+0.131
 way+0.130
Neg logit contributions
 This-0.221
 Playing-0.198
ore-0.198
to-0.191
uttering-0.189
Token talents
Token ID18054
Feature activation-9.97e-03

Pos logit contributions
 promise+0.102
 way+0.101
 forgot+0.101
ode+0.095
 passengers+0.094
Neg logit contributions
 This-0.186
ore-0.170
 Playing-0.170
to-0.169
anging-0.160
Token and
Token ID290
Feature activation+2.68e-02

Pos logit contributions
 This+0.014
 Playing+0.012
to+0.012
ore+0.012
ges+0.011
Neg logit contributions
 way-0.019
 promise-0.019
 forgot-0.018
 passengers-0.018
 forget-0.017
Token things
Token ID1243
Feature activation-4.63e-03

Pos logit contributions
 promise+0.040
 way+0.039
ode+0.038
 hood+0.037
 passengers+0.035
Neg logit contributions
 This-0.048
 Playing-0.044
to-0.042
 spending-0.040
 Do-0.039
Token to
Token ID284
Feature activation+4.27e-02

Pos logit contributions
 This+0.007
to+0.007
 Playing+0.006
ore+0.006
anging+0.006
Neg logit contributions
 way-0.009
 promise-0.008
 forgot-0.008
 passengers-0.008
 forget-0.007
Token Max
Token ID5436
Feature activation+4.79e-02

Pos logit contributions
 This+0.025
 Playing+0.021
to+0.020
ore+0.019
 late+0.018
Neg logit contributions
 promise-0.049
 way-0.048
 forgot-0.045
ode-0.045
 tears-0.044
Token and
Token ID290
Feature activation+1.24e-02

Pos logit contributions
 promise+0.091
 way+0.088
 passengers+0.082
 tears+0.080
 forget+0.079
Neg logit contributions
 This-0.071
 Playing-0.065
to-0.064
ore-0.061
anging-0.059
Token Ma
Token ID6669
Feature activation+4.22e-02

Pos logit contributions
 promise+0.026
 way+0.025
 forgot+0.024
 tears+0.023
ode+0.023
Neg logit contributions
 This-0.017
to-0.014
ges-0.014
ore-0.013
 Playing-0.013
Tokenisy
Token ID13560
Feature activation+3.49e-02

Pos logit contributions
 way+0.053
 promise+0.051
 tears+0.045
 forgot+0.044
 bit+0.044
Neg logit contributions
 This-0.087
to-0.081
 Playing-0.081
anging-0.079
ore-0.079
Token used
Token ID973
Feature activation+9.33e-03

Pos logit contributions
 promise+0.050
 scar+0.049
 tears+0.048
 way+0.048
 hood+0.048
Neg logit contributions
 This-0.061
 Playing-0.055
anging-0.053
ges-0.052
to-0.052
Token their
Token ID511
Feature activation+1.14e-01

Pos logit contributions
 promise+0.022
 forgot+0.021
 forget+0.020
 way+0.020
ode+0.020
Neg logit contributions
 This-0.010
to-0.009
ges-0.008
 Playing-0.007
 late-0.007
Token enthusiastic
Token ID21848
Feature activation+4.54e-02

Pos logit contributions
 forgot+0.138
 promise+0.133
 way+0.129
 passengers+0.124
 forget+0.122
Neg logit contributions
 This-0.235
 Playing-0.209
to-0.207
ore-0.197
-0.194
Token energy
Token ID2568
Feature activation-2.04e-02

Pos logit contributions
 forgot+0.054
 way+0.049
 promise+0.049
 forget+0.045
 bit+0.045
Neg logit contributions
 This-0.095
to-0.086
 Playing-0.085
elt-0.081
ore-0.080
Token to
Token ID284
Feature activation+2.70e-02

Pos logit contributions
 This+0.017
to+0.014
ore+0.014
 Playing+0.013
anging+0.012
Neg logit contributions
 way-0.051
 promise-0.051
 forgot-0.050
 forget-0.048
 passengers-0.048
Token play
Token ID711
Feature activation-3.05e-02

Pos logit contributions
 way+0.039
 forgot+0.039
 promise+0.037
 scar+0.035
 tears+0.035
Neg logit contributions
 This-0.048
to-0.042
ore-0.040
 Playing-0.040
anging-0.040
Token together
Token ID1978
Feature activation-1.06e-02

Pos logit contributions
 This+0.037
to+0.032
 Playing+0.032
ore+0.031
anging+0.028
Neg logit contributions
 way-0.067
 promise-0.065
 forgot-0.063
 forget-0.060
 passengers-0.060
Token Bunny
Token ID28683
Feature activation+4.74e-02

Pos logit contributions
 way+0.045
 promise+0.043
 forgot+0.041
 passengers+0.040
 bit+0.038
Neg logit contributions
 This-0.041
to-0.038
 Playing-0.038
ore-0.037
anging-0.035
Token and
Token ID290
Feature activation+2.77e-02

Pos logit contributions
 promise+0.085
 way+0.082
 passengers+0.082
 forget+0.076
ode+0.074
Neg logit contributions
 This-0.075
to-0.067
 Playing-0.066
ore-0.064
anging-0.063
Token Jay
Token ID9180
Feature activation+5.28e-02

Pos logit contributions
 promise+0.057
 way+0.055
 forgot+0.052
 forget+0.051
 tears+0.051
Neg logit contributions
 This-0.037
to-0.033
 Playing-0.033
ore-0.032
-0.031
Token each
Token ID1123
Feature activation+7.05e-02

Pos logit contributions
 way+0.086
 passengers+0.072
ode+0.072
 promise+0.072
 scar+0.071
Neg logit contributions
 This-0.094
to-0.085
ges-0.085
ore-0.082
anging-0.082
Token had
Token ID550
Feature activation+4.29e-02

Pos logit contributions
 way+0.100
 promise+0.093
 passengers+0.092
ode+0.090
 hood+0.086
Neg logit contributions
 This-0.133
to-0.132
ges-0.125
ore-0.123
anging-0.118
Token their
Token ID511
Feature activation+1.13e-01

Pos logit contributions
 promise+0.091
ode+0.085
 head+0.080
 passengers+0.080
 surge+0.080
Neg logit contributions
 This-0.053
to-0.043
 spending-0.041
 late-0.038
 him-0.036
Token own
Token ID898
Feature activation+8.97e-02

Pos logit contributions
 way+0.124
 forgot+0.124
 promise+0.121
 passengers+0.114
ode+0.112
Neg logit contributions
 This-0.249
 Playing-0.225
to-0.220
ore-0.212
 That-0.206
Token special
Token ID2041
Feature activation+6.96e-02

Pos logit contributions
 way+0.102
 promise+0.098
 forgot+0.091
 passengers+0.084
 forget+0.083
Neg logit contributions
 This-0.200
to-0.187
 Playing-0.186
ore-0.183
anging-0.176
Token tail
Token ID7894
Feature activation-7.77e-03

Pos logit contributions
 way+0.080
 promise+0.077
 forgot+0.074
 passengers+0.067
 forget+0.066
Neg logit contributions
 This-0.154
to-0.143
 Playing-0.142
ore-0.140
anging-0.133
Token.
Token ID13
Feature activation-2.96e-02

Pos logit contributions
 This+0.008
ore+0.007
to+0.006
 Playing+0.006
ges+0.006
Neg logit contributions
 promise-0.018
 way-0.018
 forgot-0.017
 passengers-0.017
 forget-0.016
Token They
Token ID1119
Feature activation+6.05e-02

Pos logit contributions
 This+0.030
to+0.030
uttering+0.028
ore+0.028
anging+0.027
Neg logit contributions
 way-0.066
 promise-0.061
 passengers-0.059
 forgot-0.059
 tears-0.057
Token.
Token ID13
Feature activation-4.01e-02

Pos logit contributions
 way+0.012
 promise+0.012
 forgot+0.011
 passengers+0.011
 forget+0.011
Neg logit contributions
 This-0.008
to-0.007
 Playing-0.007
ore-0.007
anging-0.006
Token
Token ID198
Feature activation-2.26e-02

Pos logit contributions
uttering+0.038
to+0.038
 This+0.036
anging+0.036
ore+0.036
Neg logit contributions
 way-0.092
 promise-0.085
 forgot-0.082
 passengers-0.081
 tears-0.080
Token
Token ID198
Feature activation-2.33e-02

Pos logit contributions
 This+0.024
elt+0.022
 Playing+0.022
used+0.022
ays+0.022
Neg logit contributions
 way-0.051
 promise-0.048
 forgot-0.046
 other-0.045
 passengers-0.045
TokenThey
Token ID2990
Feature activation+5.31e-02

Pos logit contributions
 This+0.033
to+0.030
 Playing+0.030
ore+0.029
anging+0.027
Neg logit contributions
 way-0.046
 promise-0.045
 forgot-0.042
 tears-0.041
 forget-0.041
Token tied
Token ID8165
Feature activation-3.55e-02

Pos logit contributions
 way+0.093
 promise+0.092
 difference+0.088
 forget+0.083
 tears+0.082
Neg logit contributions
 him-0.068
 This-0.068
to-0.067
anging-0.062
-0.062
Token their
Token ID511
Feature activation+1.13e-01

Pos logit contributions
 This+0.043
to+0.037
 Playing+0.036
ore+0.035
ges+0.033
Neg logit contributions
 promise-0.079
 way-0.076
 forgot-0.076
 forget-0.073
ode-0.070
Token rope
Token ID17182
Feature activation-2.81e-02

Pos logit contributions
 forgot+0.128
 forget+0.117
 promise+0.116
 passengers+0.106
 surge+0.105
Neg logit contributions
 This-0.229
to-0.218
-0.197
ore-0.195
anging-0.193
Token around
Token ID1088
Feature activation-2.62e-02

Pos logit contributions
 This+0.032
to+0.028
 Playing+0.027
ore+0.027
anging+0.025
Neg logit contributions
 way-0.063
 promise-0.062
 forgot-0.059
 passengers-0.057
 forget-0.057
Token the
Token ID262
Feature activation+7.40e-02

Pos logit contributions
 This+0.032
 Playing+0.027
to+0.027
ore+0.027
ges+0.026
Neg logit contributions
 promise-0.056
 way-0.055
 forgot-0.054
 forget-0.052
ode-0.051
Token pu
Token ID47574
Feature activation-5.21e-02

Pos logit contributions
 forgot+0.107
 promise+0.103
 passengers+0.092
 way+0.092
 scar+0.090
Neg logit contributions
 This-0.127
 late-0.118
ore-0.117
to-0.113
 Playing-0.111
Token,
Token ID11
Feature activation-1.48e-03

Pos logit contributions
 This+0.076
 Playing+0.070
to+0.069
elt+0.068
ore+0.067
Neg logit contributions
 way-0.098
 promise-0.093
 forgot-0.093
 passengers-0.086
 bit-0.084
Token tomorrow
Token ID9439
Feature activation-2.34e-02

Pos logit contributions
 Playing+0.039
 This+0.038
to+0.036
anging+0.034
ges+0.034
Neg logit contributions
 way-0.049
 promise-0.048
 passengers-0.043
 forget-0.043
 forgot-0.042
Token.
Token ID13
Feature activation-2.23e-02

Pos logit contributions
 This+0.034
 Playing+0.033
to+0.032
ore+0.030
elt+0.030
Neg logit contributions
 way-0.048
 promise-0.044
 forgot-0.041
 forget-0.040
 bit-0.039
Token We
Token ID775
Feature activation+4.93e-02

Pos logit contributions
to+0.023
 This+0.022
ore+0.022
uttering+0.021
anging+0.021
Neg logit contributions
 way-0.050
 promise-0.049
 passengers-0.046
 forgot-0.046
 forget-0.045
Token will
Token ID481
Feature activation+1.61e-02

Pos logit contributions
 tears+0.091
 way+0.089
 floor+0.085
 passengers+0.079
ode+0.079
Neg logit contributions
 This-0.073
ore-0.063
-0.061
 Today-0.059
 Playing-0.056
Token pack
Token ID2353
Feature activation-5.12e-02

Pos logit contributions
 way+0.021
 tears+0.020
 forgot+0.020
 promise+0.019
ode+0.018
Neg logit contributions
 This-0.032
to-0.027
 Playing-0.027
ore-0.027
 Today-0.026
Token our
Token ID674
Feature activation+1.13e-01

Pos logit contributions
 This+0.072
to+0.067
 Playing+0.066
ore+0.065
anging+0.065
Neg logit contributions
 way-0.101
 promise-0.098
 forgot-0.090
 tears-0.089
 passengers-0.089
Token bags
Token ID11668
Feature activation-2.87e-02

Pos logit contributions
 forgot+0.146
 way+0.128
 forget+0.127
 promise+0.123
 surge+0.119
Neg logit contributions
 This-0.225
-0.207
ore-0.205
 Playing-0.201
to-0.196
Token and
Token ID290
Feature activation+2.75e-02

Pos logit contributions
 This+0.038
to+0.035
 Playing+0.034
ore+0.033
anging+0.031
Neg logit contributions
 way-0.060
 promise-0.058
 forgot-0.054
 forget-0.052
 passengers-0.052
Token drive
Token ID3708
Feature activation-4.85e-02

Pos logit contributions
 way+0.039
 promise+0.037
 forgot+0.036
 tears+0.036
 surge+0.034
Neg logit contributions
 This-0.051
to-0.045
 Playing-0.044
 late-0.043
ore-0.042
Token there
Token ID612
Feature activation-1.43e-02

Pos logit contributions
 This+0.065
to+0.059
 Playing+0.058
ore+0.057
anging+0.054
Neg logit contributions
 way-0.100
 promise-0.097
 forgot-0.091
 passengers-0.089
 forget-0.087
Token.
Token ID13
Feature activation-3.30e-02

Pos logit contributions
 This+0.020
to+0.018
 Playing+0.018
ore+0.018
elt+0.017
Neg logit contributions
 way-0.029
 promise-0.028
 forgot-0.026
 passengers-0.025
 bit-0.025
Token how
Token ID703
Feature activation+4.42e-04

Pos logit contributions
 way+0.027
 promise+0.026
 forgot+0.025
 passengers+0.024
 forget+0.024
Neg logit contributions
 This-0.020
to-0.018
 Playing-0.018
ore-0.018
anging-0.017
Token to
Token ID284
Feature activation+3.55e-02

Pos logit contributions
 way+0.001
 promise+0.001
 forgot+0.001
 passengers+0.001
 forget+0.001
Neg logit contributions
 This-0.001
 Playing-0.001
to-0.001
ore-0.001
anging-0.001
Token fly
Token ID6129
Feature activation-2.81e-02

Pos logit contributions
 way+0.053
 forgot+0.049
 promise+0.049
 tears+0.045
 passengers+0.044
Neg logit contributions
 This-0.065
ore-0.058
to-0.058
 Playing-0.057
ges-0.055
Token and
Token ID290
Feature activation+2.61e-02

Pos logit contributions
 This+0.038
to+0.034
 Playing+0.033
ore+0.033
anging+0.031
Neg logit contributions
 way-0.058
 promise-0.056
 forgot-0.053
 passengers-0.051
 forget-0.051
Token use
Token ID779
Feature activation+4.96e-03

Pos logit contributions
 promise+0.040
 way+0.038
 forgot+0.036
ode+0.034
 tears+0.034
Neg logit contributions
 This-0.046
to-0.043
 Playing-0.041
ore-0.040
 Do-0.039
Token their
Token ID511
Feature activation+1.12e-01

Pos logit contributions
 promise+0.011
 forgot+0.011
 way+0.010
 forget+0.010
ode+0.010
Neg logit contributions
 This-0.006
to-0.005
 Playing-0.005
ore-0.005
ges-0.005
Token wings
Token ID12098
Feature activation-2.59e-02

Pos logit contributions
 forgot+0.117
 promise+0.108
 forget+0.098
 cash+0.096
 officer+0.095
Neg logit contributions
 This-0.241
to-0.212
 Playing-0.210
-0.208
ore-0.208
Token to
Token ID284
Feature activation+3.30e-02

Pos logit contributions
 This+0.027
to+0.024
ore+0.023
 Playing+0.022
anging+0.020
Neg logit contributions
 way-0.060
 promise-0.059
 forgot-0.057
 passengers-0.055
 forget-0.055
Token soar
Token ID48701
Feature activation-3.98e-02

Pos logit contributions
 way+0.046
 forgot+0.046
 promise+0.044
 passengers+0.040
ode+0.039
Neg logit contributions
 This-0.061
to-0.055
ore-0.055
 Playing-0.053
ges-0.052
Token.
Token ID13
Feature activation-3.56e-02

Pos logit contributions
 This+0.052
to+0.047
 Playing+0.046
ore+0.045
anging+0.042
Neg logit contributions
 way-0.084
 promise-0.081
 forgot-0.077
 passengers-0.074
 forget-0.074
Token Soon
Token ID15894
Feature activation+1.96e-02

Pos logit contributions
 This+0.034
to+0.032
ore+0.031
uttering+0.031
 Playing+0.031
Neg logit contributions
 way-0.083
 promise-0.079
 forgot-0.076
 passengers-0.073
 tears-0.073
Token give
Token ID1577
Feature activation-3.25e-02

Pos logit contributions
 way+0.016
 scar+0.016
 forgot+0.016
 tears+0.015
 passengers+0.015
Neg logit contributions
 This-0.019
to-0.016
ore-0.015
?'-0.015
?-0.015
Token the
Token ID262
Feature activation+8.78e-02

Pos logit contributions
 This+0.038
to+0.035
ore+0.032
ges+0.029
 Playing+0.029
Neg logit contributions
 promise-0.071
 way-0.071
 forgot-0.069
 forget-0.067
 passengers-0.065
Token farmer
Token ID18739
Feature activation+1.10e-02

Pos logit contributions
 forgot+0.122
 forget+0.108
ode+0.108
 promise+0.107
 hood+0.104
Neg logit contributions
 This-0.159
-0.140
 late-0.139
to-0.138
ore-0.131
Token some
Token ID617
Feature activation+6.47e-02

Pos logit contributions
 way+0.024
 promise+0.023
 forgot+0.023
 forget+0.022
 passengers+0.021
Neg logit contributions
 This-0.014
to-0.011
ore-0.011
 Playing-0.010
 late-0.010
Token of
Token ID286
Feature activation+3.44e-02

Pos logit contributions
 forgot+0.090
 way+0.088
 promise+0.083
 forget+0.081
 passengers+0.078
Neg logit contributions
 This-0.123
ore-0.115
to-0.114
 Playing-0.109
-0.106
Token their
Token ID511
Feature activation+1.12e-01

Pos logit contributions
 way+0.075
 promise+0.074
 forgot+0.073
 forget+0.068
 bit+0.067
Neg logit contributions
 This-0.041
to-0.036
ore-0.035
 Playing-0.035
ges-0.032
Token fruits
Token ID15921
Feature activation-2.73e-02

Pos logit contributions
 forgot+0.147
 way+0.141
 promise+0.133
 forget+0.130
ode+0.127
Neg logit contributions
 This-0.218
to-0.198
 Playing-0.192
ore-0.188
-0.185
Token and
Token ID290
Feature activation+2.51e-02

Pos logit contributions
 This+0.039
to+0.035
 Playing+0.035
ore+0.034
anging+0.032
Neg logit contributions
 way-0.054
 promise-0.052
 forgot-0.049
 passengers-0.047
 forget-0.047
Token vegetables
Token ID13701
Feature activation-1.99e-02

Pos logit contributions
 promise+0.038
 way+0.037
 surge+0.035
ode+0.034
 hood+0.034
Neg logit contributions
 This-0.042
to-0.038
 late-0.036
 spending-0.035
 Playing-0.034
Token for
Token ID329
Feature activation-5.05e-03

Pos logit contributions
 This+0.025
to+0.023
 Playing+0.023
ore+0.022
anging+0.020
Neg logit contributions
 way-0.042
 promise-0.041
 forgot-0.039
 forget-0.037
 passengers-0.037
Token free
Token ID1479
Feature activation-1.78e-02

Pos logit contributions
 This+0.007
to+0.006
 Playing+0.006
ore+0.006
 late+0.006
Neg logit contributions
 way-0.010
 promise-0.010
 forgot-0.009
 forget-0.009
ode-0.009
Token Lily
Token ID20037
Feature activation+5.06e-02

Pos logit contributions
 This+0.044
 Playing+0.039
to+0.038
ore+0.037
 late+0.035
Neg logit contributions
 way-0.052
 promise-0.052
 forgot-0.048
 passengers-0.047
 forget-0.046
Token learned
Token ID4499
Feature activation-8.88e-03

Pos logit contributions
 promise+0.062
 way+0.059
 passengers+0.054
 tears+0.051
 scar+0.049
Neg logit contributions
 This-0.106
 Playing-0.102
to-0.100
anging-0.096
ore-0.096
Token that
Token ID326
Feature activation-7.38e-03

Pos logit contributions
 This+0.014
ges+0.013
ore+0.013
used+0.013
anging+0.013
Neg logit contributions
 way-0.016
 promise-0.014
 other-0.014
 tears-0.014
 forgot-0.014
Token everyone
Token ID2506
Feature activation+2.78e-02

Pos logit contributions
 This+0.011
 Playing+0.010
to+0.010
ore+0.010
ges+0.009
Neg logit contributions
 way-0.014
 promise-0.014
 forgot-0.013
 passengers-0.012
 forget-0.012
Token has
Token ID468
Feature activation+4.74e-02

Pos logit contributions
 way+0.046
 promise+0.044
 forgot+0.041
 passengers+0.040
 forget+0.039
Neg logit contributions
 This-0.048
 Playing-0.045
to-0.044
ore-0.044
anging-0.041
Token their
Token ID511
Feature activation+1.12e-01

Pos logit contributions
 promise+0.085
ode+0.081
 pile+0.078
 way+0.078
 captain+0.074
Neg logit contributions
 This-0.076
 Playing-0.066
 late-0.062
to-0.061
elt-0.059
Token own
Token ID898
Feature activation+8.39e-02

Pos logit contributions
ode+0.168
 forgot+0.154
 surge+0.148
 captain+0.144
 pile+0.143
Neg logit contributions
 This-0.184
 Playing-0.166
uttering-0.152
 here-0.152
ires-0.151
Token style
Token ID3918
Feature activation-8.24e-03

Pos logit contributions
ode+0.100
 forgot+0.097
 way+0.094
 forget+0.091
 bit+0.090
Neg logit contributions
 This-0.169
 Playing-0.154
ore-0.144
to-0.143
-0.141
Token and
Token ID290
Feature activation+2.62e-02

Pos logit contributions
 This+0.012
 Playing+0.011
ore+0.010
to+0.010
anging+0.009
Neg logit contributions
 way-0.016
 promise-0.016
 forgot-0.015
 forget-0.014
 passengers-0.014
Token it
Token ID340
Feature activation+1.58e-02

Pos logit contributions
 promise+0.046
 way+0.045
ode+0.043
 pile+0.042
 hood+0.041
Neg logit contributions
 This-0.041
 Playing-0.038
to-0.036
 Do-0.033
 spending-0.033
Token's
Token ID338
Feature activation+4.49e-02

Pos logit contributions
 promise+0.024
 way+0.024
 passengers+0.023
 scar+0.022
 forgot+0.021
Neg logit contributions
 This-0.029
 Playing-0.027
to-0.025
ore-0.025
-0.024
Token people
Token ID661
Feature activation+2.93e-02

Pos logit contributions
 scar+0.112
 ribbon+0.108
 hood+0.106
 promise+0.105
 way+0.104
Neg logit contributions
 This-0.143
 late-0.136
-0.133
ore-0.130
ires-0.127
Token's
Token ID338
Feature activation+6.82e-02

Pos logit contributions
 way+0.058
 scar+0.055
 promise+0.054
ode+0.054
 pile+0.050
Neg logit contributions
ore-0.039
ges-0.037
ing-0.036
 This-0.035
used-0.035
Token hopes
Token ID7176
Feature activation+1.30e-02

Pos logit contributions
 forget+0.077
ode+0.077
 forgot+0.076
 pile+0.075
 way+0.072
Neg logit contributions
 This-0.124
to-0.120
 Playing-0.117
ore-0.116
oo-0.110
Token of
Token ID286
Feature activation+3.59e-02

Pos logit contributions
 promise+0.029
ode+0.027
 way+0.027
 scar+0.026
 pile+0.026
Neg logit contributions
 This-0.014
to-0.012
 late-0.012
ore-0.012
 Playing-0.011
Token restoring
Token ID25646
Feature activation-1.51e-02

Pos logit contributions
 promise+0.076
 way+0.074
 forgot+0.072
 forget+0.068
ode+0.067
Neg logit contributions
 This-0.045
 Playing-0.040
to-0.037
ore-0.037
 late-0.036
Token their
Token ID511
Feature activation+1.12e-01

Pos logit contributions
 This+0.020
ore+0.017
to+0.017
 Playing+0.017
ges+0.016
Neg logit contributions
 promise-0.030
 way-0.030
 forgot-0.030
 forget-0.028
 passengers-0.027
Token freedom
Token ID4925
Feature activation-8.65e-03

Pos logit contributions
 forgot+0.149
 hood+0.138
 promise+0.136
 way+0.135
ode+0.135
Neg logit contributions
 This-0.193
ore-0.176
 Playing-0.175
to-0.174
-0.167
Token were
Token ID547
Feature activation+5.15e-02

Pos logit contributions
 This+0.010
ore+0.009
to+0.008
 Playing+0.008
ges+0.008
Neg logit contributions
 promise-0.018
 way-0.018
 forgot-0.017
 passengers-0.017
 scar-0.017
Token shattered
Token ID23273
Feature activation-2.59e-02

Pos logit contributions
 promise+0.076
 way+0.075
ode+0.071
 forgot+0.069
 forget+0.069
Neg logit contributions
 This-0.086
 late-0.084
to-0.079
 Playing-0.077
ore-0.076
Token.
Token ID13
Feature activation-3.34e-02

Pos logit contributions
 This+0.034
to+0.031
ore+0.030
 Playing+0.030
ges+0.028
Neg logit contributions
 way-0.053
 promise-0.052
 forgot-0.049
 forget-0.047
 passengers-0.047
Token The
Token ID383
Feature activation+8.78e-02

Pos logit contributions
 This+0.031
to+0.026
 Playing+0.026
ore+0.025
anging+0.022
Neg logit contributions
 way-0.083
 promise-0.082
 forgot-0.078
 passengers-0.076
 forget-0.075
Token bird
Token ID6512
Feature activation+3.74e-02

Pos logit contributions
 forgot+0.113
ode+0.107
 promise+0.101
 hood+0.100
 scar+0.097
Neg logit contributions
-0.132
 This-0.131
 here-0.131
 late-0.130
 Playing-0.120
Token and
Token ID290
Feature activation+1.36e-02

Pos logit contributions
 promise+0.058
 way+0.057
ode+0.056
 hood+0.054
 passengers+0.054
Neg logit contributions
 This-0.056
-0.054
anging-0.053
ore-0.053
to-0.053
Token his
Token ID465
Feature activation+8.03e-02

Pos logit contributions
 promise+0.035
ode+0.034
 way+0.034
 forgot+0.033
 forget+0.032
Neg logit contributions
 This-0.009
 Playing-0.006
ges-0.006
ore-0.006
to-0.005
Token friends
Token ID2460
Feature activation+2.63e-02

Pos logit contributions
 forgot+0.106
ode+0.098
 forget+0.095
 bit+0.091
 hood+0.091
Neg logit contributions
 This-0.140
ore-0.134
uttering-0.134
oo-0.131
-0.130
Token put
Token ID1234
Feature activation-2.91e-03

Pos logit contributions
 way+0.040
 promise+0.038
 scar+0.038
 tears+0.038
ode+0.038
Neg logit contributions
 This-0.042
ore-0.039
to-0.038
-0.038
 Playing-0.037
Token their
Token ID511
Feature activation+1.12e-01

Pos logit contributions
 This+0.003
ore+0.003
to+0.003
+0.003
 late+0.003
Neg logit contributions
 forgot-0.006
 promise-0.006
 way-0.006
 forget-0.006
ode-0.006
Token plan
Token ID1410
Feature activation-2.97e-02

Pos logit contributions
 forgot+0.148
ode+0.134
 forget+0.129
 way+0.125
 hood+0.124
Neg logit contributions
 This-0.200
ore-0.191
 here-0.185
uttering-0.180
-0.179
Token to
Token ID284
Feature activation+1.37e-02

Pos logit contributions
 This+0.030
to+0.026
ore+0.025
 Playing+0.024
 late+0.022
Neg logit contributions
 way-0.069
 promise-0.068
 forgot-0.066
 forget-0.065
 passengers-0.064
Token work
Token ID670
Feature activation-3.59e-02

Pos logit contributions
 forgot+0.021
 way+0.020
ode+0.019
 bit+0.018
 promise+0.018
Neg logit contributions
 This-0.024
to-0.020
ore-0.020
 late-0.020
 Playing-0.019
Token.
Token ID13
Feature activation-3.57e-02

Pos logit contributions
 This+0.040
to+0.036
 Playing+0.035
ore+0.034
anging+0.031
Neg logit contributions
 way-0.082
 promise-0.080
 forgot-0.076
 passengers-0.073
 tears-0.073
Token The
Token ID383
Feature activation+8.51e-02

Pos logit contributions
to+0.039
ore+0.037
uttering+0.037
 This+0.036
ges+0.036
Neg logit contributions
 way-0.078
 promise-0.072
 passengers-0.069
 forgot-0.069
 tears-0.069
Token
Token ID198
Feature activation-1.28e-02

Pos logit contributions
 This+0.019
elt+0.018
ges+0.018
ays+0.018
used+0.018
Neg logit contributions
 way-0.032
 promise-0.030
 other-0.029
 forgot-0.028
 tears-0.027
TokenJoe
Token ID19585
Feature activation+4.72e-02

Pos logit contributions
 This+0.022
to+0.020
 Playing+0.020
ore+0.020
anging+0.019
Neg logit contributions
 way-0.022
 promise-0.021
 forgot-0.020
 passengers-0.019
 forget-0.019
Token and
Token ID290
Feature activation+1.70e-02

Pos logit contributions
 way+0.079
 promise+0.075
 passengers+0.073
 forget+0.071
 scar+0.068
Neg logit contributions
 This-0.075
to-0.074
anging-0.067
ore-0.067
 Playing-0.066
Token Sally
Token ID25737
Feature activation+5.62e-02

Pos logit contributions
 way+0.038
 promise+0.038
 forgot+0.036
 passengers+0.035
 forget+0.034
Neg logit contributions
 This-0.019
to-0.017
 Playing-0.016
ore-0.016
ges-0.015
Token put
Token ID1234
Feature activation-4.14e-03

Pos logit contributions
 way+0.090
 passengers+0.084
 scar+0.080
 coc+0.079
 tears+0.077
Neg logit contributions
 This-0.081
to-0.078
used-0.077
anging-0.077
 him-0.076
Token their
Token ID511
Feature activation+1.12e-01

Pos logit contributions
 This+0.005
ore+0.004
to+0.004
+0.004
ges+0.004
Neg logit contributions
 forgot-0.009
 way-0.009
 promise-0.009
 forget-0.009
ode-0.009
Token shells
Token ID19679
Feature activation-1.15e-02

Pos logit contributions
 forgot+0.150
 forget+0.126
 promise+0.117
ode+0.117
 surge+0.115
Neg logit contributions
 This-0.215
ore-0.182
 Playing-0.182
used-0.181
-0.181
Token on
Token ID319
Feature activation-1.02e-02

Pos logit contributions
 This+0.014
to+0.013
ore+0.012
 Playing+0.011
ges+0.011
Neg logit contributions
 way-0.025
 promise-0.024
 forgot-0.023
 forget-0.022
 passengers-0.022
Token the
Token ID262
Feature activation+7.40e-02

Pos logit contributions
 This+0.014
to+0.013
ore+0.012
 Playing+0.012
ges+0.012
Neg logit contributions
 way-0.020
 promise-0.020
 forgot-0.019
 passengers-0.018
 forget-0.018
Token scale
Token ID5046
Feature activation-1.61e-02

Pos logit contributions
 promise+0.087
 forgot+0.085
 passengers+0.084
 scar+0.080
ode+0.075
Neg logit contributions
 This-0.156
ore-0.137
to-0.132
 Playing-0.130
 That-0.126
Token,
Token ID11
Feature activation-6.19e-03

Pos logit contributions
 This+0.020
to+0.017
ore+0.017
 Playing+0.016
anging+0.016
Neg logit contributions
 way-0.034
 promise-0.034
 forgot-0.033
 forget-0.032
 passengers-0.031
Token
Token ID198
Feature activation-1.66e-02

Pos logit contributions
 This+0.039
to+0.035
ore+0.034
 Playing+0.034
anging+0.031
Neg logit contributions
 way-0.094
 promise-0.091
 forgot-0.087
 tears-0.084
 passengers-0.084
Token
Token ID198
Feature activation-1.60e-02

Pos logit contributions
 This+0.019
elt+0.017
 Playing+0.017
anging+0.017
uttering+0.016
Neg logit contributions
 way-0.035
 promise-0.034
 forgot-0.033
 other-0.032
 passengers-0.031
TokenThe
Token ID464
Feature activation+8.20e-02

Pos logit contributions
 This+0.022
to+0.021
 Playing+0.020
ore+0.019
anging+0.018
Neg logit contributions
 way-0.033
 promise-0.031
 forgot-0.030
 tears-0.029
 forget-0.028
Token cats
Token ID11875
Feature activation+3.34e-02

Pos logit contributions
ode+0.114
 forgot+0.109
 promise+0.102
 way+0.100
 hood+0.095
Neg logit contributions
 This-0.146
 late-0.137
 Playing-0.137
-0.127
 Today-0.124
Token put
Token ID1234
Feature activation-6.06e-03

Pos logit contributions
 way+0.052
 passengers+0.048
ode+0.048
 scar+0.047
 hood+0.047
Neg logit contributions
 This-0.051
ore-0.050
-0.046
to-0.046
used-0.045
Token their
Token ID511
Feature activation+1.11e-01

Pos logit contributions
 This+0.008
ore+0.007
to+0.006
ges+0.006
 Playing+0.006
Neg logit contributions
 promise-0.013
 way-0.013
 forgot-0.013
 forget-0.012
ode-0.012
Token paws
Token ID49193
Feature activation-2.44e-02

Pos logit contributions
 forgot+0.141
ode+0.127
 captain+0.121
 forget+0.119
 promise+0.117
Neg logit contributions
 This-0.226
 Playing-0.198
ges-0.191
ore-0.189
 That-0.187
Token up
Token ID510
Feature activation-1.23e-02

Pos logit contributions
 This+0.035
to+0.032
ore+0.031
 Playing+0.031
ges+0.029
Neg logit contributions
 way-0.048
 promise-0.047
 forgot-0.044
 passengers-0.043
 forget-0.042
Token to
Token ID284
Feature activation+7.49e-03

Pos logit contributions
 This+0.016
to+0.014
ore+0.014
 Playing+0.013
 late+0.013
Neg logit contributions
 way-0.026
 promise-0.025
 forgot-0.024
 passengers-0.024
 forget-0.023
Token each
Token ID1123
Feature activation+4.27e-02

Pos logit contributions
 way+0.014
 forgot+0.014
 promise+0.014
ode+0.014
 passengers+0.013
Neg logit contributions
 This-0.010
to-0.008
ore-0.008
ges-0.008
 Playing-0.008
Token other
Token ID584
Feature activation+1.01e-02

Pos logit contributions
 forgot+0.053
 way+0.048
ode+0.047
 promise+0.047
 passengers+0.046
Neg logit contributions
 This-0.088
ore-0.086
to-0.082
ges-0.080
 Playing-0.077
Token teacher
Token ID4701
Feature activation+1.33e-02

Pos logit contributions
 This+0.008
 Do+0.007
 Playing+0.006
 You+0.006
 Why+0.006
Neg logit contributions
 way-0.011
 forgot-0.010
 tears-0.009
ode-0.009
 heads-0.009
Token.
Token ID13
Feature activation-2.15e-02

Pos logit contributions
 way+0.029
 promise+0.028
 forgot+0.026
 passengers+0.026
 forget+0.025
Neg logit contributions
 This-0.016
to-0.015
ore-0.014
 Playing-0.014
anging-0.013
Token We
Token ID775
Feature activation+4.95e-02

Pos logit contributions
to+0.024
ore+0.021
uttering+0.021
anging+0.021
 This+0.020
Neg logit contributions
 way-0.047
 promise-0.047
 passengers-0.043
 forgot-0.043
 forget-0.042
Token will
Token ID481
Feature activation+1.46e-02

Pos logit contributions
 way+0.093
 tears+0.091
 passengers+0.089
 floor+0.084
 scar+0.081
Neg logit contributions
 This-0.068
?-0.055
 That-0.054
 Today-0.052
 Playing-0.052
Token use
Token ID779
Feature activation-3.28e-03

Pos logit contributions
 way+0.020
 promise+0.018
 forgot+0.018
 passengers+0.017
 tears+0.017
Neg logit contributions
 This-0.030
 Playing-0.026
to-0.025
ore-0.025
anging-0.025
Token our
Token ID674
Feature activation+1.11e-01

Pos logit contributions
 This+0.004
 Playing+0.004
to+0.003
ore+0.003
ges+0.003
Neg logit contributions
 promise-0.007
 forgot-0.007
 way-0.007
 forget-0.006
 passengers-0.006
Token imagination
Token ID13843
Feature activation-3.39e-02

Pos logit contributions
 promise+0.144
 forgot+0.142
 way+0.138
 passengers+0.133
 forget+0.127
Neg logit contributions
 This-0.227
 Playing-0.200
to-0.195
ore-0.188
-0.183
Token."
Token ID526
Feature activation-4.38e-02

Pos logit contributions
 This+0.039
to+0.034
ore+0.034
 Playing+0.033
anging+0.030
Neg logit contributions
 way-0.075
 promise-0.074
 forgot-0.071
 passengers-0.068
 tears-0.068
Token
Token ID198
Feature activation-2.01e-02

Pos logit contributions
to+0.049
uttering+0.047
ore+0.047
 This+0.047
used+0.046
Neg logit contributions
 way-0.094
 promise-0.089
 forgot-0.086
 tears-0.085
 other-0.083
Token
Token ID198
Feature activation-1.46e-02

Pos logit contributions
 This+0.027
used+0.027
anging+0.026
elt+0.026
uttering+0.025
Neg logit contributions
 promise-0.038
 way-0.037
 other-0.037
 tears-0.035
 passengers-0.034
TokenThey
Token ID2990
Feature activation+6.23e-02

Pos logit contributions
 This+0.022
to+0.020
ore+0.020
 Playing+0.020
anging+0.019
Neg logit contributions
 way-0.027
 promise-0.027
 forgot-0.025
 passengers-0.024
 forget-0.024
Token
Token ID198
Feature activation-1.45e-02

Pos logit contributions
 This+0.018
 Playing+0.016
to+0.015
ore+0.015
elt+0.014
Neg logit contributions
 way-0.045
 promise-0.044
 forgot-0.042
 passengers-0.041
 tears-0.040
TokenSo
Token ID2396
Feature activation-8.55e-03

Pos logit contributions
 This+0.025
to+0.024
 Playing+0.022
ore+0.022
anging+0.021
Neg logit contributions
 way-0.025
 promise-0.024
 forgot-0.022
 forget-0.021
 tears-0.021
Token the
Token ID262
Feature activation+7.76e-02

Pos logit contributions
 This+0.008
ore+0.006
used+0.006
to+0.006
 That+0.006
Neg logit contributions
ode-0.020
 promise-0.020
 hood-0.019
 way-0.019
 forgot-0.019
Token kids
Token ID3988
Feature activation+3.31e-02

Pos logit contributions
ode+0.110
 promise+0.105
 forgot+0.102
 forget+0.098
 scar+0.097
Neg logit contributions
 This-0.136
 Playing-0.125
 late-0.124
-0.124
 here-0.122
Token collected
Token ID7723
Feature activation+4.51e-03

Pos logit contributions
 way+0.054
 promise+0.049
 forget+0.048
 tears+0.048
 scar+0.047
Neg logit contributions
to-0.052
 This-0.051
ore-0.050
anging-0.049
ges-0.048
Token their
Token ID511
Feature activation+1.11e-01

Pos logit contributions
 promise+0.010
 forgot+0.009
 forget+0.009
 way+0.009
 passengers+0.009
Neg logit contributions
 This-0.006
ore-0.005
to-0.005
-0.005
 late-0.004
Token umb
Token ID20810
Feature activation-9.61e-03

Pos logit contributions
 forgot+0.134
 promise+0.128
 way+0.127
 passengers+0.123
 forget+0.120
Neg logit contributions
 This-0.230
to-0.208
 Playing-0.202
ore-0.202
-0.200
Tokenrell
Token ID11252
Feature activation-6.94e-03

Pos logit contributions
 This+0.018
to+0.017
ore+0.017
 Playing+0.017
ges+0.016
Neg logit contributions
 way-0.015
 promise-0.013
 forgot-0.012
 passengers-0.012
 pile-0.012
Tokenas
Token ID292
Feature activation+1.34e-03

Pos logit contributions
 This+0.014
to+0.013
ore+0.013
 Playing+0.013
anging+0.013
Neg logit contributions
 way-0.010
 promise-0.009
 forgot-0.008
 tears-0.008
 forget-0.008
Token and
Token ID290
Feature activation+3.05e-02

Pos logit contributions
 way+0.003
 promise+0.003
 forgot+0.003
 forget+0.002
 passengers+0.002
Neg logit contributions
 This-0.002
to-0.002
ore-0.002
 Playing-0.002
anging-0.002
Token went
Token ID1816
Feature activation-1.36e-02

Pos logit contributions
 promise+0.049
ode+0.045
 way+0.042
 forget+0.041
 hood+0.040
Neg logit contributions
 This-0.048
to-0.048
elt-0.047
ges-0.045
ing-0.044
Token "
Token ID366
Feature activation-4.05e-02

Pos logit contributions
 way+0.029
 promise+0.028
 forgot+0.026
 passengers+0.025
 forget+0.025
Neg logit contributions
 This-0.036
to-0.034
 Playing-0.033
ore-0.033
anging-0.031
TokenI
Token ID40
Feature activation+6.96e-03

Pos logit contributions
 This+0.057
 Playing+0.052
to+0.051
ore+0.051
anging+0.048
Neg logit contributions
 way-0.078
 promise-0.077
 forgot-0.073
 forget-0.070
 bit-0.069
Token want
Token ID765
Feature activation-3.78e-02

Pos logit contributions
 way+0.012
 promise+0.011
 forgot+0.010
 passengers+0.010
 tears+0.010
Neg logit contributions
 This-0.012
to-0.011
ore-0.011
 Playing-0.011
anging-0.010
Token to
Token ID284
Feature activation-1.37e-02

Pos logit contributions
 This+0.042
to+0.035
 Playing+0.034
ore+0.033
ges+0.029
Neg logit contributions
 way-0.086
 promise-0.086
 forgot-0.083
 passengers-0.080
 forget-0.079
Token c
Token ID269
Feature activation-7.47e-02

Pos logit contributions
 This+0.027
to+0.023
ore+0.022
 Playing+0.022
ges+0.021
Neg logit contributions
 way-0.019
 forgot-0.018
 promise-0.018
 passengers-0.017
 tears-0.017
Tokenuddle
Token ID24500
Feature activation-1.21e-01

Pos logit contributions
 This+0.188
ges+0.182
 Do+0.180
anging+0.173
 Why+0.173
Neg logit contributions
 promise-0.052
 scar-0.039
 way-0.036
 crown-0.035
 hood-0.031
Token with
Token ID351
Feature activation-2.22e-02

Pos logit contributions
to+0.158
 This+0.157
anging+0.153
 Playing+0.151
uttering+0.146
Neg logit contributions
 way-0.234
 promise-0.233
 bit-0.214
 pile-0.211
 other-0.208
Token you
Token ID345
Feature activation+6.81e-03

Pos logit contributions
 This+0.033
to+0.030
 Playing+0.030
ore+0.029
ges+0.027
Neg logit contributions
 way-0.042
 promise-0.041
 forgot-0.039
 forget-0.037
 passengers-0.037
Token,
Token ID11
Feature activation-2.66e-02

Pos logit contributions
 way+0.015
 promise+0.014
 forgot+0.014
 passengers+0.013
 forget+0.013
Neg logit contributions
 This-0.008
to-0.008
 Playing-0.007
ore-0.007
anging-0.007
Token mom
Token ID1995
Feature activation-6.91e-04

Pos logit contributions
 This+0.039
 Playing+0.034
to+0.033
ore+0.032
 Do+0.031
Neg logit contributions
 way-0.050
 promise-0.048
 forgot-0.048
 tears-0.045
 passengers-0.045
Token.
Token ID13
Feature activation-4.82e-02

Pos logit contributions
 This+0.001
to+0.001
ore+0.001
 Playing+0.001
uttering+0.001
Neg logit contributions
 way-0.001
 promise-0.001
 forgot-0.001
 bit-0.001
 forget-0.001
Token the
Token ID262
Feature activation+4.48e-02

Pos logit contributions
 This+0.034
 Playing+0.029
ore+0.029
to+0.028
+0.026
Neg logit contributions
 promise-0.048
 way-0.047
 forgot-0.045
 passengers-0.044
 forget-0.043
Token bird
Token ID6512
Feature activation-9.70e-03

Pos logit contributions
 forgot+0.056
 promise+0.054
 way+0.052
 forget+0.048
 passengers+0.046
Neg logit contributions
 This-0.087
ore-0.081
 Playing-0.081
-0.080
 late-0.078
Token suddenly
Token ID6451
Feature activation-2.51e-02

Pos logit contributions
 This+0.019
to+0.018
ore+0.018
 Playing+0.018
anging+0.017
Neg logit contributions
 way-0.013
 promise-0.013
 passengers-0.011
 forgot-0.011
 tears-0.011
Token began
Token ID2540
Feature activation-7.88e-02

Pos logit contributions
 This+0.047
to+0.044
ore+0.043
 Playing+0.043
ges+0.041
Neg logit contributions
 way-0.037
 promise-0.036
 forgot-0.033
 passengers-0.032
 forget-0.031
Token to
Token ID284
Feature activation-7.41e-03

Pos logit contributions
 This+0.084
to+0.074
 Playing+0.073
ore+0.072
anging+0.064
Neg logit contributions
 way-0.184
 promise-0.177
 forgot-0.170
 passengers-0.164
 forget-0.164
Token yawn
Token ID40908
Feature activation-1.16e-01

Pos logit contributions
 This+0.014
to+0.013
ore+0.013
 Playing+0.012
used+0.012
Neg logit contributions
 way-0.010
 promise-0.009
 forgot-0.009
 passengers-0.009
 scar-0.008
Token with
Token ID351
Feature activation-9.90e-03

Pos logit contributions
 Playing+0.157
 This+0.157
ges+0.138
to+0.138
 Do+0.135
Neg logit contributions
 way-0.218
 promise-0.205
 forgot-0.204
 bit-0.200
 forget-0.188
Token joy
Token ID8716
Feature activation-7.71e-02

Pos logit contributions
 This+0.019
ore+0.017
to+0.017
 Playing+0.017
ges+0.016
Neg logit contributions
 way-0.014
 promise-0.014
 forgot-0.013
ode-0.012
 passengers-0.012
Token.
Token ID13
Feature activation-5.97e-02

Pos logit contributions
 This+0.117
 Playing+0.107
to+0.104
ore+0.103
anging+0.094
Neg logit contributions
 way-0.147
 promise-0.136
 forgot-0.135
 bit-0.127
 passengers-0.127
Token
Token ID220
Feature activation-6.83e-02

Pos logit contributions
uttering+0.065
ore+0.065
to+0.063
 This+0.062
anging+0.062
Neg logit contributions
 way-0.124
 promise-0.115
 forgot-0.112
 tears-0.110
 passengers-0.108
Token
Token ID198
Feature activation-4.10e-02

Pos logit contributions
used+0.078
uttering+0.078
 This+0.078
anging+0.078
elt+0.075
Neg logit contributions
 way-0.125
 promise-0.116
 tears-0.113
 other-0.112
 forgot-0.110
Token they
Token ID484
Feature activation+4.74e-02

Pos logit contributions
 promise+0.034
 way+0.033
 passengers+0.030
 forget+0.029
 forgot+0.029
Neg logit contributions
 This-0.032
to-0.031
ore-0.028
 late-0.028
elt-0.027
Token began
Token ID2540
Feature activation-4.32e-02

Pos logit contributions
 way+0.078
 promise+0.073
 forget+0.067
 passengers+0.063
 tears+0.062
Neg logit contributions
to-0.079
 This-0.073
ges-0.073
anging-0.073
elt-0.072
Token to
Token ID284
Feature activation+2.22e-02

Pos logit contributions
 Playing+0.057
 This+0.057
ore+0.052
ires+0.050
to+0.049
Neg logit contributions
 way-0.088
 promise-0.078
 tears-0.078
 pile-0.076
 bit-0.076
Token carefully
Token ID7773
Feature activation+7.11e-04

Pos logit contributions
 way+0.029
 promise+0.028
 forgot+0.027
 passengers+0.026
 tears+0.024
Neg logit contributions
 This-0.045
to-0.042
ore-0.040
 Playing-0.040
anging-0.039
Token ch
Token ID442
Feature activation-4.34e-02

Pos logit contributions
 way+0.001
 promise+0.001
 forgot+0.001
 pile+0.001
 tears+0.001
Neg logit contributions
 This-0.001
 Playing-0.001
to-0.001
ore-0.001
uttering-0.001
Tokenisel
Token ID36811
Feature activation-1.15e-01

Pos logit contributions
 This+0.082
to+0.076
 Playing+0.076
ore+0.074
anging+0.070
Neg logit contributions
 way-0.066
 promise-0.064
 forgot-0.059
 passengers-0.056
 tears-0.056
Token the
Token ID262
Feature activation+7.66e-02

Pos logit contributions
 This+0.179
 Playing+0.164
ore+0.155
to+0.152
elt+0.143
Neg logit contributions
 way-0.223
 promise-0.203
 forgot-0.197
 passengers-0.190
 tears-0.190
Token rock
Token ID3881
Feature activation-3.27e-02

Pos logit contributions
 forgot+0.093
 promise+0.087
 passengers+0.083
 forget+0.075
 way+0.075
Neg logit contributions
 This-0.141
ore-0.141
-0.136
ing-0.131
to-0.129
Token.
Token ID13
Feature activation-4.79e-02

Pos logit contributions
 This+0.041
 Playing+0.037
to+0.037
ore+0.035
elt+0.032
Neg logit contributions
 way-0.070
 promise-0.067
 forgot-0.064
 bit-0.062
 passengers-0.061
Token They
Token ID1119
Feature activation+5.02e-02

Pos logit contributions
uttering+0.059
ore+0.054
anging+0.054
ges+0.053
to+0.052
Neg logit contributions
 way-0.099
 tears-0.089
 promise-0.087
 forgot-0.084
 other-0.084
Token kept
Token ID4030
Feature activation-2.20e-02

Pos logit contributions
 promise+0.087
 way+0.086
 deal+0.073
 difference+0.072
 feelings+0.072
Neg logit contributions
to-0.076
ges-0.075
anging-0.072
 him-0.070
 This-0.069
Token he
Token ID339
Feature activation+3.96e-02

Pos logit contributions
 promise+0.031
 way+0.026
ode+0.025
 forget+0.024
 eye+0.023
Neg logit contributions
 This-0.028
 Playing-0.025
to-0.025
 late-0.024
 spending-0.024
Token tried
Token ID3088
Feature activation-6.80e-02

Pos logit contributions
 way+0.062
 promise+0.062
 passengers+0.058
ode+0.057
 forget+0.053
Neg logit contributions
to-0.062
 This-0.061
ore-0.057
 Playing-0.056
-0.053
Token to
Token ID284
Feature activation+3.55e-03

Pos logit contributions
 This+0.073
 Playing+0.063
to+0.063
ore+0.062
anging+0.056
Neg logit contributions
 way-0.160
 promise-0.153
 forgot-0.147
 passengers-0.142
 tears-0.142
Token take
Token ID1011
Feature activation-2.58e-02

Pos logit contributions
 way+0.005
 forgot+0.005
 passengers+0.005
 promise+0.005
ode+0.005
Neg logit contributions
 This-0.006
to-0.005
ore-0.005
oo-0.005
 him-0.005
Token deep
Token ID2769
Feature activation-3.80e-02

Pos logit contributions
 This+0.033
to+0.029
ore+0.027
 Playing+0.026
ges+0.025
Neg logit contributions
 promise-0.057
 way-0.054
 forgot-0.054
 forget-0.052
ode-0.049
Token breaths
Token ID45576
Feature activation-1.14e-01

Pos logit contributions
 This+0.083
to+0.079
 Playing+0.078
ore+0.077
anging+0.074
Neg logit contributions
 way-0.047
 promise-0.043
 forgot-0.040
 tears-0.038
 passengers-0.037
Token to
Token ID284
Feature activation-9.20e-03

Pos logit contributions
 This+0.154
to+0.141
 Playing+0.140
ore+0.135
anging+0.125
Neg logit contributions
 way-0.233
 promise-0.224
 forgot-0.213
 passengers-0.204
 forget-0.203
Token calm
Token ID9480
Feature activation-7.02e-02

Pos logit contributions
 This+0.017
to+0.016
ore+0.016
 Playing+0.015
ges+0.015
Neg logit contributions
 way-0.013
 promise-0.013
 forgot-0.013
 passengers-0.012
ode-0.011
Token down
Token ID866
Feature activation-4.07e-02

Pos logit contributions
 This+0.082
 Playing+0.077
to+0.076
ore+0.073
uttering+0.070
Neg logit contributions
 way-0.157
 promise-0.147
 forgot-0.140
 tears-0.140
 passengers-0.139
Token.
Token ID13
Feature activation-5.70e-02

Pos logit contributions
 This+0.055
to+0.054
 Playing+0.053
elt+0.049
ore+0.049
Neg logit contributions
 way-0.083
 promise-0.076
 tears-0.072
 bit-0.072
 passengers-0.071
Token Tim
Token ID5045
Feature activation+3.77e-02

Pos logit contributions
uttering+0.077
ges+0.072
ore+0.072
anging+0.070
to+0.070
Neg logit contributions
 way-0.114
 promise-0.101
 forgot-0.098
 tears-0.097
 pile-0.093
Token you
Token ID345
Feature activation-3.89e-03

Pos logit contributions
 promise+0.041
ode+0.040
 way+0.040
 passengers+0.037
 scar+0.037
Neg logit contributions
 This-0.018
 Playing-0.014
 late-0.014
ges-0.013
ore-0.013
Token go
Token ID467
Feature activation-7.14e-02

Pos logit contributions
 This+0.007
to+0.006
ore+0.006
 Playing+0.006
ges+0.005
Neg logit contributions
 way-0.007
 promise-0.006
 forgot-0.006
 passengers-0.006
 tears-0.006
Token,
Token ID11
Feature activation-3.70e-02

Pos logit contributions
 This+0.102
 Playing+0.094
to+0.093
ore+0.088
ges+0.086
Neg logit contributions
 way-0.144
 promise-0.138
 forgot-0.129
 passengers-0.125
 forget-0.125
Token my
Token ID616
Feature activation+4.04e-02

Pos logit contributions
 This+0.059
to+0.052
 Playing+0.052
ore+0.050
 Do+0.047
Neg logit contributions
 way-0.064
 promise-0.062
 forgot-0.060
 tears-0.057
 passengers-0.057
Token d
Token ID288
Feature activation-3.62e-02

Pos logit contributions
 forgot+0.046
 way+0.044
 forget+0.039
 promise+0.039
 passengers+0.038
Neg logit contributions
 This-0.083
ore-0.080
to-0.078
-0.075
 Playing-0.074
Tokenarl
Token ID7063
Feature activation-1.12e-01

Pos logit contributions
 This+0.041
 Playing+0.037
to+0.036
ore+0.033
anging+0.031
Neg logit contributions
 promise-0.078
 way-0.078
 forgot-0.073
 passengers-0.071
 forget-0.070
Tokenings
Token ID654
Feature activation-6.91e-02

Pos logit contributions
 This+0.127
 Playing+0.118
to+0.113
ore+0.105
anging+0.102
Neg logit contributions
 way-0.261
 promise-0.250
 forgot-0.236
 forget-0.226
 passengers-0.223
Token.
Token ID13
Feature activation-5.77e-02

Pos logit contributions
 This+0.088
to+0.087
 Playing+0.082
uttering+0.082
anging+0.082
Neg logit contributions
 way-0.140
 promise-0.135
 forgot-0.127
 bit-0.124
 forget-0.120
Token Enjoy
Token ID18179
Feature activation-6.26e-02

Pos logit contributions
to+0.056
uttering+0.056
anging+0.050
ore+0.050
overed+0.046
Neg logit contributions
 promise-0.128
 way-0.127
 passengers-0.120
 forget-0.118
 forgot-0.116
Token your
Token ID534
Feature activation+4.99e-02

Pos logit contributions
 This+0.092
 Playing+0.086
to+0.084
elt+0.081
uttering+0.080
Neg logit contributions
 way-0.124
 promise-0.119
 forgot-0.108
 scar-0.106
 bit-0.106
Token lunch
Token ID9965
Feature activation-6.98e-02

Pos logit contributions
 way+0.064
 forgot+0.063
 promise+0.060
 passengers+0.057
 forget+0.056
Neg logit contributions
 This-0.100
to-0.092
ore-0.091
 Playing-0.089
-0.085
Token't
Token ID470
Feature activation-1.10e-02

Pos logit contributions
elt+0.066
to+0.066
 This+0.065
 Playing+0.065
uttering+0.064
Neg logit contributions
 way-0.140
 promise-0.138
 forget-0.130
 forgot-0.126
 tears-0.125
Token want
Token ID765
Feature activation-5.16e-02

Pos logit contributions
 This+0.021
to+0.019
ore+0.018
ges+0.018
 Playing+0.018
Neg logit contributions
 way-0.016
 promise-0.014
 tears-0.014
 scar-0.014
 forgot-0.013
Token to
Token ID284
Feature activation-2.13e-02

Pos logit contributions
 This+0.053
to+0.045
 Playing+0.043
ore+0.042
ges+0.038
Neg logit contributions
 promise-0.121
 way-0.121
 forgot-0.116
 passengers-0.111
 forget-0.110
Token go
Token ID467
Feature activation-6.40e-02

Pos logit contributions
 This+0.040
to+0.035
ore+0.034
 Playing+0.034
ges+0.032
Neg logit contributions
 way-0.031
 promise-0.029
 forgot-0.029
 passengers-0.028
 tears-0.027
Token to
Token ID284
Feature activation-3.61e-02

Pos logit contributions
 This+0.097
 Playing+0.091
to+0.090
ore+0.085
anging+0.084
Neg logit contributions
 way-0.124
 promise-0.118
 forgot-0.109
 passengers-0.107
 forget-0.106
Token bed
Token ID3996
Feature activation-1.12e-01

Pos logit contributions
 This+0.055
to+0.051
 Playing+0.050
ore+0.049
anging+0.047
Neg logit contributions
 way-0.069
 promise-0.066
 forgot-0.062
 passengers-0.060
 forget-0.060
Token yet
Token ID1865
Feature activation-3.40e-02

Pos logit contributions
 This+0.163
to+0.155
 Playing+0.153
elt+0.147
ges+0.146
Neg logit contributions
 way-0.219
 promise-0.205
 forgot-0.197
 bit-0.185
 tears-0.183
Token.
Token ID13
Feature activation-6.77e-02

Pos logit contributions
 This+0.043
to+0.040
 Playing+0.039
ore+0.038
anging+0.036
Neg logit contributions
 way-0.074
 promise-0.071
 forgot-0.067
 forget-0.065
 passengers-0.064
Token I
Token ID314
Feature activation+8.87e-03

Pos logit contributions
uttering+0.081
to+0.076
ore+0.073
anging+0.072
ing+0.070
Neg logit contributions
 way-0.139
 promise-0.135
 forgot-0.126
 passengers-0.125
 forget-0.125
Token want
Token ID765
Feature activation-2.76e-02

Pos logit contributions
 way+0.014
 passengers+0.013
ode+0.012
 tears+0.012
 promise+0.012
Neg logit contributions
 This-0.016
to-0.015
ore-0.015
 late-0.014
-0.014
Token to
Token ID284
Feature activation-6.10e-03

Pos logit contributions
 This+0.023
to+0.019
 Playing+0.018
ore+0.018
 late+0.015
Neg logit contributions
 promise-0.071
 way-0.070
 forgot-0.068
 forget-0.065
 passengers-0.065
Token not
Token ID407
Feature activation+4.62e-04

Pos logit contributions
 This+0.003
to+0.003
ore+0.003
 Playing+0.003
ges+0.003
Neg logit contributions
 promise-0.005
 way-0.005
 forgot-0.005
 forget-0.005
ode-0.004
Token want
Token ID765
Feature activation-5.00e-02

Pos logit contributions
 way+0.001
 promise+0.001
 forgot+0.001
 passengers+0.001
 tears+0.001
Neg logit contributions
 This-0.001
to-0.001
 Playing-0.001
ore-0.001
anging-0.001
Token to
Token ID284
Feature activation-1.86e-02

Pos logit contributions
 This+0.047
to+0.039
 Playing+0.036
ore+0.036
ges+0.032
Neg logit contributions
 promise-0.121
 way-0.119
 forgot-0.116
 passengers-0.110
 forget-0.110
Token go
Token ID467
Feature activation-6.18e-02

Pos logit contributions
 This+0.036
to+0.032
ore+0.031
 Playing+0.031
ges+0.030
Neg logit contributions
 way-0.025
 promise-0.024
 forgot-0.024
 passengers-0.022
 scar-0.022
Token to
Token ID284
Feature activation-3.68e-02

Pos logit contributions
 This+0.099
to+0.091
 Playing+0.091
ore+0.088
anging+0.085
Neg logit contributions
 way-0.114
 promise-0.109
 forgot-0.102
 passengers-0.098
 forget-0.098
Token bed
Token ID3996
Feature activation-1.12e-01

Pos logit contributions
 This+0.057
to+0.055
 Playing+0.053
ore+0.052
anging+0.051
Neg logit contributions
 way-0.069
 promise-0.065
 forgot-0.060
 forget-0.059
 passengers-0.059
Token.
Token ID13
Feature activation-6.87e-02

Pos logit contributions
 This+0.164
to+0.155
 Playing+0.154
elt+0.146
ges+0.144
Neg logit contributions
 way-0.220
 promise-0.206
 forgot-0.198
 tears-0.186
 bit-0.186
Token She
Token ID1375
Feature activation+4.55e-02

Pos logit contributions
uttering+0.087
to+0.080
anging+0.077
ore+0.076
ing+0.076
Neg logit contributions
 way-0.139
 promise-0.134
 forgot-0.125
 passengers-0.124
 tears-0.123
Token wanted
Token ID2227
Feature activation-3.49e-02

Pos logit contributions
 way+0.077
 passengers+0.073
ode+0.071
 promise+0.071
 captain+0.067
Neg logit contributions
 This-0.069
 Playing-0.065
-0.063
to-0.063
ore-0.061
Token to
Token ID284
Feature activation-3.21e-03

Pos logit contributions
 This+0.023
to+0.018
ore+0.016
 Playing+0.015
 late+0.014
Neg logit contributions
 promise-0.097
 forgot-0.093
 way-0.092
 forget-0.089
 surge-0.089
Token play
Token ID711
Feature activation-6.48e-02

Pos logit contributions
 This+0.005
ore+0.004
to+0.004
?+0.004
 She+0.004
Neg logit contributions
 forgot-0.005
 way-0.005
ode-0.005
 passengers-0.005
 promise-0.004
Token were
Token ID547
Feature activation+8.15e-03

Pos logit contributions
 way+0.032
 scar+0.028
ode+0.027
 passengers+0.027
 promise+0.027
Neg logit contributions
 This-0.033
ore-0.030
 Playing-0.029
-0.029
to-0.029
Token both
Token ID1111
Feature activation+3.59e-02

Pos logit contributions
 way+0.014
 promise+0.014
ode+0.013
 forgot+0.013
 forget+0.013
Neg logit contributions
 This-0.012
 late-0.011
 Playing-0.011
 spending-0.010
 here-0.010
Token too
Token ID1165
Feature activation+9.52e-03

Pos logit contributions
 way+0.057
ode+0.056
 promise+0.056
 scar+0.055
 forgot+0.054
Neg logit contributions
 This-0.057
 late-0.052
ore-0.051
 Playing-0.048
ges-0.047
Token young
Token ID1862
Feature activation-4.48e-02

Pos logit contributions
 way+0.017
 promise+0.016
 forgot+0.015
 forget+0.014
 passengers+0.014
Neg logit contributions
 This-0.016
to-0.015
 Playing-0.015
ore-0.014
anging-0.013
Token to
Token ID284
Feature activation+2.60e-03

Pos logit contributions
 This+0.050
to+0.045
 Playing+0.044
ore+0.043
anging+0.039
Neg logit contributions
 way-0.101
 promise-0.098
 forgot-0.094
 passengers-0.091
 forget-0.090
Token argue
Token ID7267
Feature activation-1.12e-01

Pos logit contributions
 way+0.004
 forgot+0.003
 promise+0.003
 tears+0.003
 scar+0.003
Neg logit contributions
 This-0.005
to-0.004
ore-0.004
 Playing-0.004
used-0.004
Token over
Token ID625
Feature activation-4.87e-02

Pos logit contributions
 This+0.154
to+0.147
ore+0.141
 Playing+0.137
elt+0.133
Neg logit contributions
 way-0.227
 promise-0.215
 forgot-0.203
 forget-0.194
 passengers-0.193
Token the
Token ID262
Feature activation+4.51e-02

Pos logit contributions
 This+0.068
to+0.060
 Playing+0.059
ore+0.059
ges+0.055
Neg logit contributions
 way-0.096
 promise-0.094
 forgot-0.090
 passengers-0.085
 forget-0.085
Token television
Token ID5581
Feature activation-5.58e-02

Pos logit contributions
 forgot+0.055
 promise+0.050
 way+0.047
ode+0.045
 passengers+0.044
Neg logit contributions
 This-0.089
ore-0.082
 Playing-0.080
 late-0.080
-0.079
Token.
Token ID13
Feature activation-6.54e-02

Pos logit contributions
 This+0.063
ore+0.053
 Playing+0.051
to+0.051
anging+0.045
Neg logit contributions
 way-0.123
 promise-0.122
 forgot-0.119
 passengers-0.116
 tears-0.114
Token
Token ID198
Feature activation-4.35e-02

Pos logit contributions
to+0.070
ore+0.069
uttering+0.068
 This+0.067
anging+0.066
Neg logit contributions
 way-0.139
 promise-0.131
 forgot-0.127
 tears-0.123
 passengers-0.123
Token opinions
Token ID9317
Feature activation-7.42e-02

Pos logit contributions
 This+0.030
 Playing+0.028
ore+0.028
to+0.028
ges+0.026
Neg logit contributions
 promise-0.021
 forgot-0.021
 way-0.021
 forget-0.019
 passengers-0.018
Token.
Token ID13
Feature activation-6.36e-02

Pos logit contributions
 This+0.102
to+0.096
ore+0.091
 Playing+0.091
anging+0.087
Neg logit contributions
 way-0.151
 promise-0.144
 forgot-0.136
 forget-0.130
 passengers-0.129
Token They
Token ID1119
Feature activation+3.41e-02

Pos logit contributions
uttering+0.067
to+0.066
ore+0.065
anging+0.061
ges+0.058
Neg logit contributions
 way-0.136
 promise-0.133
 forgot-0.124
 passengers-0.124
 forget-0.123
Token start
Token ID923
Feature activation-5.79e-02

Pos logit contributions
 way+0.054
ode+0.047
 passengers+0.047
 tears+0.045
 scar+0.044
Neg logit contributions
 This-0.054
 She-0.048
 him-0.046
?-0.045
 Playing-0.045
Token to
Token ID284
Feature activation-6.05e-03

Pos logit contributions
 This+0.065
to+0.057
 Playing+0.056
ore+0.056
anging+0.050
Neg logit contributions
 way-0.132
 promise-0.128
 forgot-0.122
 passengers-0.118
 forget-0.118
Token argue
Token ID7267
Feature activation-1.12e-01

Pos logit contributions
 This+0.011
 Playing+0.009
to+0.009
ges+0.009
ore+0.009
Neg logit contributions
 way-0.008
 promise-0.008
 forgot-0.008
ode-0.008
 passengers-0.008
Token.
Token ID13
Feature activation-6.50e-02

Pos logit contributions
 This+0.181
to+0.176
ore+0.172
elt+0.165
 Playing+0.162
Neg logit contributions
 way-0.200
 promise-0.185
 forgot-0.174
 tears-0.167
 other-0.164
Token They
Token ID1119
Feature activation+3.98e-02

Pos logit contributions
to+0.083
ore+0.081
uttering+0.081
anging+0.080
used+0.073
Neg logit contributions
 way-0.125
 promise-0.115
 other-0.114
 tears-0.113
 passengers-0.111
Token say
Token ID910
Feature activation-1.80e-02

Pos logit contributions
 way+0.071
 crew+0.068
 passengers+0.066
ode+0.065
 coc+0.063
Neg logit contributions
 This-0.056
 him-0.048
 She-0.048
?-0.045
 Why-0.045
Token,
Token ID11
Feature activation-1.32e-02

Pos logit contributions
 This+0.023
to+0.021
ore+0.020
 Playing+0.020
anging+0.019
Neg logit contributions
 way-0.038
 promise-0.037
 forgot-0.035
 passengers-0.034
 forget-0.034
Token "
Token ID366
Feature activation-1.98e-02

Pos logit contributions
to+0.016
ore+0.016
 This+0.014
uttering+0.014
ays+0.014
Neg logit contributions
 way-0.027
 promise-0.026
 forgot-0.025
 tears-0.025
 forget-0.024
Token and
Token ID290
Feature activation-1.10e-02

Pos logit contributions
 promise+0.053
 way+0.052
 forgot+0.050
ode+0.048
 forget+0.048
Neg logit contributions
 This-0.040
 late-0.038
 Playing-0.035
to-0.035
 Do-0.033
Token hide
Token ID7808
Feature activation-7.29e-02

Pos logit contributions
 This+0.019
to+0.018
 Playing+0.017
ore+0.017
 late+0.016
Neg logit contributions
 way-0.017
 promise-0.016
ode-0.015
 forgot-0.015
 passengers-0.015
Token-
Token ID12
Feature activation-2.16e-02

Pos logit contributions
 This+0.090
to+0.082
ore+0.081
 Playing+0.080
ges+0.075
Neg logit contributions
 way-0.155
 promise-0.152
 forgot-0.144
 forget-0.139
 passengers-0.138
Tokenand
Token ID392
Feature activation-5.87e-02

Pos logit contributions
to+0.021
ore+0.018
 This+0.018
 late+0.016
ges+0.015
Neg logit contributions
 way-0.054
 promise-0.053
 forgot-0.050
 forget-0.050
 tears-0.049
Token-
Token ID12
Feature activation-3.27e-02

Pos logit contributions
 This+0.077
to+0.070
ore+0.068
 Playing+0.068
anging+0.062
Neg logit contributions
 way-0.122
 promise-0.119
 forgot-0.113
 forget-0.108
 passengers-0.108
Tokenseek
Token ID36163
Feature activation-1.12e-01

Pos logit contributions
 This+0.041
to+0.037
 Playing+0.036
ore+0.036
anging+0.033
Neg logit contributions
 way-0.070
 promise-0.068
 forgot-0.065
 passengers-0.062
 forget-0.062
Token.
Token ID13
Feature activation-6.90e-02

Pos logit contributions
 This+0.133
to+0.119
 Playing+0.116
ore+0.115
anging+0.105
Neg logit contributions
 way-0.246
 promise-0.239
 forgot-0.228
 passengers-0.220
 forget-0.218
Token The
Token ID383
Feature activation+6.17e-02

Pos logit contributions
 This+0.079
to+0.078
ore+0.077
anging+0.074
uttering+0.073
Neg logit contributions
 way-0.144
 promise-0.135
 forgot-0.131
 passengers-0.129
 tears-0.126
Token monkey
Token ID21657
Feature activation+1.39e-02

Pos logit contributions
 forgot+0.077
 promise+0.073
 way+0.069
ode+0.067
 forget+0.064
Neg logit contributions
 This-0.108
ore-0.105
 late-0.104
-0.104
 Playing-0.101
Token was
Token ID373
Feature activation+1.77e-02

Pos logit contributions
 promise+0.023
 way+0.021
 hood+0.021
 passengers+0.021
ode+0.021
Neg logit contributions
 This-0.020
 Playing-0.019
to-0.018
-0.018
ore-0.018
Token very
Token ID845
Feature activation+2.15e-02

Pos logit contributions
 promise+0.032
 way+0.029
ode+0.028
 forget+0.027
 forgot+0.027
Neg logit contributions
 This-0.027
 late-0.026
 Playing-0.025
to-0.025
ore-0.023
Token she
Token ID673
Feature activation+1.82e-02

Pos logit contributions
 passengers+0.048
 way+0.047
 promise+0.046
ode+0.045
 scar+0.042
Neg logit contributions
 This-0.054
 Playing-0.047
to-0.047
 That-0.047
elt-0.045
Token had
Token ID550
Feature activation-1.48e-03

Pos logit contributions
 way+0.024
 promise+0.023
 passengers+0.022
ode+0.020
 tears+0.020
Neg logit contributions
 This-0.036
to-0.034
ore-0.033
 Playing-0.032
-0.032
Token to
Token ID284
Feature activation-3.97e-03

Pos logit contributions
 This+0.003
to+0.002
 Playing+0.002
ore+0.002
elt+0.002
Neg logit contributions
 promise-0.002
 way-0.002
 passengers-0.002
 forgot-0.002
 forget-0.002
Token go
Token ID467
Feature activation-5.79e-02

Pos logit contributions
 This+0.007
to+0.006
ore+0.006
 late+0.006
?+0.006
Neg logit contributions
 way-0.005
 forgot-0.005
 passengers-0.005
 scar-0.005
ode-0.005
Token to
Token ID284
Feature activation-2.98e-02

Pos logit contributions
 This+0.092
 Playing+0.086
to+0.085
ore+0.081
anging+0.079
Neg logit contributions
 way-0.107
 promise-0.103
 forgot-0.095
 forget-0.093
 passengers-0.091
Token bed
Token ID3996
Feature activation-1.11e-01

Pos logit contributions
 This+0.045
to+0.042
 Playing+0.041
ore+0.041
anging+0.038
Neg logit contributions
 way-0.056
 promise-0.054
 forgot-0.051
 forget-0.049
 passengers-0.049
Token with
Token ID351
Feature activation-1.75e-02

Pos logit contributions
 This+0.164
 Playing+0.157
to+0.154
elt+0.148
ore+0.144
Neg logit contributions
 way-0.216
 promise-0.199
 forgot-0.194
 tears-0.186
 bit-0.181
Token no
Token ID645
Feature activation+2.10e-02

Pos logit contributions
 This+0.018
to+0.015
ore+0.015
 Playing+0.015
+0.013
Neg logit contributions
 promise-0.041
 way-0.041
 forgot-0.039
 passengers-0.038
 forget-0.038
Token chalk
Token ID30860
Feature activation-7.01e-02

Pos logit contributions
 forgot+0.030
 promise+0.027
 way+0.026
 forget+0.026
ode+0.025
Neg logit contributions
 This-0.037
 late-0.034
ore-0.034
 Today-0.034
 Playing-0.034
Token.
Token ID13
Feature activation-6.03e-02

Pos logit contributions
 This+0.083
to+0.074
 Playing+0.072
ore+0.072
ges+0.065
Neg logit contributions
 way-0.153
 promise-0.151
 forgot-0.143
 passengers-0.138
 forget-0.137
Token<|endoftext|>
Token ID50256
Feature activation-6.23e-02

Pos logit contributions
uttering+0.061
ore+0.060
to+0.058
anging+0.055
ges+0.054
Neg logit contributions
 way-0.134
 promise-0.125
 forgot-0.123
 tears-0.119
 forget-0.119
Token her
Token ID607
Feature activation+5.10e-02

Pos logit contributions
 This+0.083
 Playing+0.078
to+0.077
ore+0.076
anging+0.072
Neg logit contributions
 way-0.123
 tears-0.112
 promise-0.110
 forgot-0.106
 bit-0.104
Token eyes
Token ID2951
Feature activation-4.58e-02

Pos logit contributions
 forgot+0.064
 promise+0.058
 way+0.057
 passengers+0.057
 forget+0.056
Neg logit contributions
 This-0.105
ore-0.098
to-0.096
 Playing-0.093
-0.090
Token and
Token ID290
Feature activation+1.90e-02

Pos logit contributions
 This+0.071
to+0.065
 Playing+0.064
ore+0.063
anging+0.059
Neg logit contributions
 way-0.084
 promise-0.082
 forgot-0.077
 passengers-0.074
 forget-0.073
Token took
Token ID1718
Feature activation-2.09e-02

Pos logit contributions
 promise+0.023
 way+0.023
ode+0.022
 passengers+0.022
 crew+0.019
Neg logit contributions
to-0.036
 This-0.036
 late-0.033
-0.033
 Playing-0.033
Token deep
Token ID2769
Feature activation-3.06e-02

Pos logit contributions
 This+0.024
to+0.022
ore+0.020
ges+0.019
 Playing+0.018
Neg logit contributions
 promise-0.048
 way-0.047
 forgot-0.046
 forget-0.044
ode-0.043
Token breaths
Token ID45576
Feature activation-1.11e-01

Pos logit contributions
 This+0.066
to+0.063
 Playing+0.062
ore+0.061
anging+0.059
Neg logit contributions
 way-0.038
 promise-0.036
 forgot-0.033
 passengers-0.030
 tears-0.030
Token.
Token ID13
Feature activation-5.70e-02

Pos logit contributions
 This+0.147
to+0.133
 Playing+0.131
ore+0.128
anging+0.119
Neg logit contributions
 way-0.231
 promise-0.223
 forgot-0.212
 passengers-0.204
 forget-0.203
Token Soon
Token ID15894
Feature activation+3.45e-03

Pos logit contributions
ore+0.053
uttering+0.049
xy+0.047
ges+0.047
anging+0.047
Neg logit contributions
 way-0.129
 tears-0.119
 forgot-0.114
 promise-0.111
 floor-0.111
Token,
Token ID11
Feature activation-3.00e-02

Pos logit contributions
 promise+0.009
 way+0.008
ode+0.008
 passengers+0.008
 forgot+0.008
Neg logit contributions
 This-0.003
to-0.002
 Playing-0.002
ges-0.002
ore-0.002
Token she
Token ID673
Feature activation+4.75e-02

Pos logit contributions
 This+0.028
to+0.022
 late+0.022
 Playing+0.021
ore+0.020
Neg logit contributions
 promise-0.075
 way-0.072
 forgot-0.068
ode-0.066
 passengers-0.066
Token felt
Token ID2936
Feature activation+2.99e-03

Pos logit contributions
 promise+0.073
 way+0.073
 passengers+0.068
ode+0.062
 deal+0.060
Neg logit contributions
to-0.079
-0.076
ore-0.072
 This-0.070
 Playing-0.069
TokenAnna
Token ID31160
Feature activation+1.87e-02

Pos logit contributions
 This+0.044
to+0.041
 Playing+0.040
ore+0.040
anging+0.038
Neg logit contributions
 way-0.032
 promise-0.031
 forgot-0.029
 forget-0.027
 passengers-0.026
Token and
Token ID290
Feature activation-1.01e-02

Pos logit contributions
 way+0.028
 promise+0.027
 passengers+0.025
 forgot+0.025
 forget+0.024
Neg logit contributions
 This-0.035
to-0.033
ore-0.032
 Playing-0.031
ges-0.030
Token Ben
Token ID3932
Feature activation+1.20e-02

Pos logit contributions
 This+0.013
to+0.012
 Playing+0.012
ore+0.012
ges+0.011
Neg logit contributions
 way-0.021
 promise-0.020
 forgot-0.018
 passengers-0.018
ode-0.018
Token start
Token ID923
Feature activation-6.69e-02

Pos logit contributions
 way+0.019
 promise+0.017
ode+0.016
 passengers+0.016
 tears+0.015
Neg logit contributions
 This-0.021
-0.019
 Playing-0.019
to-0.019
ore-0.019
Token to
Token ID284
Feature activation-1.30e-02

Pos logit contributions
 This+0.081
 Playing+0.074
to+0.072
ore+0.072
elt+0.065
Neg logit contributions
 way-0.149
 promise-0.141
 forgot-0.131
 tears-0.130
 bit-0.129
Token argue
Token ID7267
Feature activation-1.11e-01

Pos logit contributions
 This+0.025
to+0.023
 Playing+0.023
ore+0.022
ges+0.021
Neg logit contributions
 way-0.018
 promise-0.017
 forgot-0.016
 passengers-0.016
 tears-0.015
Token.
Token ID13
Feature activation-6.64e-02

Pos logit contributions
 This+0.173
to+0.167
ore+0.163
elt+0.157
uttering+0.154
Neg logit contributions
 way-0.203
 promise-0.192
 forgot-0.174
 other-0.172
 tears-0.171
Token Anna
Token ID11735
Feature activation+3.40e-02

Pos logit contributions
uttering+0.103
to+0.101
ore+0.099
ing+0.095
anging+0.094
Neg logit contributions
 way-0.109
 tears-0.100
 promise-0.096
 other-0.095
 forgot-0.093
Token says
Token ID1139
Feature activation-2.02e-02

Pos logit contributions
 passengers+0.062
 way+0.061
 crew+0.058
ode+0.058
 captain+0.058
Neg logit contributions
 This-0.050
 Playing-0.047
-0.044
to-0.043
ore-0.042
Token Ben
Token ID3932
Feature activation+1.07e-02

Pos logit contributions
 This+0.027
to+0.025
ore+0.024
 Playing+0.024
anging+0.022
Neg logit contributions
 way-0.042
 promise-0.040
 forgot-0.039
 tears-0.037
 forget-0.037
Token has
Token ID468
Feature activation+2.48e-02

Pos logit contributions
 way+0.018
 promise+0.017
 forgot+0.016
 forget+0.015
 passengers+0.015
Neg logit contributions
 This-0.019
to-0.017
 Playing-0.017
ore-0.017
anging-0.016
Token,
Token ID11
Feature activation-2.47e-02

Pos logit contributions
 This+0.041
ore+0.035
to+0.034
 Playing+0.033
ges+0.031
Neg logit contributions
 way-0.078
 promise-0.077
 forgot-0.075
 passengers-0.074
 tears-0.073
Token and
Token ID290
Feature activation-9.73e-03

Pos logit contributions
 This+0.040
 Playing+0.034
to+0.033
 late+0.032
 That+0.032
Neg logit contributions
 promise-0.042
 way-0.041
 forgot-0.040
 passengers-0.039
ode-0.038
Token they
Token ID484
Feature activation+2.61e-02

Pos logit contributions
 This+0.012
to+0.011
 Playing+0.010
ges+0.010
 late+0.010
Neg logit contributions
 promise-0.019
 way-0.019
ode-0.018
 passengers-0.018
 hood-0.017
Token started
Token ID2067
Feature activation-6.31e-02

Pos logit contributions
 way+0.045
ode+0.040
 passengers+0.039
 promise+0.038
 difference+0.037
Neg logit contributions
 This-0.036
 at-0.035
ges-0.035
to-0.034
 him-0.033
Token to
Token ID284
Feature activation+6.05e-04

Pos logit contributions
 This+0.070
 Playing+0.062
to+0.061
ore+0.061
anging+0.054
Neg logit contributions
 way-0.146
 promise-0.140
 forgot-0.133
 tears-0.129
 bit-0.128
Token argue
Token ID7267
Feature activation-1.11e-01

Pos logit contributions
 way+0.001
 passengers+0.001
 forgot+0.001
 promise+0.001
 tears+0.001
Neg logit contributions
 This-0.001
to-0.001
 Playing-0.001
ore-0.001
ges-0.001
Token.
Token ID13
Feature activation-6.44e-02

Pos logit contributions
 This+0.160
to+0.154
ore+0.150
 Playing+0.144
elt+0.144
Neg logit contributions
 way-0.217
 promise-0.202
 forgot-0.190
 tears-0.184
 other-0.180
Token Their
Token ID5334
Feature activation+4.24e-02

Pos logit contributions
ore+0.071
to+0.070
 This+0.068
uttering+0.068
anging+0.066
Neg logit contributions
 way-0.137
 promise-0.127
 forgot-0.125
 tears-0.122
 passengers-0.120
Token mom
Token ID1995
Feature activation+2.22e-02

Pos logit contributions
ode+0.060
 forgot+0.058
 surge+0.057
 forget+0.056
 promise+0.054
Neg logit contributions
 This-0.073
 Playing-0.067
to-0.064
uck-0.060
ires-0.060
Token said
Token ID531
Feature activation-1.61e-02

Pos logit contributions
 way+0.036
 promise+0.035
 passengers+0.034
 crew+0.032
 coc+0.032
Neg logit contributions
 This-0.034
to-0.034
 Playing-0.033
ing-0.033
 Why-0.032
Token,
Token ID11
Feature activation-1.33e-02

Pos logit contributions
 This+0.020
to+0.019
 Playing+0.018
ore+0.018
anging+0.016
Neg logit contributions
 way-0.034
 promise-0.033
 forgot-0.032
 passengers-0.030
 tears-0.030
Token.
Token ID13
Feature activation-7.57e-02

Pos logit contributions
 This+0.005
 Playing+0.004
to+0.004
ore+0.004
ges+0.004
Neg logit contributions
 way-0.008
 promise-0.008
 forgot-0.008
 passengers-0.007
 forget-0.007
Token She
Token ID1375
Feature activation+3.48e-02

Pos logit contributions
uttering+0.086
to+0.082
ore+0.081
anging+0.079
ges+0.073
Neg logit contributions
 way-0.155
 promise-0.146
 forgot-0.142
 passengers-0.139
 forget-0.137
Token climbs
Token ID34332
Feature activation-5.67e-02

Pos logit contributions
 way+0.050
 promise+0.046
 passengers+0.045
ode+0.044
 forget+0.041
Neg logit contributions
 This-0.064
to-0.060
 Playing-0.060
ore-0.058
-0.058
Token up
Token ID510
Feature activation-6.48e-02

Pos logit contributions
 This+0.079
 Playing+0.076
to+0.074
anging+0.071
unch+0.071
Neg logit contributions
 way-0.116
 other-0.100
 tears-0.098
 bit-0.098
 promise-0.097
Token the
Token ID262
Feature activation+3.60e-02

Pos logit contributions
 This+0.097
 Playing+0.093
to+0.092
ore+0.088
anging+0.085
Neg logit contributions
 way-0.124
 promise-0.114
 tears-0.107
 forgot-0.107
 bit-0.105
Token steps
Token ID4831
Feature activation-1.10e-01

Pos logit contributions
 forgot+0.048
 promise+0.046
 passengers+0.043
 way+0.041
 forget+0.039
Neg logit contributions
 This-0.074
ore-0.069
-0.065
to-0.064
 Playing-0.063
Token and
Token ID290
Feature activation-8.89e-04

Pos logit contributions
 This+0.188
 Playing+0.179
to+0.176
ore+0.165
elt+0.157
Neg logit contributions
 way-0.187
 promise-0.172
 bit-0.159
 forgot-0.158
 other-0.154
Token sits
Token ID10718
Feature activation-5.93e-02

Pos logit contributions
 This+0.001
to+0.001
ore+0.001
 Playing+0.001
anging+0.001
Neg logit contributions
 way-0.002
 promise-0.002
 forgot-0.002
 passengers-0.002
 forget-0.002
Token on
Token ID319
Feature activation-3.90e-02

Pos logit contributions
 This+0.093
 Playing+0.085
to+0.082
ges+0.074
anging+0.074
Neg logit contributions
 way-0.113
 promise-0.107
 head-0.104
 pile-0.103
 other-0.101
Token the
Token ID262
Feature activation+3.14e-02

Pos logit contributions
 This+0.062
to+0.058
 Playing+0.057
ore+0.057
anging+0.054
Neg logit contributions
 way-0.071
 promise-0.066
 forgot-0.062
 tears-0.061
 passengers-0.061
Token top
Token ID1353
Feature activation-5.02e-02

Pos logit contributions
 forgot+0.037
 promise+0.036
 way+0.032
 passengers+0.031
 crew+0.029
Neg logit contributions
 This-0.066
ore-0.062
to-0.059
-0.058
 Playing-0.058
Token get
Token ID651
Feature activation-5.10e-02

Pos logit contributions
ays+0.020
ore+0.019
uttering+0.019
anging+0.019
to+0.019
Neg logit contributions
 way-0.028
 tears-0.026
 promise-0.026
 forgot-0.026
 bit-0.026
Token across
Token ID1973
Feature activation-7.58e-02

Pos logit contributions
 This+0.074
to+0.068
ore+0.066
 Playing+0.065
 late+0.061
Neg logit contributions
 way-0.097
 promise-0.095
 forgot-0.090
 passengers-0.087
 forget-0.086
Token the
Token ID262
Feature activation+3.39e-02

Pos logit contributions
 This+0.115
to+0.109
 Playing+0.108
ore+0.103
elt+0.101
Neg logit contributions
 way-0.146
 promise-0.133
 forgot-0.124
 tears-0.124
 passengers-0.121
Token wet
Token ID9583
Feature activation-2.98e-02

Pos logit contributions
 forgot+0.045
 promise+0.044
 passengers+0.038
 way+0.037
 tears+0.036
Neg logit contributions
 This-0.063
ore-0.061
 late-0.061
-0.059
 Playing-0.055
Token p
Token ID279
Feature activation-3.65e-02

Pos logit contributions
 This+0.063
ore+0.060
 Playing+0.058
to+0.057
ges+0.057
Neg logit contributions
 promise-0.036
 way-0.033
 forgot-0.033
 passengers-0.031
 forget-0.030
Tokenuddle
Token ID24500
Feature activation-1.10e-01

Pos logit contributions
 This+0.071
to+0.067
ore+0.066
 Playing+0.065
anging+0.063
Neg logit contributions
 way-0.052
 promise-0.050
 forgot-0.046
 passengers-0.045
 forget-0.044
Token without
Token ID1231
Feature activation-8.24e-03

Pos logit contributions
 This+0.142
to+0.130
 Playing+0.127
ore+0.123
anging+0.114
Neg logit contributions
 way-0.233
 promise-0.223
 forgot-0.213
 forget-0.204
 bit-0.203
Token getting
Token ID1972
Feature activation-2.77e-02

Pos logit contributions
 This+0.010
to+0.010
 Playing+0.009
ore+0.009
ges+0.009
Neg logit contributions
 promise-0.017
 way-0.017
 forgot-0.016
 forget-0.015
 passengers-0.015
Token wet
Token ID9583
Feature activation-6.78e-02

Pos logit contributions
 This+0.053
to+0.051
ore+0.050
 Playing+0.049
 late+0.048
Neg logit contributions
 way-0.039
 promise-0.038
 forgot-0.035
 passengers-0.033
 forget-0.033
Token.
Token ID13
Feature activation-6.49e-02

Pos logit contributions
 This+0.101
to+0.095
 Playing+0.090
ore+0.085
anging+0.082
Neg logit contributions
 way-0.136
 promise-0.124
 forgot-0.121
 tears-0.118
 bit-0.116
Token
Token ID198
Feature activation-4.53e-02

Pos logit contributions
uttering+0.069
to+0.069
ore+0.069
 This+0.068
anging+0.065
Neg logit contributions
 way-0.139
 promise-0.130
 forgot-0.128
 tears-0.124
 passengers-0.122
Token big
Token ID1263
Feature activation+3.59e-03

Pos logit contributions
 forgot+0.036
 passengers+0.034
 promise+0.033
ode+0.032
 heads+0.032
Neg logit contributions
 This-0.051
ore-0.047
 late-0.046
to-0.046
 Do-0.045
Token tree
Token ID5509
Feature activation-5.62e-02

Pos logit contributions
 forgot+0.005
 promise+0.004
 passengers+0.004
 way+0.004
 forget+0.004
Neg logit contributions
 This-0.007
ore-0.007
 Playing-0.006
 Today-0.006
 Do-0.006
Token and
Token ID290
Feature activation+3.46e-03

Pos logit contributions
 This+0.079
to+0.074
 Playing+0.072
ore+0.069
ges+0.065
Neg logit contributions
 way-0.112
 promise-0.108
 forgot-0.102
 bit-0.099
 forget-0.098
Token decided
Token ID3066
Feature activation-4.72e-02

Pos logit contributions
 promise+0.005
 way+0.005
 passengers+0.005
ode+0.004
 forgot+0.004
Neg logit contributions
 This-0.006
to-0.006
 Playing-0.006
ore-0.006
elt-0.005
Token to
Token ID284
Feature activation-1.50e-02

Pos logit contributions
 Playing+0.060
 This+0.060
ore+0.059
ays+0.056
ges+0.055
Neg logit contributions
 way-0.101
 forgot-0.092
 promise-0.091
 forget-0.086
 other-0.085
Token lean
Token ID10904
Feature activation-1.10e-01

Pos logit contributions
 This+0.026
to+0.023
ore+0.022
used+0.020
anging+0.020
Neg logit contributions
 forgot-0.023
 way-0.022
 scar-0.022
 promise-0.022
 passengers-0.022
Token against
Token ID1028
Feature activation-5.28e-02

Pos logit contributions
 Playing+0.180
 This+0.178
anging+0.164
unch+0.163
ires+0.158
Neg logit contributions
 other-0.167
 way-0.165
 promise-0.164
 bit-0.157
 head-0.150
Token it
Token ID340
Feature activation-3.21e-02

Pos logit contributions
 This+0.075
to+0.069
 Playing+0.068
ore+0.067
anging+0.062
Neg logit contributions
 way-0.104
 promise-0.101
 forgot-0.095
 passengers-0.092
 forget-0.091
Token.
Token ID13
Feature activation-6.54e-02

Pos logit contributions
 This+0.042
to+0.038
 Playing+0.038
ore+0.037
ges+0.034
Neg logit contributions
 way-0.068
 promise-0.065
 forgot-0.060
 forget-0.059
 bit-0.059
Token The
Token ID383
Feature activation+6.17e-02

Pos logit contributions
uttering+0.069
ore+0.068
to+0.065
 This+0.065
 Playing+0.064
Neg logit contributions
 way-0.140
 promise-0.129
 forgot-0.127
 tears-0.122
 forget-0.122
Token taller
Token ID25242
Feature activation-1.30e-02

Pos logit contributions
 forgot+0.081
 promise+0.072
 forget+0.068
 way+0.067
 passengers+0.062
Neg logit contributions
 This-0.114
-0.111
ore-0.111
 Playing-0.102
to-0.102
Token to
Token ID284
Feature activation+6.30e-04

Pos logit contributions
 This+0.051
to+0.045
 Playing+0.045
ore+0.044
anging+0.041
Neg logit contributions
 way-0.099
 promise-0.095
 forgot-0.091
 passengers-0.088
 tears-0.087
Token play
Token ID711
Feature activation-6.43e-02

Pos logit contributions
 way+0.001
 promise+0.001
 forgot+0.001
 passengers+0.001
 tears+0.001
Neg logit contributions
 This-0.001
to-0.001
 Playing-0.001
ore-0.001
anging-0.001
Token in
Token ID287
Feature activation-3.24e-02

Pos logit contributions
 This+0.085
to+0.080
 Playing+0.075
ore+0.074
used+0.074
Neg logit contributions
 way-0.130
 promise-0.123
 pile-0.119
 bit-0.115
 other-0.115
Token the
Token ID262
Feature activation+2.75e-02

Pos logit contributions
to+0.057
 This+0.056
elt+0.056
ore+0.054
uttering+0.053
Neg logit contributions
 way-0.056
 promise-0.047
 other-0.047
 pile-0.046
 tears-0.046
Token p
Token ID279
Feature activation-3.95e-02

Pos logit contributions
 promise+0.035
 forgot+0.033
 way+0.032
 passengers+0.030
 forget+0.029
Neg logit contributions
 This-0.058
 Playing-0.054
ore-0.052
to-0.052
-0.051
Tokenuddle
Token ID24500
Feature activation-1.09e-01

Pos logit contributions
 This+0.079
to+0.074
 Playing+0.073
ore+0.072
anging+0.069
Neg logit contributions
 way-0.056
 promise-0.053
 forgot-0.049
 passengers-0.046
 forget-0.046
Token.
Token ID13
Feature activation-6.04e-02

Pos logit contributions
 This+0.158
to+0.147
 Playing+0.142
ore+0.138
anging+0.130
Neg logit contributions
 way-0.214
 promise-0.205
 forgot-0.193
 bit-0.185
 forget-0.184
Token One
Token ID1881
Feature activation+9.57e-03

Pos logit contributions
uttering+0.087
ore+0.085
to+0.085
used+0.084
ging+0.083
Neg logit contributions
 way-0.110
 promise-0.096
 pile-0.094
 other-0.093
 forget-0.089
Token day
Token ID1110
Feature activation-5.72e-02

Pos logit contributions
 way+0.015
 promise+0.014
 forgot+0.013
 forget+0.013
 bit+0.012
Neg logit contributions
 This-0.018
to-0.017
 Playing-0.017
ore-0.016
anging-0.016
Token,
Token ID11
Feature activation-4.64e-02

Pos logit contributions
 Playing+0.113
ays+0.109
xy+0.109
ires+0.107
aghetti+0.104
Neg logit contributions
 way-0.082
 bit-0.077
 forgot-0.077
 other-0.076
 p-0.070
Token D
Token ID360
Feature activation+4.84e-03

Pos logit contributions
 Playing+0.084
 This+0.078
ore+0.077
ays+0.076
anging+0.074
Neg logit contributions
 way-0.080
 forgot-0.073
 bit-0.072
 other-0.069
 forget-0.067
Token She
Token ID1375
Feature activation+3.48e-02

Pos logit contributions
uttering+0.086
to+0.082
ore+0.081
anging+0.079
ges+0.073
Neg logit contributions
 way-0.155
 promise-0.146
 forgot-0.142
 passengers-0.139
 forget-0.137
Token stood
Token ID6204
Feature activation-5.78e-02

Pos logit contributions
 way+0.050
 promise+0.046
 passengers+0.045
ode+0.044
 forget+0.041
Neg logit contributions
 This-0.064
to-0.060
 Playing-0.060
ore-0.058
-0.058
Token up
Token ID510
Feature activation-4.94e-02

Pos logit contributions
 This+0.106
 Playing+0.096
ore+0.093
to+0.092
anging+0.087
Neg logit contributions
 way-0.093
 tears-0.090
 promise-0.090
 head-0.086
 scar-0.085
Token and
Token ID290
Feature activation+1.93e-03

Pos logit contributions
 This+0.085
 Playing+0.084
to+0.079
ore+0.076
anging+0.075
Neg logit contributions
 way-0.083
 tears-0.074
 promise-0.074
 bit-0.073
 pile-0.068
Token started
Token ID2067
Feature activation-6.63e-02

Pos logit contributions
 way+0.003
 promise+0.003
 passengers+0.002
 forgot+0.002
 forget+0.002
Neg logit contributions
 This-0.004
to-0.004
ore-0.004
 Playing-0.004
elt-0.003
Token sway
Token ID20009
Feature activation-1.09e-01

Pos logit contributions
 This+0.077
 Playing+0.069
to+0.067
ore+0.066
anging+0.060
Neg logit contributions
 way-0.150
 promise-0.142
 forgot-0.136
 tears-0.134
 bit-0.132
Tokening
Token ID278
Feature activation-5.29e-02

Pos logit contributions
 This+0.168
 Playing+0.162
to+0.154
ore+0.144
anging+0.139
Neg logit contributions
 way-0.194
 promise-0.183
 other-0.179
 bit-0.178
 tears-0.174
Token to
Token ID284
Feature activation-1.74e-02

Pos logit contributions
 This+0.068
to+0.062
 Playing+0.061
ore+0.059
anging+0.055
Neg logit contributions
 way-0.111
 promise-0.108
 forgot-0.102
 passengers-0.099
 tears-0.098
Token the
Token ID262
Feature activation+5.33e-02

Pos logit contributions
 This+0.021
to+0.018
ore+0.017
ges+0.017
 Playing+0.017
Neg logit contributions
 promise-0.038
 way-0.038
 forgot-0.036
ode-0.034
 passengers-0.034
Token music
Token ID2647
Feature activation-5.32e-02

Pos logit contributions
 forgot+0.065
 promise+0.059
 way+0.057
 forget+0.052
ode+0.049
Neg logit contributions
 This-0.103
ore-0.102
to-0.096
 late-0.094
-0.094
Token.
Token ID13
Feature activation-6.42e-02

Pos logit contributions
 This+0.058
ore+0.050
to+0.049
 Playing+0.047
ges+0.044
Neg logit contributions
 promise-0.118
 way-0.117
 forgot-0.114
 passengers-0.109
 forget-0.108
Tokenily
Token ID813
Feature activation+1.39e-02

Pos logit contributions
 way+0.002
 promise+0.002
 forgot+0.001
 forget+0.001
 passengers+0.001
Neg logit contributions
 This-0.001
to-0.001
 Playing-0.001
ore-0.001
ges-0.001
Token and
Token ID290
Feature activation-1.23e-02

Pos logit contributions
 way+0.022
 promise+0.021
 passengers+0.021
 forget+0.019
ode+0.019
Neg logit contributions
 This-0.024
to-0.022
 Playing-0.022
ore-0.021
-0.021
Token Ben
Token ID3932
Feature activation+1.14e-02

Pos logit contributions
 This+0.015
to+0.013
 Playing+0.013
ore+0.012
ges+0.012
Neg logit contributions
 way-0.026
 promise-0.026
 forgot-0.023
 passengers-0.023
ode-0.023
Token start
Token ID923
Feature activation-6.57e-02

Pos logit contributions
 way+0.017
 promise+0.016
ode+0.015
 passengers+0.015
 scar+0.014
Neg logit contributions
 This-0.020
-0.018
to-0.018
 Playing-0.018
ore-0.018
Token to
Token ID284
Feature activation-1.27e-02

Pos logit contributions
 This+0.083
 Playing+0.077
ore+0.075
to+0.074
elt+0.070
Neg logit contributions
 way-0.143
 promise-0.134
 tears-0.125
 forgot-0.124
 bit-0.123
Token argue
Token ID7267
Feature activation-1.09e-01

Pos logit contributions
 This+0.024
to+0.022
 Playing+0.021
ore+0.021
ges+0.020
Neg logit contributions
 way-0.018
 promise-0.017
 forgot-0.017
 passengers-0.017
ode-0.015
Token.
Token ID13
Feature activation-6.61e-02

Pos logit contributions
 This+0.168
to+0.162
ore+0.160
elt+0.156
uttering+0.154
Neg logit contributions
 way-0.200
 promise-0.189
 forgot-0.171
 other-0.169
 tears-0.168
Token They
Token ID1119
Feature activation+4.12e-02

Pos logit contributions
uttering+0.097
to+0.095
ore+0.094
anging+0.090
ing+0.089
Neg logit contributions
 way-0.118
 tears-0.107
 promise-0.106
 forgot-0.105
 pile-0.101
Token shout
Token ID9191
Feature activation-5.29e-02

Pos logit contributions
 crew+0.074
 way+0.074
ode+0.071
 passengers+0.070
 pill+0.069
Neg logit contributions
 This-0.056
 him-0.048
 She-0.047
 at-0.046
 Why-0.045
Token and
Token ID290
Feature activation+2.16e-02

Pos logit contributions
 This+0.072
to+0.068
ore+0.067
 Playing+0.064
elt+0.060
Neg logit contributions
 way-0.106
 promise-0.103
 forgot-0.098
 tears-0.095
 bit-0.094
Token pull
Token ID2834
Feature activation-6.71e-02

Pos logit contributions
ode+0.033
 way+0.033
 passengers+0.030
 crew+0.030
 promise+0.029
Neg logit contributions
 This-0.035
 Do-0.030
ges-0.030
 him-0.029
 down-0.029
Token lady
Token ID10846
Feature activation+1.38e-02

Pos logit contributions
ode+0.109
 forgot+0.104
 way+0.095
 scar+0.094
 forget+0.093
Neg logit contributions
 This-0.136
 late-0.126
uttering-0.122
ore-0.120
to-0.119
Token and
Token ID290
Feature activation+1.67e-02

Pos logit contributions
 way+0.029
 promise+0.028
 forgot+0.028
 passengers+0.027
 scar+0.026
Neg logit contributions
 This-0.017
ore-0.014
to-0.014
 Playing-0.013
ges-0.013
Token helped
Token ID4193
Feature activation-4.59e-02

Pos logit contributions
 way+0.029
ode+0.028
 promise+0.028
 passengers+0.026
 hood+0.025
Neg logit contributions
 This-0.024
 Playing-0.022
 late-0.021
 Do-0.021
elt-0.021
Token her
Token ID607
Feature activation+4.93e-02

Pos logit contributions
 This+0.049
to+0.043
ore+0.041
 Playing+0.041
ges+0.037
Neg logit contributions
 way-0.107
 promise-0.105
 forgot-0.101
 passengers-0.097
 forget-0.096
Token until
Token ID1566
Feature activation-1.51e-03

Pos logit contributions
 way+0.076
 promise+0.073
 forgot+0.068
 passengers+0.064
 forget+0.064
Neg logit contributions
 This-0.093
to-0.087
 Playing-0.085
ore-0.085
anging-0.080
Token the
Token ID262
Feature activation+8.04e-02

Pos logit contributions
 This+0.002
to+0.002
ore+0.001
 Playing+0.001
ges+0.001
Neg logit contributions
 way-0.003
 promise-0.003
 forgot-0.003
 passengers-0.003
 forget-0.003
Token ambulance
Token ID22536
Feature activation-1.18e-02

Pos logit contributions
 forgot+0.113
 promise+0.097
 way+0.095
 forget+0.094
ode+0.093
Neg logit contributions
 This-0.148
 late-0.139
-0.132
ore-0.132
 Playing-0.129
Token came
Token ID1625
Feature activation-7.29e-03

Pos logit contributions
 This+0.020
to+0.018
ore+0.018
+0.017
 Playing+0.017
Neg logit contributions
 way-0.018
 promise-0.018
 scar-0.017
ode-0.017
 passengers-0.017
Token.
Token ID13
Feature activation-4.42e-02

Pos logit contributions
 This+0.013
 Playing+0.012
ore+0.012
to+0.011
anging+0.011
Neg logit contributions
 way-0.013
 promise-0.012
 passengers-0.011
 other-0.011
 forget-0.011
Token He
Token ID679
Feature activation+6.46e-02

Pos logit contributions
to+0.048
ore+0.046
uttering+0.046
ges+0.045
 This+0.044
Neg logit contributions
 way-0.098
 promise-0.094
 tears-0.093
 forgot-0.091
 bit-0.087
Token told
Token ID1297
Feature activation-2.91e-02

Pos logit contributions
 way+0.116
 thrill+0.107
ode+0.106
 passengers+0.104
 sides+0.104
Neg logit contributions
-0.088
to-0.086
 late-0.083
elt-0.079
 She-0.077
Token
Token ID198
Feature activation-3.12e-02

Pos logit contributions
to+0.064
uttering+0.063
anging+0.061
ing+0.058
used+0.058
Neg logit contributions
 way-0.100
 tears-0.095
 promise-0.093
 forgot-0.091
 other-0.087
Token
Token ID198
Feature activation-2.91e-02

Pos logit contributions
elt+0.042
used+0.041
uttering+0.040
 This+0.040
anging+0.039
Neg logit contributions
 way-0.058
 promise-0.057
 other-0.054
 tears-0.053
 forgot-0.052
Token"
Token ID1
Feature activation-3.49e-03

Pos logit contributions
 This+0.044
to+0.042
ore+0.041
elt+0.040
ays+0.039
Neg logit contributions
 promise-0.052
 way-0.051
 forgot-0.050
 passengers-0.048
 forget-0.047
TokenWhere
Token ID8496
Feature activation-1.53e-03

Pos logit contributions
 This+0.004
to+0.004
 late+0.004
 Playing+0.004
+0.004
Neg logit contributions
 way-0.008
 promise-0.007
 forgot-0.007
 forget-0.007
 passengers-0.007
Token are
Token ID389
Feature activation+2.88e-02

Pos logit contributions
 This+0.003
to+0.003
 Playing+0.003
ore+0.003
uttering+0.003
Neg logit contributions
 way-0.002
 promise-0.002
 forgot-0.002
 forget-0.001
 bit-0.001
Token the
Token ID262
Feature activation+7.67e-02

Pos logit contributions
 way+0.060
 promise+0.058
 forgot+0.055
 passengers+0.053
 forget+0.053
Neg logit contributions
 This-0.038
to-0.035
 Playing-0.034
ore-0.034
anging-0.031
Token toys
Token ID14958
Feature activation-1.19e-02

Pos logit contributions
 forgot+0.096
ode+0.081
 passengers+0.079
 forget+0.079
 promise+0.077
Neg logit contributions
 This-0.140
 here-0.140
 late-0.138
-0.133
 Do-0.133
Token?"
Token ID1701
Feature activation-4.64e-02

Pos logit contributions
 This+0.015
to+0.015
 Playing+0.014
ore+0.013
ges+0.013
Neg logit contributions
 way-0.026
 promise-0.025
 forgot-0.024
 forget-0.023
 bit-0.022
Token Tom
Token ID4186
Feature activation+3.65e-02

Pos logit contributions
 This+0.067
to+0.065
ore+0.063
 Playing+0.061
anging+0.059
Neg logit contributions
 way-0.089
 promise-0.085
 forgot-0.083
 tears-0.080
 forget-0.079
Token cried
Token ID16896
Feature activation-5.48e-02

Pos logit contributions
 promise+0.054
 way+0.054
 passengers+0.048
 forgot+0.048
 forget+0.046
Neg logit contributions
 This-0.066
to-0.064
 Playing-0.062
ore-0.060
 late-0.058
Token.
Token ID13
Feature activation-5.57e-02

Pos logit contributions
 This+0.082
 Playing+0.077
to+0.076
ore+0.073
anging+0.070
Neg logit contributions
 way-0.102
 promise-0.099
 tears-0.094
 passengers-0.092
 forgot-0.092
Token lot
Token ID1256
Feature activation+3.22e-02

Pos logit contributions
ode+0.118
 heads+0.111
 forgot+0.109
 members+0.107
ople+0.104
Neg logit contributions
 This-0.093
-0.090
 late-0.088
 Do-0.085
 Today-0.085
Token of
Token ID286
Feature activation+4.41e-02

Pos logit contributions
 way+0.065
 promise+0.065
 forgot+0.062
 forget+0.059
 tears+0.057
Neg logit contributions
 This-0.045
ore-0.041
to-0.040
 Playing-0.040
ges-0.037
Token fun
Token ID1257
Feature activation-2.72e-02

Pos logit contributions
 forgot+0.075
 forget+0.072
 promise+0.071
ode+0.071
 bit+0.066
Neg logit contributions
 This-0.069
 Playing-0.067
-0.066
 late-0.065
to-0.061
Token with
Token ID351
Feature activation+2.82e-03

Pos logit contributions
 This+0.039
to+0.037
 Playing+0.034
ore+0.034
elt+0.034
Neg logit contributions
 way-0.055
 promise-0.050
 passengers-0.049
 forgot-0.048
 tears-0.047
Token the
Token ID262
Feature activation+9.24e-02

Pos logit contributions
 way+0.006
 promise+0.006
 forgot+0.006
 forget+0.006
ode+0.005
Neg logit contributions
 This-0.003
 Playing-0.003
ore-0.003
to-0.003
ges-0.003
Token big
Token ID1263
Feature activation+5.49e-02

Pos logit contributions
 forgot+0.153
ode+0.139
sie+0.136
 promise+0.134
 bit+0.130
Neg logit contributions
 This-0.150
 Playing-0.138
-0.131
 late-0.126
 Do-0.125
Token steel
Token ID7771
Feature activation+3.54e-02

Pos logit contributions
 forgot+0.094
 promise+0.086
Days+0.082
ode+0.082
 forget+0.082
Neg logit contributions
 This-0.090
 Playing-0.081
 Today-0.076
-0.074
 Do-0.073
Token car
Token ID1097
Feature activation-6.79e-03

Pos logit contributions
 forgot+0.061
 promise+0.061
 forget+0.059
 way+0.058
 scar+0.051
Neg logit contributions
 This-0.056
ore-0.054
 Playing-0.049
ing-0.047
to-0.047
Token.
Token ID13
Feature activation-4.53e-02

Pos logit contributions
 This+0.007
 Playing+0.006
ore+0.006
to+0.006
anging+0.006
Neg logit contributions
 way-0.016
 promise-0.015
 forgot-0.015
 forget-0.014
 tears-0.014
Token
Token ID198
Feature activation-1.86e-02

Pos logit contributions
to+0.054
used+0.053
ore+0.051
anging+0.050
 This+0.049
Neg logit contributions
 way-0.094
 promise-0.087
 passengers-0.086
 forgot-0.085
 tears-0.083
Token
Token ID198
Feature activation-1.73e-02

Pos logit contributions
 This+0.026
elt+0.025
used+0.025
anging+0.024
uttering+0.024
Neg logit contributions
 way-0.035
 promise-0.035
 other-0.033
 passengers-0.032
 forgot-0.031
Token saw
Token ID2497
Feature activation-1.35e-02

Pos logit contributions
 promise+0.010
 way+0.009
ode+0.009
 passengers+0.008
 tears+0.008
Neg logit contributions
 This-0.009
to-0.008
-0.008
 Playing-0.008
ges-0.008
Token a
Token ID257
Feature activation+5.72e-02

Pos logit contributions
 This+0.019
to+0.018
ore+0.017
 Playing+0.017
anging+0.016
Neg logit contributions
 way-0.027
 promise-0.026
 forgot-0.024
 passengers-0.024
 tears-0.023
Token cute
Token ID13779
Feature activation+4.01e-02

Pos logit contributions
 promise+0.083
 way+0.079
 forgot+0.077
 minds+0.076
 passengers+0.075
Neg logit contributions
 This-0.097
ore-0.093
-0.091
to-0.091
 late-0.087
Token bunny
Token ID44915
Feature activation+6.88e-04

Pos logit contributions
 way+0.043
 promise+0.042
 forgot+0.039
 passengers+0.036
 forget+0.035
Neg logit contributions
 This-0.092
to-0.086
ore-0.085
 Playing-0.085
ges-0.080
Token.
Token ID13
Feature activation-4.63e-02

Pos logit contributions
 way+0.001
 promise+0.001
 forgot+0.001
 bit+0.001
 pile+0.001
Neg logit contributions
 This-0.001
to-0.001
 Playing-0.001
ore-0.001
anging-0.001
Token The
Token ID383
Feature activation+7.59e-02

Pos logit contributions
ore+0.070
uttering+0.070
to+0.069
anging+0.068
used+0.067
Neg logit contributions
 way-0.085
 forgot-0.077
 promise-0.074
 tears-0.074
 pile-0.072
Token bunny
Token ID44915
Feature activation+1.76e-02

Pos logit contributions
 promise+0.101
 way+0.101
 forgot+0.097
 passengers+0.092
 forget+0.087
Neg logit contributions
 This-0.151
 Playing-0.138
to-0.137
ore-0.137
-0.131
Token had
Token ID550
Feature activation+3.18e-02

Pos logit contributions
 promise+0.028
 way+0.027
 passengers+0.026
 forget+0.024
ode+0.023
Neg logit contributions
 This-0.031
to-0.029
 Playing-0.029
ore-0.028
-0.027
Token an
Token ID281
Feature activation+6.38e-02

Pos logit contributions
 promise+0.072
 way+0.061
 forgot+0.060
ode+0.059
 forget+0.059
Neg logit contributions
 This-0.044
to-0.037
elt-0.033
 late-0.033
 That-0.032
Token adorable
Token ID29012
Feature activation+5.63e-02

Pos logit contributions
 way+0.084
 promise+0.080
 forgot+0.077
 passengers+0.071
 forget+0.070
Neg logit contributions
 This-0.132
to-0.122
 Playing-0.121
ore-0.120
anging-0.114
Token little
Token ID1310
Feature activation+4.68e-02

Pos logit contributions
 way+0.064
 promise+0.062
 forgot+0.057
 passengers+0.053
 forget+0.052
Neg logit contributions
 This-0.125
to-0.118
 Playing-0.116
ore-0.116
anging-0.110
Token Tommy
Token ID19919
Feature activation+3.53e-02

Pos logit contributions
 This+0.028
to+0.025
 Playing+0.025
ore+0.025
anging+0.023
Neg logit contributions
 way-0.051
 promise-0.049
 forgot-0.047
 passengers-0.045
 forget-0.045
Token noticed
Token ID6810
Feature activation-3.74e-02

Pos logit contributions
 promise+0.054
 way+0.050
 passengers+0.049
 tears+0.044
 satisfaction+0.044
Neg logit contributions
to-0.060
 This-0.057
elt-0.056
-0.055
anging-0.054
Token something
Token ID1223
Feature activation+8.27e-03

Pos logit contributions
 This+0.046
to+0.042
 Playing+0.041
ore+0.040
anging+0.037
Neg logit contributions
 way-0.080
 promise-0.079
 forgot-0.075
 forget-0.072
 passengers-0.072
Token strange
Token ID6283
Feature activation-2.10e-02

Pos logit contributions
 way+0.012
 promise+0.012
 forgot+0.011
 passengers+0.011
 forget+0.010
Neg logit contributions
 This-0.016
to-0.015
 Playing-0.014
ore-0.014
anging-0.014
Token.
Token ID13
Feature activation-4.35e-02

Pos logit contributions
 This+0.035
 Playing+0.031
to+0.031
anging+0.030
ore+0.029
Neg logit contributions
 way-0.038
 promise-0.033
 bit-0.033
 tears-0.032
 forgot-0.032
Token The
Token ID383
Feature activation+7.63e-02

Pos logit contributions
to+0.043
anging+0.041
uttering+0.041
ore+0.041
ges+0.039
Neg logit contributions
 way-0.094
 tears-0.091
 promise-0.086
 hood-0.084
 forgot-0.084
Token grass
Token ID8701
Feature activation-1.84e-02

Pos logit contributions
 forgot+0.122
 promise+0.113
 forget+0.104
atha+0.099
ode+0.099
Neg logit contributions
-0.125
 This-0.125
ore-0.115
 Playing-0.113
 Today-0.112
Token was
Token ID373
Feature activation+2.97e-02

Pos logit contributions
 This+0.036
to+0.034
 Playing+0.034
ore+0.033
anging+0.032
Neg logit contributions
 way-0.026
 promise-0.025
 forgot-0.023
 passengers-0.022
 forget-0.022
Token starting
Token ID3599
Feature activation-3.43e-02

Pos logit contributions
 way+0.050
 promise+0.050
 forgot+0.046
 passengers+0.044
 forget+0.044
Neg logit contributions
 This-0.049
to-0.045
 Playing-0.045
ore-0.044
 late-0.042
Token to
Token ID284
Feature activation+2.25e-02

Pos logit contributions
 This+0.038
 Playing+0.034
to+0.033
ore+0.032
ges+0.029
Neg logit contributions
 way-0.080
 promise-0.075
 forgot-0.073
 bit-0.070
 passengers-0.070
Token look
Token ID804
Feature activation-2.46e-02

Pos logit contributions
 promise+0.030
 way+0.030
 forgot+0.028
 passengers+0.027
ode+0.025
Neg logit contributions
 This-0.043
to-0.039
 Playing-0.039
ore-0.038
 late-0.038
Token mad
Token ID8805
Feature activation-5.14e-02

Pos logit contributions
 way+0.054
 promise+0.053
 forgot+0.049
 passengers+0.047
 forget+0.047
Neg logit contributions
 This-0.054
to-0.050
 Playing-0.049
ore-0.049
anging-0.046
Token at
Token ID379
Feature activation-1.91e-02

Pos logit contributions
 This+0.071
to+0.068
 Playing+0.066
ore+0.065
xy+0.060
Neg logit contributions
 way-0.103
 forgot-0.096
 promise-0.095
 tears-0.090
 forget-0.089
Token Tim
Token ID5045
Feature activation+1.20e-02

Pos logit contributions
 This+0.031
to+0.029
 Playing+0.028
ore+0.028
ges+0.026
Neg logit contributions
 way-0.034
 promise-0.033
 forgot-0.031
 passengers-0.030
 forget-0.029
Token,
Token ID11
Feature activation-9.93e-03

Pos logit contributions
 way+0.024
 promise+0.023
 forgot+0.022
 passengers+0.022
 forget+0.021
Neg logit contributions
 This-0.016
to-0.015
 Playing-0.014
ore-0.014
anging-0.013
Token but
Token ID475
Feature activation+1.57e-03

Pos logit contributions
 This+0.015
 Playing+0.013
to+0.013
 late+0.013
ore+0.012
Neg logit contributions
 promise-0.018
 way-0.018
 passengers-0.016
 forgot-0.016
ode-0.016
Token he
Token ID339
Feature activation+3.96e-02

Pos logit contributions
 way+0.004
 promise+0.004
 passengers+0.003
 forgot+0.003
 forget+0.003
Neg logit contributions
 This-0.002
 Playing-0.001
to-0.001
ore-0.001
 late-0.001
Token also
Token ID635
Feature activation+2.78e-02

Pos logit contributions
 way+0.069
 passengers+0.068
 runway+0.065
 hood+0.064
ode+0.063
Neg logit contributions
to-0.055
 at-0.049
 This-0.048
uck-0.047
 Playing-0.047
Token felt
Token ID2936
Feature activation+3.10e-03

Pos logit contributions
 way+0.038
 promise+0.035
 passengers+0.034
ode+0.032
 scar+0.030
Neg logit contributions
 This-0.054
to-0.052
 Playing-0.051
elt-0.049
 late-0.048
Token sorry
Token ID7926
Feature activation-4.12e-02

Pos logit contributions
 way+0.005
 promise+0.004
 forgot+0.004
 passengers+0.004
 forget+0.004
Neg logit contributions
 This-0.006
to-0.006
 Playing-0.006
ore-0.006
anging-0.005
Token for
Token ID329
Feature activation-1.69e-02

Pos logit contributions
 This+0.059
to+0.058
 Playing+0.054
ore+0.054
anging+0.053
Neg logit contributions
 way-0.081
 promise-0.079
 forgot-0.072
 tears-0.071
 other-0.069
Token him
Token ID683
Feature activation+1.62e-02

Pos logit contributions
 This+0.017
to+0.015
ore+0.015
 Playing+0.014
anging+0.013
Neg logit contributions
 way-0.041
 promise-0.039
 forgot-0.038
 passengers-0.037
 forget-0.036
Token catch
Token ID4929
Feature activation-3.68e-02

Pos logit contributions
 way+0.037
 forgot+0.034
 promise+0.032
 passengers+0.032
 tears+0.032
Neg logit contributions
 This-0.048
ore-0.042
to-0.042
 Playing-0.041
ges-0.040
Token fish
Token ID5916
Feature activation-1.81e-02

Pos logit contributions
 This+0.064
to+0.061
 Playing+0.060
anging+0.058
ore+0.058
Neg logit contributions
 way-0.060
 promise-0.058
 bit-0.052
 other-0.052
 tears-0.051
Token."
Token ID526
Feature activation-4.46e-02

Pos logit contributions
 This+0.025
to+0.023
 Playing+0.023
ore+0.021
anging+0.020
Neg logit contributions
 way-0.036
 promise-0.036
 forgot-0.033
 bit-0.032
 forget-0.032
Token
Token ID198
Feature activation-3.25e-02

Pos logit contributions
 Playing+0.064
 This+0.063
to+0.062
ore+0.062
uttering+0.059
Neg logit contributions
 way-0.086
 promise-0.080
 forgot-0.076
 tears-0.075
 passengers-0.072
Token
Token ID198
Feature activation-2.81e-02

Pos logit contributions
used+0.049
 Playing+0.049
uttering+0.047
anging+0.046
 This+0.045
Neg logit contributions
 way-0.060
 promise-0.056
 other-0.055
 forgot-0.050
 pile-0.049
Token"
Token ID1
Feature activation+8.19e-03

Pos logit contributions
 This+0.040
 Playing+0.037
to+0.036
ore+0.036
ges+0.033
Neg logit contributions
 way-0.057
 promise-0.055
 forgot-0.052
 bit-0.050
 passengers-0.049
TokenWow
Token ID22017
Feature activation-1.17e-02

Pos logit contributions
 way+0.016
 promise+0.015
 forgot+0.015
 passengers+0.014
 tears+0.014
Neg logit contributions
 This-0.012
to-0.011
 Playing-0.011
ore-0.011
ges-0.010
Token,
Token ID11
Feature activation+7.21e-03

Pos logit contributions
 This+0.016
to+0.016
 Playing+0.015
ore+0.015
elt+0.014
Neg logit contributions
 way-0.024
 promise-0.023
 forgot-0.022
 forget-0.021
 pile-0.021
Token Tom
Token ID4186
Feature activation+3.14e-02

Pos logit contributions
 way+0.017
 promise+0.016
 forgot+0.016
ode+0.015
 passengers+0.015
Neg logit contributions
 This-0.008
 That-0.006
to-0.005
 Playing-0.005
 Do-0.005
Token,
Token ID11
Feature activation+5.77e-03

Pos logit contributions
 way+0.069
 promise+0.067
 forgot+0.064
 forget+0.061
 bit+0.060
Neg logit contributions
 This-0.039
to-0.036
 Playing-0.035
ore-0.035
ges-0.031
Token that
Token ID326
Feature activation+1.63e-02

Pos logit contributions
 way+0.013
 promise+0.012
 forgot+0.012
 tears+0.012
 passengers+0.011
Neg logit contributions
 This-0.007
to-0.005
 Playing-0.005
 Do-0.005
 That-0.005
Token.
Token ID13
Feature activation-4.40e-02

Pos logit contributions
 way+0.074
 promise+0.071
 forgot+0.068
 passengers+0.064
 forget+0.064
Neg logit contributions
 This-0.054
to-0.049
 Playing-0.049
ore-0.048
ges-0.045
Token Now
Token ID2735
Feature activation-1.34e-02

Pos logit contributions
uttering+0.046
ore+0.044
ges+0.043
to+0.043
 This+0.041
Neg logit contributions
 way-0.098
 promise-0.089
 forgot-0.085
 tears-0.084
 passengers-0.084
Token he
Token ID339
Feature activation+5.70e-02

Pos logit contributions
 This+0.015
to+0.012
 Playing+0.012
ore+0.012
anging+0.011
Neg logit contributions
 promise-0.031
 way-0.030
 forgot-0.029
 passengers-0.028
 tears-0.028
Token was
Token ID373
Feature activation+3.65e-02

Pos logit contributions
 way+0.079
 promise+0.074
 passengers+0.071
 tears+0.068
 scar+0.066
Neg logit contributions
 This-0.108
to-0.103
ore-0.100
 Playing-0.100
-0.097
Token known
Token ID1900
Feature activation-7.00e-03

Pos logit contributions
 way+0.060
 promise+0.060
 forgot+0.055
 passengers+0.053
 forget+0.053
Neg logit contributions
 This-0.062
to-0.058
 Playing-0.056
ore-0.056
anging-0.054
Token as
Token ID355
Feature activation+1.18e-02

Pos logit contributions
 This+0.009
to+0.008
ore+0.008
 Playing+0.008
ges+0.007
Neg logit contributions
 way-0.015
 promise-0.014
 forgot-0.014
 forget-0.013
 passengers-0.013
Token the
Token ID262
Feature activation+7.71e-02

Pos logit contributions
 way+0.023
 promise+0.021
 forgot+0.021
 passengers+0.020
 forget+0.020
Neg logit contributions
 This-0.018
 Playing-0.016
ore-0.016
to-0.016
ges-0.015
Token brav
Token ID49025
Feature activation+1.57e-02

Pos logit contributions
 forgot+0.104
 promise+0.099
 way+0.094
 tears+0.093
 hood+0.091
Neg logit contributions
 This-0.138
 late-0.125
to-0.124
-0.120
ore-0.119
Tokenest
Token ID395
Feature activation+3.32e-02

Pos logit contributions
 way+0.025
 promise+0.024
 forgot+0.024
 forget+0.023
 pile+0.022
Neg logit contributions
 This-0.028
to-0.025
ore-0.025
 Playing-0.024
anging-0.024
Token boy
Token ID2933
Feature activation+2.49e-02

Pos logit contributions
 promise+0.051
 way+0.050
 forgot+0.049
 tears+0.046
 scar+0.045
Neg logit contributions
 This-0.055
ore-0.052
to-0.051
 Playing-0.049
ing-0.049
Token in
Token ID287
Feature activation+1.15e-02

Pos logit contributions
 way+0.044
 promise+0.042
 forgot+0.040
 passengers+0.038
 forget+0.038
Neg logit contributions
 This-0.041
to-0.038
 Playing-0.037
ore-0.037
anging-0.035
Token was
Token ID373
Feature activation+4.61e-02

Pos logit contributions
 way+0.046
 promise+0.045
ode+0.041
 scar+0.041
 forget+0.041
Neg logit contributions
 This-0.041
ore-0.039
to-0.039
 Playing-0.038
anging-0.035
Token so
Token ID523
Feature activation+4.50e-02

Pos logit contributions
 way+0.072
 promise+0.071
 forgot+0.065
 tears+0.062
 forget+0.062
Neg logit contributions
 This-0.082
to-0.076
 Playing-0.074
ore-0.073
anging-0.072
Token happy
Token ID3772
Feature activation-2.89e-02

Pos logit contributions
 way+0.062
 promise+0.059
 forgot+0.055
 forget+0.051
 passengers+0.051
Neg logit contributions
 This-0.092
to-0.086
 Playing-0.085
ore-0.085
ges-0.080
Token to
Token ID284
Feature activation+2.05e-02

Pos logit contributions
 This+0.047
 Playing+0.043
to+0.043
ithering+0.042
ore+0.042
Neg logit contributions
 way-0.051
 forgot-0.045
 promise-0.041
 passengers-0.041
 bit-0.041
Token see
Token ID766
Feature activation-1.45e-02

Pos logit contributions
 way+0.029
 promise+0.028
 forgot+0.026
 forget+0.025
 passengers+0.025
Neg logit contributions
 This-0.040
to-0.039
 Playing-0.038
ore-0.038
elt-0.036
Token it
Token ID340
Feature activation+2.84e-02

Pos logit contributions
 This+0.016
to+0.014
 Playing+0.014
ore+0.014
ges+0.012
Neg logit contributions
 way-0.033
 promise-0.033
 forgot-0.031
 forget-0.030
 bit-0.029
Token soar
Token ID48701
Feature activation-3.74e-02

Pos logit contributions
 way+0.051
 promise+0.049
 forgot+0.046
 forget+0.044
 passengers+0.044
Neg logit contributions
 This-0.046
to-0.043
 Playing-0.042
ore-0.042
ges-0.039
Token!
Token ID0
Feature activation-2.92e-02

Pos logit contributions
 This+0.055
 Playing+0.050
to+0.050
ore+0.048
ges+0.045
Neg logit contributions
 way-0.075
 promise-0.070
 forgot-0.067
 passengers-0.064
 forget-0.064
Token<|endoftext|>
Token ID50256
Feature activation-3.94e-02

Pos logit contributions
uttering+0.031
used+0.031
to+0.031
ges+0.030
anging+0.029
Neg logit contributions
 way-0.063
 forgot-0.057
 promise-0.057
 tears-0.054
 other-0.054
TokenOnce
Token ID7454
Feature activation-1.06e-02

Pos logit contributions
anging+0.059
used+0.058
uttering+0.057
ires+0.055
elt+0.054
Neg logit contributions
 way-0.076
 other-0.067
 tears-0.060
 pile-0.059
 promise-0.059
Token upon
Token ID2402
Feature activation-1.90e-02

Pos logit contributions
 This+0.014
to+0.014
 Playing+0.013
elt+0.013
anging+0.013
Neg logit contributions
 way-0.023
 promise-0.021
 forgot-0.020
 other-0.019
 forget-0.018
Token upon
Token ID2402
Feature activation-4.47e-02

Pos logit contributions
 This+0.049
 Playing+0.046
to+0.045
elt+0.043
ore+0.043
Neg logit contributions
 way-0.072
 promise-0.067
 forgot-0.067
 other-0.062
 tears-0.061
Token a
Token ID257
Feature activation+1.88e-04

Pos logit contributions
 This+0.075
ore+0.073
 Playing+0.071
to+0.070
anging+0.068
Neg logit contributions
 way-0.074
 promise-0.068
 forgot-0.067
 other-0.066
 tears-0.066
Token time
Token ID640
Feature activation-4.45e-02

Pos logit contributions
 way+0.000
 promise+0.000
 forgot+0.000
 passengers+0.000
 forget+0.000
Neg logit contributions
 This-0.000
to-0.000
 Playing-0.000
ore-0.000
anging-0.000
Token there
Token ID612
Feature activation-1.93e-02

Pos logit contributions
to+0.093
ore+0.087
eating+0.086
ays+0.086
 Playing+0.085
Neg logit contributions
 way-0.061
 forgot-0.047
 promise-0.046
 p-0.045
 h-0.045
Token was
Token ID373
Feature activation-4.40e-03

Pos logit contributions
 This+0.041
to+0.039
 Playing+0.039
ore+0.038
anging+0.037
Neg logit contributions
 way-0.026
 promise-0.023
 forgot-0.022
 forget-0.020
 pile-0.019
Token a
Token ID257
Feature activation+2.41e-02

Pos logit contributions
ore+0.008
 This+0.008
to+0.007
used+0.007
 Playing+0.007
Neg logit contributions
 way-0.007
 other-0.006
 promise-0.006
 tears-0.006
 forgot-0.006
Token little
Token ID1310
Feature activation+1.50e-02

Pos logit contributions
 way+0.026
 promise+0.024
 forgot+0.022
 tears+0.021
 passengers+0.020
Neg logit contributions
 This-0.054
to-0.051
 Playing-0.051
ore-0.050
-0.048
Token girl
Token ID2576
Feature activation+9.41e-03

Pos logit contributions
 way+0.018
 forgot+0.017
 promise+0.017
 tears+0.016
 forget+0.015
Neg logit contributions
 This-0.031
ore-0.031
 Playing-0.029
elt-0.028
-0.028
Token named
Token ID3706
Feature activation-1.60e-02

Pos logit contributions
 way+0.016
 promise+0.015
 forgot+0.014
 passengers+0.014
 forget+0.014
Neg logit contributions
 This-0.016
to-0.015
 Playing-0.015
ore-0.014
anging-0.014
Token Sue
Token ID26089
Feature activation+1.53e-02

Pos logit contributions
 This+0.028
to+0.026
ore+0.026
 Playing+0.026
anging+0.025
Neg logit contributions
 way-0.026
 promise-0.025
 forgot-0.024
 forget-0.022
 passengers-0.022
Token.
Token ID13
Feature activation-4.05e-02

Pos logit contributions
 way+0.032
 promise+0.031
 forgot+0.030
 forget+0.028
 passengers+0.028
Neg logit contributions
 This-0.020
to-0.018
ore-0.018
 Playing-0.018
anging-0.016
Token.
Token ID13
Feature activation-4.21e-02

Pos logit contributions
 way+0.072
 promise+0.069
 forgot+0.066
 passengers+0.062
 forget+0.062
Neg logit contributions
 This-0.048
to-0.044
ore-0.044
 Playing-0.043
anging-0.039
Token Tom
Token ID4186
Feature activation+5.07e-02

Pos logit contributions
ore+0.061
to+0.059
used+0.059
uttering+0.058
anging+0.057
Neg logit contributions
 way-0.083
 forgot-0.072
 promise-0.071
 tears-0.070
 forget-0.068
Token had
Token ID550
Feature activation+3.92e-02

Pos logit contributions
 way+0.079
 promise+0.079
 passengers+0.072
 tears+0.072
 forget+0.069
Neg logit contributions
 This-0.088
 Playing-0.083
to-0.082
ore-0.077
anging-0.076
Token a
Token ID257
Feature activation+7.20e-02

Pos logit contributions
 promise+0.102
 way+0.092
 forget+0.089
 forgot+0.089
ode+0.087
Neg logit contributions
 This-0.040
to-0.033
 late-0.029
 Playing-0.029
-0.026
Token special
Token ID2041
Feature activation+5.92e-02

Pos logit contributions
 forgot+0.097
ode+0.096
 promise+0.095
 passengers+0.093
 tears+0.092
Neg logit contributions
 This-0.133
to-0.116
-0.113
ore-0.113
 Playing-0.111
Token shield
Token ID7614
Feature activation-3.38e-02

Pos logit contributions
 way+0.069
 forgot+0.067
 promise+0.067
 forget+0.061
 passengers+0.061
Neg logit contributions
 This-0.126
to-0.117
ore-0.117
 Playing-0.114
uttering-0.109
Token that
Token ID326
Feature activation+2.28e-02

Pos logit contributions
 This+0.039
ore+0.034
to+0.033
 Playing+0.033
anging+0.030
Neg logit contributions
 way-0.074
 promise-0.074
 forgot-0.070
 passengers-0.068
 tears-0.067
Token was
Token ID373
Feature activation+3.36e-02

Pos logit contributions
 promise+0.049
 passengers+0.045
 way+0.044
ode+0.044
 hood+0.043
Neg logit contributions
 This-0.029
to-0.025
 Playing-0.024
ore-0.023
 late-0.021
Token very
Token ID845
Feature activation+4.32e-02

Pos logit contributions
 promise+0.058
 way+0.058
 forgot+0.054
 forget+0.053
 passengers+0.051
Neg logit contributions
 This-0.053
to-0.050
 Playing-0.048
ore-0.047
 late-0.046
Token tough
Token ID5802
Feature activation-2.15e-02

Pos logit contributions
 way+0.058
 promise+0.055
 forgot+0.051
 passengers+0.048
 forget+0.048
Neg logit contributions
 This-0.088
to-0.083
ore-0.082
 Playing-0.081
 late-0.077
Token.
Token ID13
Feature activation-4.47e-02

Pos logit contributions
 This+0.027
to+0.025
 Playing+0.024
ore+0.024
anging+0.022
Neg logit contributions
 way-0.046
 promise-0.044
 forgot-0.042
 passengers-0.041
 forget-0.040
Token,
Token ID11
Feature activation-2.69e-02

Pos logit contributions
to+0.061
ore+0.060
 Playing+0.059
 This+0.059
xy+0.058
Neg logit contributions
 way-0.061
 forgot-0.054
 other-0.051
 bit-0.050
 promise-0.049
Token they
Token ID484
Feature activation+5.00e-02

Pos logit contributions
 This+0.038
to+0.036
ore+0.036
 Playing+0.035
anging+0.034
Neg logit contributions
 way-0.054
 promise-0.050
 forgot-0.049
 bit-0.046
 passengers-0.046
Token saw
Token ID2497
Feature activation-1.35e-02

Pos logit contributions
 promise+0.074
 way+0.073
 tears+0.065
 passengers+0.064
ode+0.063
Neg logit contributions
 This-0.090
to-0.086
-0.085
 Playing-0.082
ges-0.081
Token a
Token ID257
Feature activation+5.71e-02

Pos logit contributions
 This+0.019
to+0.018
ore+0.018
 Playing+0.017
anging+0.017
Neg logit contributions
 way-0.027
 promise-0.025
 forgot-0.024
 tears-0.023
 passengers-0.023
Token big
Token ID1263
Feature activation+3.41e-02

Pos logit contributions
 promise+0.082
 forgot+0.081
 way+0.080
 passengers+0.077
ode+0.077
Neg logit contributions
 This-0.094
ore-0.090
 late-0.087
to-0.087
-0.086
Token slide
Token ID10649
Feature activation-4.23e-02

Pos logit contributions
 forgot+0.045
 promise+0.043
 way+0.043
 passengers+0.041
 forget+0.038
Neg logit contributions
 This-0.067
ore-0.061
 Playing-0.061
-0.057
 late-0.056
Token in
Token ID287
Feature activation+3.40e-03

Pos logit contributions
to+0.061
 This+0.061
 Playing+0.056
ore+0.054
ges+0.052
Neg logit contributions
 way-0.085
 promise-0.077
 bit-0.074
 forgot-0.074
 pile-0.073
Token the
Token ID262
Feature activation+5.10e-02

Pos logit contributions
 promise+0.007
 way+0.007
 forgot+0.007
 forget+0.006
 passengers+0.006
Neg logit contributions
 This-0.004
 Playing-0.004
to-0.004
ore-0.004
-0.003
Token park
Token ID3952
Feature activation-3.61e-02

Pos logit contributions
 promise+0.080
 crew+0.074
 forgot+0.073
 passengers+0.072
 scar+0.070
Neg logit contributions
 This-0.096
-0.092
 Playing-0.083
ore-0.082
elt-0.080
Token.
Token ID13
Feature activation-3.89e-02

Pos logit contributions
 This+0.049
to+0.048
 Playing+0.045
ore+0.044
ges+0.042
Neg logit contributions
 way-0.076
 promise-0.071
 forgot-0.066
 bit-0.064
 forget-0.064
Token Tom
Token ID4186
Feature activation+5.41e-02

Pos logit contributions
to+0.053
ore+0.052
uttering+0.050
anging+0.050
xy+0.047
Neg logit contributions
 way-0.077
 tears-0.069
 forgot-0.069
 promise-0.068
 bit-0.066
Token.
Token ID13
Feature activation-5.80e-02

Pos logit contributions
 This+0.008
to+0.008
 Playing+0.007
ore+0.007
anging+0.007
Neg logit contributions
 way-0.012
 promise-0.012
 forgot-0.011
 forget-0.011
 bit-0.011
Token
Token ID198
Feature activation-3.56e-02

Pos logit contributions
uttering+0.071
anging+0.071
to+0.071
ore+0.065
elt+0.065
Neg logit contributions
 way-0.115
 promise-0.109
 other-0.104
 tears-0.103
 pile-0.098
Token
Token ID198
Feature activation-3.44e-02

Pos logit contributions
elt+0.051
used+0.049
anging+0.048
 This+0.046
uttering+0.044
Neg logit contributions
 way-0.065
 promise-0.062
 other-0.062
 passengers-0.054
 forgot-0.053
TokenOne
Token ID3198
Feature activation+2.53e-02

Pos logit contributions
 This+0.060
to+0.057
ore+0.056
elt+0.056
 Playing+0.055
Neg logit contributions
 promise-0.054
 way-0.053
 forgot-0.048
 bit-0.047
 passengers-0.047
Token day
Token ID1110
Feature activation-4.12e-02

Pos logit contributions
 way+0.040
 promise+0.039
 forgot+0.036
 forget+0.034
 passengers+0.034
Neg logit contributions
 This-0.047
to-0.044
 Playing-0.043
ore-0.042
anging-0.041
Token,
Token ID11
Feature activation-2.87e-02

Pos logit contributions
to+0.069
 This+0.067
 Playing+0.066
anging+0.065
uttering+0.064
Neg logit contributions
 way-0.071
 forgot-0.063
 bit-0.063
 promise-0.062
 other-0.061
Token Anna
Token ID11735
Feature activation+4.47e-02

Pos logit contributions
 This+0.045
to+0.042
 Playing+0.042
ore+0.041
anging+0.039
Neg logit contributions
 way-0.053
 promise-0.051
 forgot-0.049
 bit-0.046
 forget-0.046
Token wants
Token ID3382
Feature activation-1.75e-02

Pos logit contributions
 way+0.079
 promise+0.077
 forgot+0.072
 passengers+0.070
 forget+0.069
Neg logit contributions
 This-0.071
to-0.066
 Playing-0.065
ore-0.064
anging-0.060
Token to
Token ID284
Feature activation+8.81e-03

Pos logit contributions
 This+0.018
to+0.016
 Playing+0.015
ore+0.015
anging+0.014
Neg logit contributions
 way-0.042
 promise-0.040
 forgot-0.039
 passengers-0.037
 forget-0.037
Token ride
Token ID6594
Feature activation-6.87e-02

Pos logit contributions
 way+0.013
 promise+0.012
 forgot+0.012
 passengers+0.011
 scar+0.011
Neg logit contributions
 This-0.017
to-0.015
 Playing-0.014
ore-0.014
anging-0.014
Token the
Token ID262
Feature activation+5.97e-02

Pos logit contributions
 This+0.108
to+0.107
anging+0.105
ore+0.105
elt+0.103
Neg logit contributions
 way-0.122
 promise-0.115
 other-0.108
 tears-0.106
 passengers-0.106
Token had
Token ID550
Feature activation+2.67e-02

Pos logit contributions
 way+0.017
 promise+0.016
 forgot+0.015
 bit+0.014
 forget+0.014
Neg logit contributions
 This-0.025
to-0.024
 Playing-0.024
ore-0.024
anging-0.023
Token a
Token ID257
Feature activation+6.03e-02

Pos logit contributions
 way+0.054
 promise+0.052
 forgot+0.050
 passengers+0.048
 forget+0.048
Neg logit contributions
 This-0.037
to-0.033
 Playing-0.033
ore-0.033
anging-0.030
Token very
Token ID845
Feature activation+4.93e-02

Pos logit contributions
 forgot+0.083
 passengers+0.082
 way+0.079
 promise+0.077
ode+0.077
Neg logit contributions
 This-0.109
to-0.096
ore-0.093
 Playing-0.090
 Today-0.090
Token long
Token ID890
Feature activation+2.88e-02

Pos logit contributions
 way+0.067
 promise+0.064
 forgot+0.060
 passengers+0.059
 forget+0.057
Neg logit contributions
 This-0.098
to-0.091
ore-0.090
 Playing-0.089
anging-0.085
Token journey
Token ID7002
Feature activation-6.16e-02

Pos logit contributions
 promise+0.036
 way+0.036
 forgot+0.034
 passengers+0.032
 forget+0.032
Neg logit contributions
 This-0.059
to-0.053
 Playing-0.053
ore-0.053
anging-0.050
Token ahead
Token ID4058
Feature activation-3.17e-02

Pos logit contributions
 This+0.083
 Playing+0.078
to+0.078
ore+0.073
elt+0.071
Neg logit contributions
 way-0.127
 promise-0.116
 forgot-0.110
 bit-0.109
 passengers-0.107
Token of
Token ID286
Feature activation-8.42e-04

Pos logit contributions
 This+0.044
to+0.044
 Playing+0.042
ore+0.040
elt+0.040
Neg logit contributions
 way-0.060
 promise-0.055
 passengers-0.052
 other-0.051
 bit-0.050
Token him
Token ID683
Feature activation+1.27e-02

Pos logit contributions
 This+0.001
to+0.001
ore+0.001
 Playing+0.001
anging+0.001
Neg logit contributions
 way-0.002
 promise-0.002
 forgot-0.002
 passengers-0.002
 forget-0.002
Token.
Token ID13
Feature activation-4.29e-02

Pos logit contributions
 way+0.026
 promise+0.024
 forgot+0.023
 passengers+0.022
 bit+0.022
Neg logit contributions
 This-0.017
to-0.016
 Playing-0.016
anging-0.015
ore-0.015
Token He
Token ID679
Feature activation+5.24e-02

Pos logit contributions
uttering+0.064
to+0.061
ging+0.060
ore+0.059
ing+0.059
Neg logit contributions
 way-0.083
 pile-0.071
 other-0.068
 promise-0.068
 tears-0.067
Token took
Token ID1718
Feature activation-1.36e-02

Pos logit contributions
 way+0.088
 promise+0.088
 forget+0.078
 tears+0.077
 forgot+0.075
Neg logit contributions
 This-0.088
to-0.082
 Playing-0.082
ore-0.077
-0.076
Token it
Token ID340
Feature activation+3.07e-02

Pos logit contributions
 way+0.018
 promise+0.018
 other+0.017
 passengers+0.016
 forgot+0.016
Neg logit contributions
 This-0.017
to-0.016
ore-0.016
 Playing-0.016
anging-0.016
Token has
Token ID468
Feature activation+3.24e-02

Pos logit contributions
 way+0.055
 promise+0.053
 passengers+0.052
 forgot+0.051
 forget+0.049
Neg logit contributions
 This-0.046
to-0.043
 Playing-0.042
ore-0.042
-0.040
Token to
Token ID284
Feature activation+2.98e-02

Pos logit contributions
 promise+0.064
 way+0.059
 forgot+0.058
 forget+0.057
ode+0.056
Neg logit contributions
 This-0.046
 Playing-0.038
to-0.038
elt-0.036
-0.035
Token go
Token ID467
Feature activation-2.69e-02

Pos logit contributions
 way+0.039
 forgot+0.037
 passengers+0.034
ode+0.034
 promise+0.034
Neg logit contributions
 This-0.057
to-0.048
 Playing-0.048
ore-0.047
oo-0.047
Token home
Token ID1363
Feature activation-5.37e-02

Pos logit contributions
 This+0.047
 Playing+0.045
to+0.044
ore+0.042
anging+0.042
Neg logit contributions
 way-0.045
 promise-0.043
 forgot-0.040
 bit-0.038
 forget-0.038
Token,"
Token ID553
Feature activation-2.69e-02

Pos logit contributions
 This+0.080
 Playing+0.073
to+0.073
ore+0.068
anging+0.067
Neg logit contributions
 way-0.105
 promise-0.104
 forgot-0.096
 forget-0.092
 bit-0.092
Token Ben
Token ID3932
Feature activation+4.59e-02

Pos logit contributions
 This+0.040
to+0.037
 Playing+0.036
ore+0.036
anging+0.034
Neg logit contributions
 way-0.051
 promise-0.050
 forgot-0.047
 passengers-0.045
 forget-0.045
Token says
Token ID1139
Feature activation-1.73e-02

Pos logit contributions
 way+0.076
 promise+0.072
 forgot+0.071
 passengers+0.068
 forget+0.066
Neg logit contributions
 This-0.079
 Playing-0.072
to-0.071
ore-0.069
-0.067
Token.
Token ID13
Feature activation-4.89e-02

Pos logit contributions
 This+0.027
 Playing+0.026
to+0.026
ore+0.025
elt+0.025
Neg logit contributions
 promise-0.031
 way-0.030
 tears-0.028
 other-0.026
 head-0.026
Token
Token ID198
Feature activation-2.87e-02

Pos logit contributions
used+0.064
anging+0.062
to+0.062
uttering+0.061
ore+0.060
Neg logit contributions
 way-0.093
 tears-0.089
 other-0.088
 bit-0.083
 pile-0.083
Token
Token ID198
Feature activation-2.31e-02

Pos logit contributions
used+0.040
 This+0.039
anging+0.038
elt+0.036
uttering+0.036
Neg logit contributions
 way-0.053
 other-0.053
 promise-0.052
 tears-0.050
 passengers-0.048
Token.
Token ID13
Feature activation-4.24e-02

Pos logit contributions
 This+0.031
to+0.030
 Playing+0.029
ore+0.028
ges+0.027
Neg logit contributions
 way-0.044
 forgot-0.038
 promise-0.038
 bit-0.037
 tears-0.036
Token He
Token ID679
Feature activation+6.34e-02

Pos logit contributions
to+0.041
uttering+0.040
 This+0.040
ore+0.040
ges+0.038
Neg logit contributions
 way-0.098
 promise-0.089
 forgot-0.087
 passengers-0.086
 tears-0.086
Token would
Token ID561
Feature activation-6.74e-03

Pos logit contributions
 way+0.090
 promise+0.089
 passengers+0.084
ode+0.082
 hood+0.082
Neg logit contributions
 This-0.107
to-0.107
 Playing-0.101
ore-0.100
-0.099
Token take
Token ID1011
Feature activation-8.63e-03

Pos logit contributions
 This+0.013
to+0.012
ore+0.012
 Playing+0.012
anging+0.011
Neg logit contributions
 way-0.009
 promise-0.008
 forgot-0.008
 passengers-0.008
 tears-0.008
Token big
Token ID1263
Feature activation+9.29e-03

Pos logit contributions
 This+0.013
to+0.012
ore+0.011
 Playing+0.011
+0.011
Neg logit contributions
 promise-0.017
 forgot-0.016
 way-0.015
 forget-0.015
 pile-0.014
Token breaths
Token ID45576
Feature activation-9.06e-02

Pos logit contributions
 way+0.012
 promise+0.012
 forgot+0.011
 passengers+0.011
 forget+0.010
Neg logit contributions
 This-0.019
to-0.018
 Playing-0.017
ore-0.017
ges-0.016
Token of
Token ID286
Feature activation+1.84e-02

Pos logit contributions
 This+0.127
to+0.115
ore+0.114
 Playing+0.112
anging+0.105
Neg logit contributions
 way-0.178
 promise-0.175
 forgot-0.166
 passengers-0.159
 forget-0.158
Token the
Token ID262
Feature activation+8.45e-02

Pos logit contributions
 forgot+0.037
 promise+0.036
 way+0.034
 forget+0.033
ode+0.033
Neg logit contributions
 This-0.024
ore-0.021
 Playing-0.021
to-0.020
 late-0.020
Token fresh
Token ID4713
Feature activation+4.30e-02

Pos logit contributions
 forgot+0.113
 promise+0.110
 way+0.101
 forget+0.094
 passengers+0.092
Neg logit contributions
 This-0.174
 Playing-0.153
-0.149
ore-0.147
elt-0.146
Token air
Token ID1633
Feature activation-3.31e-02

Pos logit contributions
 way+0.046
 promise+0.041
 forgot+0.036
 forget+0.034
 passengers+0.034
Neg logit contributions
 This-0.101
to-0.098
 Playing-0.095
ore-0.095
anging-0.092
Token and
Token ID290
Feature activation+2.92e-02

Pos logit contributions
 This+0.047
to+0.042
ore+0.042
 Playing+0.041
anging+0.038
Neg logit contributions
 way-0.065
 promise-0.063
 forgot-0.060
 passengers-0.058
 forget-0.057
Token you
Token ID345
Feature activation+2.81e-02

Pos logit contributions
 way+0.016
 promise+0.015
 forgot+0.015
 passengers+0.014
 forget+0.014
Neg logit contributions
 This-0.009
to-0.008
 Playing-0.008
ore-0.008
anging-0.007
Token.
Token ID13
Feature activation-3.17e-02

Pos logit contributions
 way+0.059
 promise+0.058
 forgot+0.054
 forget+0.052
 passengers+0.052
Neg logit contributions
 This-0.038
to-0.035
 Playing-0.033
ore-0.033
anging-0.032
Token We
Token ID775
Feature activation+4.25e-02

Pos logit contributions
uttering+0.044
to+0.041
anging+0.038
overed+0.037
unch+0.036
Neg logit contributions
 promise-0.060
 way-0.059
 forget-0.056
 forgot-0.055
 tears-0.054
Token can
Token ID460
Feature activation-9.43e-03

Pos logit contributions
 way+0.083
 tears+0.074
 passengers+0.073
 floor+0.071
 directions+0.070
Neg logit contributions
 This-0.057
ore-0.054
ges-0.049
 Playing-0.047
-0.047
Token c
Token ID269
Feature activation-3.16e-02

Pos logit contributions
 This+0.017
to+0.015
ore+0.015
 Playing+0.015
ges+0.014
Neg logit contributions
 way-0.015
 forgot-0.013
 promise-0.013
 passengers-0.013
 tears-0.012
Tokenuddle
Token ID24500
Feature activation-8.69e-02

Pos logit contributions
 This+0.075
ges+0.071
 Do+0.069
used+0.069
 Why+0.067
Neg logit contributions
 promise-0.030
 way-0.027
 scar-0.025
 tears-0.022
 hood-0.022
Token and
Token ID290
Feature activation+9.65e-03

Pos logit contributions
 This+0.127
uttering+0.120
anging+0.120
to+0.119
 Playing+0.118
Neg logit contributions
 way-0.155
 promise-0.150
 other-0.148
 scar-0.144
 h-0.143
Token sn
Token ID3013
Feature activation-4.14e-02

Pos logit contributions
 way+0.015
 promise+0.014
 forgot+0.013
 passengers+0.013
 tears+0.012
Neg logit contributions
 This-0.017
to-0.015
 Playing-0.015
 Do-0.015
ore-0.014
Tokenuggle
Token ID33498
Feature activation-6.45e-02

Pos logit contributions
 This+0.052
used+0.045
to+0.045
anging+0.043
 Playing+0.042
Neg logit contributions
 promise-0.084
 way-0.077
 scar-0.075
 bit-0.072
 pile-0.072
Token and
Token ID290
Feature activation+1.71e-02

Pos logit contributions
 This+0.091
 Playing+0.083
to+0.078
anging+0.078
elt+0.076
Neg logit contributions
 promise-0.131
 way-0.128
 forgot-0.121
 bit-0.119
 scar-0.116
Token keep
Token ID1394
Feature activation-8.58e-03

Pos logit contributions
 way+0.023
 promise+0.021
 forgot+0.020
 passengers+0.020
 tears+0.019
Neg logit contributions
 This-0.033
to-0.031
 Playing-0.030
ore-0.030
 late-0.029
Token with
Token ID351
Feature activation-4.70e-03

Pos logit contributions
 This+0.087
to+0.078
 Playing+0.077
ore+0.075
anging+0.070
Neg logit contributions
 way-0.148
 promise-0.140
 forgot-0.132
 bit-0.132
 tears-0.131
Token Max
Token ID5436
Feature activation+3.68e-03

Pos logit contributions
 This+0.005
to+0.004
 Playing+0.004
ore+0.004
anging+0.004
Neg logit contributions
 way-0.011
 promise-0.011
 forgot-0.010
 passengers-0.010
 forget-0.010
Token and
Token ID290
Feature activation+4.35e-03

Pos logit contributions
 way+0.007
 promise+0.006
 forgot+0.006
 bit+0.006
 forget+0.006
Neg logit contributions
 This-0.006
to-0.005
ore-0.005
 Playing-0.005
elt-0.005
Token accidentally
Token ID14716
Feature activation-4.01e-02

Pos logit contributions
 promise+0.010
 way+0.010
 passengers+0.009
 forgot+0.009
 tears+0.009
Neg logit contributions
 This-0.005
to-0.004
 Playing-0.004
ges-0.004
ore-0.004
Token tri
Token ID1333
Feature activation-6.59e-02

Pos logit contributions
 This+0.086
to+0.082
ore+0.079
 Playing+0.079
ges+0.076
Neg logit contributions
 way-0.049
 promise-0.048
 forgot-0.043
 passengers-0.041
 forget-0.040
Tokenpped
Token ID1496
Feature activation-8.71e-02

Pos logit contributions
 This+0.098
 Playing+0.085
to+0.080
ore+0.078
elt+0.075
Neg logit contributions
 way-0.128
 promise-0.120
 forgot-0.120
 tears-0.115
 bit-0.115
Token on
Token ID319
Feature activation-3.39e-02

Pos logit contributions
 This+0.142
uttering+0.141
 Playing+0.140
to+0.136
ires+0.136
Neg logit contributions
 way-0.156
 bit-0.134
 other-0.133
 tears-0.132
 h-0.125
Token a
Token ID257
Feature activation+2.34e-02

Pos logit contributions
 This+0.046
to+0.043
 Playing+0.042
ore+0.042
anging+0.039
Neg logit contributions
 way-0.069
 promise-0.066
 forgot-0.062
 tears-0.060
 passengers-0.060
Token cable
Token ID7862
Feature activation-5.15e-02

Pos logit contributions
 promise+0.023
 forgot+0.022
 way+0.022
 passengers+0.020
 forget+0.019
Neg logit contributions
 This-0.055
ore-0.051
to-0.051
 Playing-0.049
ges-0.048
Token.
Token ID13
Feature activation-6.60e-02

Pos logit contributions
 This+0.081
to+0.075
 Playing+0.074
ore+0.073
anging+0.068
Neg logit contributions
 way-0.093
 promise-0.090
 forgot-0.085
 passengers-0.081
 forget-0.081
Token She
Token ID1375
Feature activation+4.03e-02

Pos logit contributions
uttering+0.110
anging+0.104
ore+0.101
to+0.098
ires+0.097
Neg logit contributions
 way-0.114
 tears-0.107
 forgot-0.101
 bit-0.098
 other-0.094
Token the
Token ID262
Feature activation+5.01e-02

Pos logit contributions
 This+0.049
to+0.043
ore+0.040
ges+0.037
 Playing+0.037
Neg logit contributions
 promise-0.096
 way-0.093
 forgot-0.092
 forget-0.088
ode-0.085
Token comb
Token ID1974
Feature activation-7.62e-02

Pos logit contributions
 forgot+0.065
 promise+0.055
 forget+0.053
 way+0.052
 passengers+0.051
Neg logit contributions
 This-0.100
ore-0.094
-0.088
to-0.088
ges-0.085
Token and
Token ID290
Feature activation+5.03e-03

Pos logit contributions
 This+0.109
 Playing+0.099
to+0.099
ore+0.095
anging+0.090
Neg logit contributions
 way-0.150
 promise-0.146
 forgot-0.136
 passengers-0.131
 forget-0.131
Token started
Token ID2067
Feature activation-6.44e-02

Pos logit contributions
 promise+0.007
 way+0.007
ode+0.007
 passengers+0.006
 forget+0.006
Neg logit contributions
 This-0.009
to-0.009
ges-0.008
 Playing-0.008
elt-0.008
Token to
Token ID284
Feature activation-4.81e-03

Pos logit contributions
 This+0.076
 Playing+0.068
ore+0.066
to+0.065
anging+0.060
Neg logit contributions
 way-0.143
 promise-0.136
 forgot-0.130
 tears-0.128
 bit-0.126
Token massage
Token ID26900
Feature activation-9.22e-02

Pos logit contributions
 This+0.010
to+0.009
 Playing+0.008
ore+0.008
ges+0.008
Neg logit contributions
 way-0.006
 passengers-0.006
 promise-0.006
 forgot-0.005
 crew-0.005
Token Anna
Token ID11735
Feature activation+1.49e-02

Pos logit contributions
 This+0.127
to+0.116
 Playing+0.115
ore+0.111
anging+0.111
Neg logit contributions
 way-0.187
 promise-0.177
 forgot-0.168
 bit-0.165
 tears-0.163
Token's
Token ID338
Feature activation+4.76e-02

Pos logit contributions
 way+0.024
 promise+0.023
 forgot+0.022
 bit+0.021
 forget+0.021
Neg logit contributions
 This-0.026
to-0.024
 Playing-0.024
ore-0.024
anging-0.023
Token hair
Token ID4190
Feature activation-5.40e-02

Pos logit contributions
 forgot+0.055
 way+0.050
 promise+0.050
 passengers+0.048
 forget+0.047
Neg logit contributions
 This-0.102
to-0.093
ore-0.092
 Playing-0.092
elt-0.088
Token too
Token ID1165
Feature activation+1.33e-02

Pos logit contributions
 This+0.073
to+0.067
 Playing+0.067
ore+0.065
anging+0.061
Neg logit contributions
 way-0.111
 promise-0.106
 forgot-0.101
 bit-0.097
 forget-0.097
Token.
Token ID13
Feature activation-6.83e-02

Pos logit contributions
 way+0.023
 promise+0.022
 bit+0.021
 forgot+0.021
 forget+0.020
Neg logit contributions
 This-0.023
 Playing-0.022
to-0.021
ore-0.020
elt-0.020
Token.
Token ID13
Feature activation-6.11e-02

Pos logit contributions
 way+0.010
 promise+0.009
 forgot+0.009
 passengers+0.009
ode+0.009
Neg logit contributions
 This-0.014
ore-0.013
to-0.012
 Playing-0.012
ges-0.012
Token The
Token ID383
Feature activation+7.01e-02

Pos logit contributions
 This+0.066
to+0.062
ore+0.062
 Playing+0.059
anging+0.058
Neg logit contributions
 way-0.136
 promise-0.130
 forgot-0.125
 tears-0.121
 passengers-0.120
Token farmer
Token ID18739
Feature activation+1.17e-02

Pos logit contributions
 forgot+0.090
 way+0.083
 promise+0.080
 forget+0.076
ode+0.072
Neg logit contributions
ore-0.127
 This-0.124
-0.121
 late-0.119
 Playing-0.118
Token tried
Token ID3088
Feature activation-6.51e-02

Pos logit contributions
 way+0.019
 promise+0.018
 forget+0.017
 passengers+0.017
 coc+0.017
Neg logit contributions
to-0.017
ore-0.016
ing-0.016
 This-0.016
uck-0.015
Token to
Token ID284
Feature activation+5.66e-03

Pos logit contributions
 This+0.056
to+0.050
ore+0.045
 Playing+0.044
ges+0.040
Neg logit contributions
 promise-0.163
 way-0.162
 forgot-0.156
 passengers-0.151
 forget-0.150
Token cheer
Token ID14042
Feature activation-9.42e-02

Pos logit contributions
 way+0.008
 forgot+0.008
 regretted+0.007
ode+0.007
 pockets+0.007
Neg logit contributions
 This-0.009
 him-0.008
to-0.008
 here-0.008
?-0.008
Token him
Token ID683
Feature activation+2.32e-02

Pos logit contributions
 This+0.090
 Playing+0.082
to+0.080
ore+0.079
elt+0.076
Neg logit contributions
 way-0.226
 promise-0.218
 forgot-0.206
 tears-0.205
 passengers-0.203
Token up
Token ID510
Feature activation-3.35e-02

Pos logit contributions
 way+0.053
 promise+0.052
 tears+0.048
 forgot+0.047
 bit+0.046
Neg logit contributions
 This-0.025
 Playing-0.024
elt-0.023
ore-0.023
to-0.022
Token,
Token ID11
Feature activation-2.29e-02

Pos logit contributions
 This+0.044
to+0.040
 Playing+0.040
ore+0.039
anging+0.036
Neg logit contributions
 way-0.070
 promise-0.068
 forgot-0.064
 passengers-0.062
 forget-0.061
Token but
Token ID475
Feature activation-3.56e-03

Pos logit contributions
 This+0.035
 Playing+0.031
to+0.030
 late+0.029
ore+0.029
Neg logit contributions
 promise-0.041
 way-0.041
 forgot-0.038
 passengers-0.038
 forget-0.036
Token nothing
Token ID2147
Feature activation-7.05e-05

Pos logit contributions
 This+0.003
 late+0.003
ore+0.003
 Playing+0.003
to+0.003
Neg logit contributions
 promise-0.008
 way-0.008
ode-0.008
 passengers-0.008
 forgot-0.008