TOP ACTIVATIONS
MAX = 0.098

rubber band around the sho eb ox and pl ucks it
the oven and set the timer . They hoped
sandbox and the merry - go - round . They have
not too spicy !" Both Will and his dad laughed .
They polished until the je ep was so shiny it almost
use the oven and the timer . She says he can
the hills . Everywhere P add ington went , he found
love you very much . More than anything . But money
pushed the buttons on the timer . It be ep ed
it drove , the je ep kept hearing the same snap
things on the earth . More than you can count .
it said ' Feed the Ele ph ants '. Jim looked
and making the other one guess where it was .
a spoon , a sho eb ox and a rubber band
food for the hungry je ep . The family
nice to you too . Will you try , Anna ?"
You are very kind . Will you play with me when
, and the merry - go - round . He had
big rock near the je ep . She has an idea
aw , the merry - go - round . They think

MIN ACTIVATIONS
MIN = -0.106

mom my surprised him with freshly baked cookies . Tim my
" I 'm just washing ," she said . "
went home and enjoyed his freshly caught fish . <|endoftext|> Once
While Lily was washing her hair , she felt
The young woman stopped washing her clothes and smiled at
there , her mom was frying a tuna steak . It
. <|endoftext|> Bob bie was washing the dishes in the kitchen
The polar bear had been living in the ig loo for
happened . As George was washing his hands outside , he
named Lucy . Lucy was washing her hands . Spot wanted
As Lily was washing the dishes , she saw
saw her mother holding a freshly - b aked muff in
€ � � I am blo oming ! â € said
, Lily noticed that her herbs were not growing well .
. After she was done washing , Sally 's mom my
. Lily didn 't like washing her hair because it took
his mom . She was washing the dark laundry in the
Oh Jack , I was washing the shower , and somehow
. Lily didn 't like washing her hair because the shampoo
day , while Sammy was washing the bell , he heard

INTERVAL 0.047 - 0.098
CONTAINS 0.762%

want to mix more colors tomorrow . <|endoftext|> L ily loved
and then went for one more dip in the pond .
. They want to say hello to the frog . They
and Tess ran around the park , quickly gathering the dolls
happy and l icked the little girl 's face . The

INTERVAL -0.004 - 0.047
CONTAINS 58.434%

hesitant at first . They did not know if it was
was better to live in a small and cozy house than
not so scary . Soon , the picture was done .
normal brother and sister again . <|endoftext|> Tim had a small
of things in his garden . So , he went to

INTERVAL -0.055 - -0.004
CONTAINS 40.690%

. He ran and ran , trying to get it back
Her brother agreed and they had lots of fun playing together
could . One day , she saw a big hill with
slipped out of Jane 's hands and fell to the ground
. M ummy agreed it was a very

INTERVAL -0.106 - -0.055
CONTAINS 0.114%

. Benny loved to eat broccoli , but he was always
put the goodies in her basket - st omach . But
, she still missed her rad ish . <|endoftext|> Once upon
Ben cried out in pain . He let go of
mom my put on their apr ons and started cooking .
Token rubber
Token ID14239
Feature activation+5.52e-03

Pos logit contributions
ivering+0.004
 lately+0.004
ishly+0.004
ening+0.004
 asleep+0.004
Neg logit contributions
J-0.003
ves-0.002
ia-0.002
Jen-0.002
 Jen-0.002
Token band
Token ID4097
Feature activation+1.34e-02

Pos logit contributions
J+0.007
ves+0.006
ia+0.006
Jen+0.006
 Jen+0.006
Neg logit contributions
ivering-0.012
 lately-0.010
ishly-0.010
 asleep-0.010
ening-0.010
Token around
Token ID1088
Feature activation-8.60e-03

Pos logit contributions
J+0.023
Jen+0.022
ia+0.021
 Jen+0.021
 tad+0.021
Neg logit contributions
ivering-0.020
pping-0.017
ishly-0.017
 lately-0.017
ening-0.017
Token the
Token ID262
Feature activation+2.13e-02

Pos logit contributions
ivering+0.017
 lately+0.015
ishly+0.015
 asleep+0.015
ening+0.015
Neg logit contributions
J-0.012
ves-0.011
ia-0.011
Jen-0.011
 Jen-0.011
Token sho
Token ID7354
Feature activation-2.37e-02

Pos logit contributions
 other+0.022
J+0.021
 two+0.020
 third+0.019
ves+0.018
Neg logit contributions
ivering-0.049
ishly-0.048
 lately-0.047
istent-0.046
 streaming-0.044
Tokeneb
Token ID1765
Feature activation+9.84e-02

Pos logit contributions
ivering+0.035
 lately+0.029
ishly+0.029
ening+0.028
 asleep+0.028
Neg logit contributions
J-0.045
ves-0.043
ia-0.042
Jen-0.042
 Jen-0.042
Tokenox
Token ID1140
Feature activation+6.28e-02

Pos logit contributions
J+0.140
Jen+0.126
 tad+0.125
ves+0.116
 Jen+0.115
Neg logit contributions
ivering-0.187
pping-0.170
 asleep-0.164
ening-0.158
ishly-0.157
Token and
Token ID290
Feature activation+2.45e-02

Pos logit contributions
J+0.095
ves+0.091
ia+0.090
 Jen+0.088
Jen+0.088
Neg logit contributions
ivering-0.115
 lately-0.101
ishly-0.098
ening-0.097
 asleep-0.097
Token pl
Token ID458
Feature activation+2.34e-03

Pos logit contributions
J+0.032
ves+0.031
 Jen+0.030
ia+0.030
 Lia+0.030
Neg logit contributions
ivering-0.051
 lately-0.045
ishly-0.043
ening-0.043
 unatt-0.043
Tokenucks
Token ID6238
Feature activation+3.96e-02

Pos logit contributions
J+0.004
ves+0.004
ia+0.004
 Lia+0.004
 third+0.004
Neg logit contributions
ivering-0.004
pping-0.003
ishly-0.003
 asleep-0.003
 lately-0.003
Token it
Token ID340
Feature activation+7.99e-03

Pos logit contributions
ves+0.069
J+0.068
ia+0.065
Jen+0.064
 Lia+0.062
Neg logit contributions
ivering-0.060
 asleep-0.055
 lately-0.055
ening-0.052
 anymore-0.051
Token the
Token ID262
Feature activation-4.74e-04

Pos logit contributions
ves+0.011
ia+0.010
J+0.010
 Lia+0.010
Jen+0.010
Neg logit contributions
ivering-0.012
 lately-0.011
 asleep-0.011
ening-0.011
 anymore-0.011
Token oven
Token ID14361
Feature activation+9.68e-03

Pos logit contributions
ivering+0.001
 lately+0.001
 asleep+0.001
ishly+0.001
ening+0.001
Neg logit contributions
J-0.001
ves-0.001
ia-0.001
Jen-0.001
 Jen-0.001
Token and
Token ID290
Feature activation+1.26e-02

Pos logit contributions
J+0.013
ia+0.012
ves+0.012
 Jen+0.012
Jen+0.012
Neg logit contributions
ivering-0.020
 lately-0.017
ishly-0.017
ening-0.017
 unatt-0.016
Token set
Token ID900
Feature activation+5.08e-02

Pos logit contributions
J+0.017
ves+0.016
ia+0.016
Jen+0.016
 Lia+0.015
Neg logit contributions
ivering-0.025
 lately-0.022
 asleep-0.022
ening-0.022
ishly-0.022
Token the
Token ID262
Feature activation+1.16e-02

Pos logit contributions
J+0.098
Jen+0.091
 tad+0.087
Jud+0.086
Ar+0.085
Neg logit contributions
 asleep-0.068
 about-0.064
ening-0.059
 anymore-0.059
 such-0.057
Token timer
Token ID19781
Feature activation+9.40e-02

Pos logit contributions
J+0.015
ves+0.014
 Lia+0.014
ia+0.014
Jen+0.014
Neg logit contributions
ivering-0.024
 asleep-0.022
 unatt-0.021
 lately-0.021
ening-0.020
Token.
Token ID13
Feature activation+1.14e-02

Pos logit contributions
J+0.179
Jen+0.166
 Lia+0.165
 tad+0.159
ia+0.159
Neg logit contributions
ivering-0.128
 asleep-0.124
 about-0.114
ening-0.113
 lately-0.112
Token
Token ID198
Feature activation+8.42e-03

Pos logit contributions
ves+0.019
J+0.019
ia+0.018
Jen+0.017
 flag+0.017
Neg logit contributions
 asleep-0.016
 lately-0.016
 Playing-0.016
ivering-0.016
 about-0.015
Token
Token ID198
Feature activation+5.99e-03

Pos logit contributions
J+0.012
ves+0.012
ia+0.012
 Lia+0.011
 Jen+0.011
Neg logit contributions
ivering-0.014
 lately-0.012
 asleep-0.012
 about-0.012
 Playing-0.012
TokenThey
Token ID2990
Feature activation+9.41e-03

Pos logit contributions
ia+0.007
 Jen+0.007
 Lia+0.007
ves+0.006
 tad+0.006
Neg logit contributions
ivering-0.012
 lately-0.011
pping-0.011
Charl-0.010
 unatt-0.010
Token hoped
Token ID10719
Feature activation+4.23e-02

Pos logit contributions
J+0.013
ves+0.012
ia+0.012
Jen+0.012
 Jen+0.011
Neg logit contributions
ivering-0.019
 lately-0.017
ishly-0.016
ening-0.016
 asleep-0.016
Token sandbox
Token ID35204
Feature activation+3.55e-02

Pos logit contributions
J+0.017
ves+0.016
ia+0.015
Jen+0.015
 Jen+0.014
Neg logit contributions
ivering-0.030
 asleep-0.026
 lately-0.026
ishly-0.026
 unatt-0.026
Token and
Token ID290
Feature activation+2.54e-02

Pos logit contributions
J+0.063
ves+0.058
Jen+0.057
 Jen+0.055
 Lia+0.055
Neg logit contributions
ivering-0.056
 lately-0.049
 asleep-0.047
ishly-0.047
ening-0.047
Token the
Token ID262
Feature activation+1.74e-02

Pos logit contributions
J+0.029
 Jen+0.029
 Lia+0.028
ves+0.027
ia+0.027
Neg logit contributions
ivering-0.058
 lately-0.050
ening-0.049
ishly-0.049
pping-0.048
Token merry
Token ID44570
Feature activation+2.76e-02

Pos logit contributions
J+0.022
ves+0.021
ia+0.020
Jen+0.019
 Jen+0.018
Neg logit contributions
ivering-0.036
 asleep-0.033
 unatt-0.032
 lately-0.032
ishly-0.032
Token-
Token ID12
Feature activation+5.70e-02

Pos logit contributions
J+0.049
Jud+0.044
Jen+0.041
 Lia+0.041
ves+0.041
Neg logit contributions
ivering-0.046
ening-0.039
 anymore-0.039
opl-0.036
 asleep-0.036
Tokengo
Token ID2188
Feature activation+9.40e-02

Pos logit contributions
Jud+0.110
J+0.110
 clues+0.109
 third+0.108
 Lia+0.108
Neg logit contributions
ivering-0.063
he-0.055
chair-0.050
 unatt-0.050
opl-0.047
Token-
Token ID12
Feature activation+5.82e-02

Pos logit contributions
J+0.192
Jud+0.186
 tad+0.167
 third+0.166
 Shelby+0.166
Neg logit contributions
ivering-0.105
 anymore-0.103
opl-0.092
 alone-0.087
 around-0.083
Tokenround
Token ID744
Feature activation+4.42e-02

Pos logit contributions
 tad+0.133
J+0.131
 Lia+0.131
ia+0.129
 third+0.128
Neg logit contributions
ivering-0.040
opl-0.039
 unatt-0.033
 lately-0.031
 anymore-0.031
Token.
Token ID13
Feature activation+1.31e-02

Pos logit contributions
J+0.070
ves+0.064
Jen+0.064
ia+0.063
 Jen+0.061
Neg logit contributions
ivering-0.079
 lately-0.070
 asleep-0.070
ishly-0.069
ening-0.068
Token They
Token ID1119
Feature activation+1.92e-02

Pos logit contributions
J+0.015
ves+0.014
ia+0.014
Jen+0.013
 Jen+0.013
Neg logit contributions
ivering-0.029
 lately-0.026
ishly-0.026
 asleep-0.026
ening-0.026
Token have
Token ID423
Feature activation+1.23e-02

Pos logit contributions
J+0.019
 Jen+0.019
 Lia+0.018
ia+0.018
Jen+0.018
Neg logit contributions
ivering-0.047
 lately-0.041
ening-0.040
 unatt-0.040
ishly-0.039
Token not
Token ID407
Feature activation+2.42e-02

Pos logit contributions
J+0.012
ves+0.011
 Jen+0.011
ia+0.011
Jen+0.011
Neg logit contributions
ivering-0.026
ishly-0.022
 asleep-0.022
 lately-0.022
 unatt-0.022
Token too
Token ID1165
Feature activation+1.45e-02

Pos logit contributions
 Jen+0.033
J+0.032
ia+0.031
 two+0.030
ves+0.030
Neg logit contributions
ivering-0.048
ishly-0.043
 lately-0.040
Charl-0.039
opl-0.039
Token spicy
Token ID26880
Feature activation-1.65e-02

Pos logit contributions
J+0.018
ves+0.017
ia+0.017
Jen+0.017
 Jen+0.016
Neg logit contributions
ivering-0.031
 lately-0.027
ening-0.027
 asleep-0.026
ishly-0.026
Token!"
Token ID2474
Feature activation+1.64e-02

Pos logit contributions
ivering+0.032
ishly+0.027
 unatt+0.026
 streaming+0.025
ening+0.025
Neg logit contributions
ves-0.024
ia-0.024
J-0.024
 Jen-0.023
 Lia-0.022
Token Both
Token ID5747
Feature activation+3.43e-02

Pos logit contributions
J+0.021
ves+0.019
ia+0.019
 Jen+0.018
Jen+0.018
Neg logit contributions
ivering-0.035
 lately-0.031
ening-0.031
ishly-0.031
 unatt-0.030
Token Will
Token ID2561
Feature activation+9.30e-02

Pos logit contributions
J+0.041
ia+0.039
 two+0.038
ves+0.037
 Jen+0.037
Neg logit contributions
ivering-0.076
 unatt-0.067
ishly-0.065
 lately-0.065
pping-0.064
Token and
Token ID290
Feature activation-3.40e-04

Pos logit contributions
J+0.133
ves+0.125
ia+0.123
Jen+0.121
 Jen+0.120
Neg logit contributions
ivering-0.180
 lately-0.159
ishly-0.155
ening-0.154
 asleep-0.154
Token his
Token ID465
Feature activation+2.37e-02

Pos logit contributions
ivering+0.001
 lately+0.001
ishly+0.001
ening+0.001
 asleep+0.001
Neg logit contributions
J-0.000
ves-0.000
ia-0.000
 Jen-0.000
Jen-0.000
Token dad
Token ID9955
Feature activation-3.03e-03

Pos logit contributions
Jen+0.025
J+0.025
ves+0.025
 Lia+0.025
 Jen+0.023
Neg logit contributions
ivering-0.052
 lately-0.048
ishly-0.046
 asleep-0.046
ening-0.046
Token laughed
Token ID13818
Feature activation-1.21e-02

Pos logit contributions
ivering+0.006
 lately+0.005
 asleep+0.005
 unatt+0.005
ening+0.005
Neg logit contributions
J-0.004
ves-0.004
ia-0.004
 Jen-0.004
Jen-0.004
Token.
Token ID13
Feature activation-1.17e-02

Pos logit contributions
ivering+0.026
opl+0.023
 unatt+0.022
pping+0.022
 lately+0.022
Neg logit contributions
J-0.015
 they-0.014
 two-0.014
ia-0.014
 second-0.013
Token They
Token ID1119
Feature activation+1.02e-02

Pos logit contributions
ivering+0.004
 lately+0.003
 asleep+0.003
ishly+0.003
ening+0.003
Neg logit contributions
J-0.004
ves-0.003
ia-0.003
Jen-0.003
 Jen-0.003
Token polished
Token ID23895
Feature activation-1.80e-02

Pos logit contributions
J+0.014
ves+0.013
ia+0.013
 Jen+0.013
Jen+0.013
Neg logit contributions
ivering-0.021
 lately-0.018
ishly-0.017
 unatt-0.017
ening-0.017
Token until
Token ID1566
Feature activation-2.31e-03

Pos logit contributions
ivering+0.038
 lately+0.033
 unatt+0.032
ishly+0.032
 asleep+0.031
Neg logit contributions
J-0.024
ves-0.023
 Jen-0.022
ia-0.022
 Lia-0.021
Token the
Token ID262
Feature activation+1.37e-02

Pos logit contributions
ivering+0.004
 lately+0.004
 asleep+0.004
ening+0.004
 unatt+0.004
Neg logit contributions
J-0.003
ia-0.003
ves-0.003
Jen-0.003
 Jen-0.003
Token je
Token ID11223
Feature activation+3.82e-02

Pos logit contributions
ves+0.020
J+0.020
 Lia+0.019
ia+0.019
ila+0.017
Neg logit contributions
ivering-0.025
 unatt-0.023
 asleep-0.022
ening-0.022
 lately-0.022
Tokenep
Token ID538
Feature activation+9.19e-02

Pos logit contributions
J+0.048
ia+0.046
 Jen+0.046
 Lia+0.045
ves+0.043
Neg logit contributions
ivering-0.082
 unatt-0.070
pping-0.069
 asleep-0.067
opl-0.067
Token was
Token ID373
Feature activation+9.06e-03

Pos logit contributions
J+0.135
ves+0.123
ia+0.123
 Lia+0.122
Jen+0.121
Neg logit contributions
ivering-0.172
 asleep-0.150
ening-0.149
ishly-0.148
 lately-0.148
Token so
Token ID523
Feature activation+9.34e-03

Pos logit contributions
J+0.010
 two+0.010
 second+0.009
ves+0.009
 third+0.009
Neg logit contributions
ishly-0.020
ivering-0.020
opl-0.017
 lately-0.017
 Playing-0.017
Token shiny
Token ID22441
Feature activation-1.18e-02

Pos logit contributions
J+0.011
ves+0.010
ia+0.010
 Jen+0.009
Jen+0.009
Neg logit contributions
ivering-0.021
ishly-0.019
 lately-0.019
ening-0.018
 asleep-0.018
Token it
Token ID340
Feature activation+1.33e-02

Pos logit contributions
ivering+0.025
ishly+0.021
opl+0.020
Charl+0.020
istent+0.020
Neg logit contributions
J-0.015
ia-0.015
ves-0.015
 they-0.014
 two-0.014
Token almost
Token ID2048
Feature activation+3.16e-02

Pos logit contributions
J+0.016
ves+0.016
ia+0.015
 Jen+0.014
Jen+0.014
Neg logit contributions
ivering-0.030
 lately-0.026
ishly-0.025
ening-0.025
 asleep-0.025
Token use
Token ID779
Feature activation-1.44e-03

Pos logit contributions
ivering+0.001
 lately+0.001
ishly+0.001
ening+0.001
pping+0.001
Neg logit contributions
J-0.001
ves-0.001
ia-0.001
Jen-0.001
 Lia-0.001
Token the
Token ID262
Feature activation-7.07e-03

Pos logit contributions
ivering+0.003
 lately+0.003
ishly+0.003
ening+0.003
 asleep+0.003
Neg logit contributions
J-0.002
ves-0.002
ia-0.002
Jen-0.002
 Jen-0.002
Token oven
Token ID14361
Feature activation+5.57e-03

Pos logit contributions
ivering+0.015
 lately+0.013
 asleep+0.013
ening+0.013
 unatt+0.013
Neg logit contributions
J-0.009
ves-0.008
Jen-0.008
ia-0.008
 Lia-0.008
Token and
Token ID290
Feature activation+1.34e-02

Pos logit contributions
J+0.009
ves+0.009
ia+0.008
Jen+0.008
 Jen+0.008
Neg logit contributions
ivering-0.010
 lately-0.009
 asleep-0.008
ishly-0.008
ening-0.008
Token the
Token ID262
Feature activation+6.74e-03

Pos logit contributions
J+0.017
ves+0.016
ia+0.015
 Jen+0.015
Jen+0.015
Neg logit contributions
ivering-0.029
 lately-0.025
ishly-0.025
ening-0.025
 asleep-0.024
Token timer
Token ID19781
Feature activation+9.17e-02

Pos logit contributions
J+0.009
ves+0.008
Jen+0.008
ia+0.008
 Lia+0.008
Neg logit contributions
ivering-0.014
 asleep-0.012
 lately-0.012
 unatt-0.012
ening-0.012
Token.
Token ID13
Feature activation+7.35e-03

Pos logit contributions
J+0.155
Jen+0.137
 Lia+0.133
ves+0.131
ia+0.130
Neg logit contributions
ivering-0.147
 lately-0.135
 asleep-0.134
ening-0.132
ishly-0.130
Token She
Token ID1375
Feature activation+4.88e-03

Pos logit contributions
J+0.011
ves+0.011
ia+0.010
Jen+0.010
 Lia+0.009
Neg logit contributions
ivering-0.013
 lately-0.012
 asleep-0.012
ishly-0.012
ening-0.011
Token says
Token ID1139
Feature activation+4.92e-02

Pos logit contributions
J+0.006
ves+0.006
ia+0.006
 Jen+0.006
Jen+0.006
Neg logit contributions
ivering-0.010
 lately-0.009
ishly-0.009
ening-0.009
 unatt-0.009
Token he
Token ID339
Feature activation-1.49e-02

Pos logit contributions
J+0.066
Jen+0.062
ves+0.060
ia+0.060
Ar+0.055
Neg logit contributions
ivering-0.091
 lately-0.089
 asleep-0.088
ishly-0.083
 about-0.083
Token can
Token ID460
Feature activation+2.13e-02

Pos logit contributions
ivering+0.028
 lately+0.025
ishly+0.024
ening+0.024
 asleep+0.024
Neg logit contributions
J-0.022
ves-0.021
ia-0.021
 Jen-0.021
Jen-0.021
Token the
Token ID262
Feature activation+2.36e-02

Pos logit contributions
ves+0.041
J+0.040
ia+0.039
Jen+0.038
 Lia+0.036
Neg logit contributions
ivering-0.048
 lately-0.046
 asleep-0.045
ening-0.044
 unatt-0.043
Token hills
Token ID18639
Feature activation+4.72e-02

Pos logit contributions
J+0.027
ia+0.025
Jen+0.025
ves+0.025
 Jen+0.024
Neg logit contributions
ivering-0.052
 lately-0.047
ishly-0.046
ening-0.046
 unatt-0.045
Token.
Token ID13
Feature activation+6.35e-03

Pos logit contributions
J+0.071
ves+0.067
ia+0.066
Jen+0.065
 Jen+0.064
Neg logit contributions
ivering-0.088
 lately-0.078
ishly-0.076
ening-0.075
 asleep-0.075
Token Everywhere
Token ID48201
Feature activation+4.32e-02

Pos logit contributions
ves+0.012
J+0.012
ia+0.011
Jen+0.011
 Jen+0.011
Neg logit contributions
ivering-0.009
 lately-0.008
 asleep-0.008
ishly-0.007
ening-0.007
Token P
Token ID350
Feature activation+5.07e-02

Pos logit contributions
J+0.064
ves+0.062
ia+0.061
Jen+0.060
 Jen+0.058
Neg logit contributions
ivering-0.079
 lately-0.072
ening-0.068
 asleep-0.068
ishly-0.068
Tokenadd
Token ID2860
Feature activation+9.08e-02

Pos logit contributions
J+0.062
ia+0.057
ves+0.057
Jen+0.055
 Jen+0.055
Neg logit contributions
ivering-0.109
 lately-0.098
ishly-0.096
ening-0.095
 asleep-0.094
Tokenington
Token ID9557
Feature activation+2.74e-02

Pos logit contributions
J+0.205
ves+0.186
ia+0.184
Jen+0.184
 Lia+0.181
Neg logit contributions
ivering-0.106
ening-0.090
 lately-0.085
ishly-0.082
 asleep-0.080
Token went
Token ID1816
Feature activation-3.74e-03

Pos logit contributions
J+0.045
ia+0.043
Jen+0.043
ves+0.043
 Lia+0.042
Neg logit contributions
ivering-0.045
 lately-0.040
 asleep-0.038
ishly-0.038
ening-0.038
Token,
Token ID11
Feature activation-1.28e-02

Pos logit contributions
ivering+0.007
ishly+0.006
 unatt+0.006
 lately+0.006
 asleep+0.006
Neg logit contributions
J-0.006
ves-0.005
 Jen-0.005
ia-0.005
 Lia-0.005
Token he
Token ID339
Feature activation+8.29e-03

Pos logit contributions
ivering+0.025
 lately+0.022
ishly+0.022
ening+0.021
 asleep+0.021
Neg logit contributions
J-0.018
ves-0.017
 Jen-0.017
ia-0.017
Jen-0.017
Token found
Token ID1043
Feature activation+2.47e-04

Pos logit contributions
J+0.011
ves+0.010
ia+0.010
Jen+0.009
 Jen+0.009
Neg logit contributions
ivering-0.018
 lately-0.016
ishly-0.015
ening-0.015
 asleep-0.015
Token love
Token ID1842
Feature activation+6.83e-03

Pos logit contributions
ivering+0.026
 lately+0.023
ishly+0.023
ening+0.023
 asleep+0.023
Neg logit contributions
J-0.018
ves-0.017
 Jen-0.017
Jen-0.017
ia-0.017
Token you
Token ID345
Feature activation-3.12e-03

Pos logit contributions
 Jen+0.007
J+0.007
ves+0.007
ia+0.007
 Lia+0.006
Neg logit contributions
ivering-0.016
ishly-0.014
istent-0.013
ening-0.013
 lately-0.013
Token very
Token ID845
Feature activation-2.87e-02

Pos logit contributions
ivering+0.008
ening+0.008
opl+0.008
 streaming+0.007
Charl+0.007
Neg logit contributions
 two-0.002
 other-0.002
 second-0.002
 they-0.002
 third-0.002
Token much
Token ID881
Feature activation-1.98e-02

Pos logit contributions
ivering+0.058
 lately+0.052
ishly+0.050
ening+0.050
 asleep+0.050
Neg logit contributions
J-0.039
ves-0.036
ia-0.036
Jen-0.035
 Jen-0.035
Token.
Token ID13
Feature activation+1.14e-03

Pos logit contributions
ivering+0.049
ishly+0.044
 streaming+0.043
pping+0.042
ening+0.042
Neg logit contributions
J-0.018
ia-0.018
ves-0.017
 Jen-0.016
 other-0.015
Token More
Token ID3125
Feature activation+9.07e-02

Pos logit contributions
J+0.002
ves+0.002
ia+0.002
Jen+0.002
 Jen+0.002
Neg logit contributions
ivering-0.002
 lately-0.002
ishly-0.001
 asleep-0.001
ening-0.001
Token than
Token ID621
Feature activation+4.29e-04

Pos logit contributions
ia+0.107
 Jen+0.106
ves+0.104
J+0.103
 Lia+0.097
Neg logit contributions
ivering-0.193
ishly-0.180
pping-0.165
 unatt-0.163
istent-0.163
Token anything
Token ID1997
Feature activation+3.63e-02

Pos logit contributions
J+0.001
ves+0.001
ia+0.001
Jen+0.001
 Jen+0.001
Neg logit contributions
ivering-0.001
 lately-0.001
ishly-0.001
ening-0.001
 asleep-0.001
Token.
Token ID13
Feature activation+1.33e-02

Pos logit contributions
ves+0.038
 they+0.037
 other+0.036
ia+0.036
 Lia+0.034
Neg logit contributions
ivering-0.088
ishly-0.078
istent-0.073
 streaming-0.072
ening-0.072
Token But
Token ID887
Feature activation+2.13e-02

Pos logit contributions
J+0.025
ves+0.024
ia+0.023
Jen+0.023
 Jen+0.022
Neg logit contributions
ivering-0.020
 lately-0.017
ishly-0.017
 asleep-0.016
ening-0.016
Token money
Token ID1637
Feature activation-3.48e-03

Pos logit contributions
J+0.024
 Jen+0.024
ia+0.023
 Lia+0.022
ves+0.022
Neg logit contributions
ivering-0.048
ening-0.041
ishly-0.041
 lately-0.040
 asleep-0.040
Token pushed
Token ID7121
Feature activation+1.05e-02

Pos logit contributions
ivering+0.004
 asleep+0.003
ishly+0.003
 about+0.003
 lately+0.003
Neg logit contributions
J-0.003
Jen-0.003
 Jen-0.003
ves-0.003
 Lia-0.003
Token the
Token ID262
Feature activation+6.55e-04

Pos logit contributions
ves+0.020
J+0.018
Jen+0.018
ia+0.018
Dan+0.017
Neg logit contributions
 anymore-0.014
 asleep-0.014
ivering-0.014
ening-0.013
 lately-0.013
Token buttons
Token ID12163
Feature activation+3.51e-02

Pos logit contributions
J+0.001
Jen+0.001
 Jen+0.001
 Lia+0.001
ia+0.001
Neg logit contributions
ivering-0.001
 asleep-0.001
ishly-0.001
ening-0.001
 unatt-0.001
Token on
Token ID319
Feature activation-3.25e-03

Pos logit contributions
J+0.058
ves+0.056
ia+0.055
Jen+0.054
 Jen+0.053
Neg logit contributions
ivering-0.059
 lately-0.052
ishly-0.050
 asleep-0.050
ening-0.050
Token the
Token ID262
Feature activation-6.14e-05

Pos logit contributions
ivering+0.005
 asleep+0.005
 lately+0.005
 anymore+0.005
ening+0.004
Neg logit contributions
J-0.005
ves-0.005
Jen-0.005
ia-0.005
ila-0.005
Token timer
Token ID19781
Feature activation+9.06e-02

Pos logit contributions
ivering+0.000
ishly+0.000
 asleep+0.000
ening+0.000
 lately+0.000
Neg logit contributions
J-0.000
Jen-0.000
 Jen-0.000
ia-0.000
ves-0.000
Token.
Token ID13
Feature activation-8.86e-04

Pos logit contributions
J+0.168
Jen+0.148
ila+0.143
 tad+0.142
ves+0.142
Neg logit contributions
ivering-0.131
 asleep-0.122
ening-0.121
ishly-0.118
 lately-0.118
Token It
Token ID632
Feature activation+2.00e-02

Pos logit contributions
ivering+0.001
 asleep+0.001
 lately+0.001
ishly+0.001
ening+0.001
Neg logit contributions
J-0.002
ves-0.002
ia-0.002
Jen-0.002
 Jen-0.001
Token be
Token ID307
Feature activation+3.07e-02

Pos logit contributions
J+0.033
ia+0.030
ves+0.029
Jen+0.029
 Jen+0.029
Neg logit contributions
ivering-0.031
 asleep-0.028
ishly-0.027
 lately-0.027
ening-0.027
Tokenep
Token ID538
Feature activation+6.34e-02

Pos logit contributions
 Lia+0.043
J+0.043
 tad+0.042
ves+0.042
ia+0.041
Neg logit contributions
ivering-0.055
 asleep-0.049
 about-0.047
pping-0.047
 unatt-0.046
Tokened
Token ID276
Feature activation+5.30e-03

Pos logit contributions
J+0.102
ves+0.095
Jen+0.093
ia+0.093
 Jen+0.091
Neg logit contributions
ivering-0.112
 lately-0.097
 asleep-0.096
ishly-0.096
ening-0.096
Token it
Token ID340
Feature activation-2.86e-03

Pos logit contributions
J+0.014
ves+0.014
 Jen+0.014
ia+0.013
 Lia+0.013
Neg logit contributions
ivering-0.028
 lately-0.024
ishly-0.024
 asleep-0.024
 unatt-0.024
Token drove
Token ID10357
Feature activation+2.25e-02

Pos logit contributions
ivering+0.006
 lately+0.005
ishly+0.005
ening+0.005
 asleep+0.005
Neg logit contributions
J-0.003
ves-0.003
ia-0.003
 Jen-0.003
Jen-0.003
Token,
Token ID11
Feature activation+1.74e-03

Pos logit contributions
J+0.037
ves+0.035
 Jen+0.035
ia+0.034
Jen+0.034
Neg logit contributions
ivering-0.039
 lately-0.032
ishly-0.032
 asleep-0.032
ening-0.031
Token the
Token ID262
Feature activation+1.39e-02

Pos logit contributions
J+0.002
ia+0.002
ves+0.002
Jen+0.002
 Jen+0.002
Neg logit contributions
ivering-0.003
 lately-0.003
 asleep-0.003
ishly-0.003
ening-0.003
Token je
Token ID11223
Feature activation+3.69e-02

Pos logit contributions
J+0.024
ves+0.024
ia+0.023
 Lia+0.023
 Jen+0.022
Neg logit contributions
ivering-0.022
 unatt-0.019
 lately-0.019
 asleep-0.018
ening-0.018
Tokenep
Token ID538
Feature activation+9.02e-02

Pos logit contributions
J+0.044
 Jen+0.042
ia+0.042
 Lia+0.041
ves+0.040
Neg logit contributions
ivering-0.082
 unatt-0.070
pping-0.069
ening-0.067
ishly-0.067
Token kept
Token ID4030
Feature activation-1.17e-02

Pos logit contributions
J+0.137
ia+0.127
 Lia+0.126
ves+0.126
Jen+0.125
Neg logit contributions
ivering-0.167
 lately-0.145
ening-0.142
 asleep-0.142
pping-0.141
Token hearing
Token ID4854
Feature activation+1.72e-02

Pos logit contributions
ivering+0.019
 lately+0.016
ishly+0.016
 unatt+0.015
ening+0.015
Neg logit contributions
J-0.020
ves-0.019
 Jen-0.019
Jen-0.018
 two-0.018
Token the
Token ID262
Feature activation-7.85e-03

Pos logit contributions
J+0.024
ves+0.023
ia+0.022
 Jen+0.022
Jen+0.022
Neg logit contributions
ivering-0.034
 lately-0.030
ishly-0.029
ening-0.029
 asleep-0.029
Token same
Token ID976
Feature activation+1.80e-02

Pos logit contributions
ivering+0.014
 unatt+0.012
 lately+0.012
ening+0.012
ishly+0.012
Neg logit contributions
J-0.012
ves-0.012
ia-0.012
 Lia-0.012
 Jen-0.011
Token snap
Token ID11495
Feature activation+1.79e-02

Pos logit contributions
J+0.024
ves+0.023
ia+0.022
Jen+0.022
 Jen+0.022
Neg logit contributions
ivering-0.037
 lately-0.033
ishly-0.032
 asleep-0.032
ening-0.031
Token things
Token ID1243
Feature activation+1.69e-02

Pos logit contributions
J+0.042
ves+0.039
ia+0.038
 Jen+0.036
Jen+0.036
Neg logit contributions
ivering-0.121
ishly-0.109
 lately-0.109
 asleep-0.107
 unatt-0.106
Token on
Token ID319
Feature activation+1.88e-02

Pos logit contributions
ves+0.024
 Jen+0.023
ia+0.023
J+0.023
 they+0.022
Neg logit contributions
ivering-0.035
ishly-0.029
 lately-0.028
 unatt-0.027
ening-0.027
Token the
Token ID262
Feature activation+1.52e-02

Pos logit contributions
J+0.028
Jen+0.025
ves+0.025
ia+0.025
 Jen+0.024
Neg logit contributions
ivering-0.034
 lately-0.032
ening-0.031
 asleep-0.031
 anymore-0.030
Token earth
Token ID4534
Feature activation+2.48e-02

Pos logit contributions
J+0.018
ves+0.017
ia+0.017
 Jen+0.016
Jen+0.016
Neg logit contributions
ivering-0.034
 lately-0.029
ishly-0.029
 asleep-0.028
ening-0.028
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
J+0.036
ves+0.035
ia+0.034
 Jen+0.033
Jen+0.033
Neg logit contributions
ivering-0.048
ishly-0.041
 lately-0.041
ening-0.040
 asleep-0.039
Token More
Token ID3125
Feature activation+8.99e-02

Pos logit contributions
J+0.021
ves+0.021
ia+0.019
Jen+0.019
ila+0.018
Neg logit contributions
ivering-0.019
 lately-0.018
ishly-0.017
 asleep-0.017
ening-0.016
Token than
Token ID621
Feature activation+9.06e-03

Pos logit contributions
J+0.109
ia+0.103
ves+0.103
 Jen+0.101
Jen+0.098
Neg logit contributions
ivering-0.193
ishly-0.171
 lately-0.166
 unatt-0.164
 asleep-0.163
Token you
Token ID345
Feature activation+3.04e-02

Pos logit contributions
J+0.013
Jen+0.013
ves+0.013
ia+0.012
 Lia+0.011
Neg logit contributions
 lately-0.016
ivering-0.016
 asleep-0.015
 unatt-0.015
 anymore-0.015
Token can
Token ID460
Feature activation+3.90e-02

Pos logit contributions
J+0.044
ves+0.042
ia+0.041
 Jen+0.040
Jen+0.040
Neg logit contributions
ivering-0.059
 lately-0.051
ishly-0.051
ening-0.050
 asleep-0.049
Token count
Token ID954
Feature activation+3.42e-02

Pos logit contributions
J+0.044
ves+0.042
ia+0.042
 Jen+0.040
Jen+0.040
Neg logit contributions
ivering-0.088
ishly-0.078
 lately-0.078
ening-0.077
 unatt-0.076
Token.
Token ID13
Feature activation+7.99e-03

Pos logit contributions
J+0.051
ves+0.049
ia+0.048
 Jen+0.048
 Lia+0.047
Neg logit contributions
ivering-0.065
ishly-0.056
 lately-0.055
 unatt-0.054
ening-0.053
Token it
Token ID340
Feature activation+5.70e-03

Pos logit contributions
J+0.016
ves+0.015
Jen+0.015
ia+0.014
 Lia+0.014
Neg logit contributions
ivering-0.022
 lately-0.021
 asleep-0.020
ishly-0.020
 about-0.020
Token said
Token ID531
Feature activation+3.23e-02

Pos logit contributions
J+0.007
ves+0.007
ia+0.007
Jen+0.007
 Jen+0.007
Neg logit contributions
ivering-0.012
 lately-0.010
ishly-0.010
ening-0.010
 asleep-0.010
Token '
Token ID705
Feature activation-9.28e-03

Pos logit contributions
J+0.057
Jen+0.054
ves+0.052
ia+0.051
 Jen+0.051
Neg logit contributions
ivering-0.047
 lately-0.044
 asleep-0.043
ishly-0.042
 about-0.042
TokenFeed
Token ID18332
Feature activation-2.59e-02

Pos logit contributions
ivering+0.015
 lately+0.014
 unatt+0.014
pping+0.013
ening+0.013
Neg logit contributions
ia-0.015
ves-0.014
 Lia-0.014
 Jen-0.013
 mothers-0.013
Token the
Token ID262
Feature activation+2.86e-03

Pos logit contributions
ivering+0.043
 lately+0.037
ishly+0.036
 asleep+0.036
ening+0.036
Neg logit contributions
J-0.044
ves-0.042
ia-0.042
Jen-0.041
 Jen-0.041
Token Ele
Token ID15987
Feature activation+8.96e-02

Pos logit contributions
J+0.004
Jen+0.004
ves+0.004
 Jen+0.004
ia+0.004
Neg logit contributions
ivering-0.005
 lately-0.005
 anymore-0.005
 asleep-0.005
ishly-0.005
Tokenph
Token ID746
Feature activation+7.58e-02

Pos logit contributions
J+0.140
Jen+0.131
 Jen+0.124
ia+0.121
 Lia+0.120
Neg logit contributions
ivering-0.158
ishly-0.144
 lately-0.143
ening-0.141
pping-0.138
Tokenants
Token ID1187
Feature activation+6.71e-03

Pos logit contributions
J+0.122
Jen+0.113
 Jen+0.110
 Lia+0.109
ia+0.106
Neg logit contributions
ivering-0.133
 lately-0.118
ening-0.118
pping-0.114
ishly-0.112
Token'.
Token ID4458
Feature activation-2.95e-04

Pos logit contributions
ves+0.010
J+0.010
ia+0.009
 Jen+0.009
 two+0.009
Neg logit contributions
ivering-0.012
ening-0.010
 asleep-0.010
 lately-0.010
ishly-0.010
Token Jim
Token ID5395
Feature activation+1.42e-02

Pos logit contributions
ivering+0.001
 lately+0.001
ishly+0.001
ening+0.000
 about+0.000
Neg logit contributions
J-0.000
ves-0.000
Jen-0.000
ia-0.000
ila-0.000
Token looked
Token ID3114
Feature activation-1.17e-02

Pos logit contributions
J+0.018
ves+0.017
ia+0.017
Jen+0.016
 Jen+0.016
Neg logit contributions
ivering-0.030
 lately-0.027
 asleep-0.026
ishly-0.026
ening-0.026
Token and
Token ID290
Feature activation+7.03e-03

Pos logit contributions
J+0.066
Jen+0.063
 Jen+0.059
ves+0.059
ia+0.058
Neg logit contributions
ivering-0.048
 asleep-0.043
 anymore-0.043
 lately-0.042
ening-0.042
Token making
Token ID1642
Feature activation+1.12e-02

Pos logit contributions
J+0.010
ves+0.010
ia+0.010
 Jen+0.010
Jen+0.010
Neg logit contributions
ivering-0.013
 lately-0.012
ishly-0.011
ening-0.011
 asleep-0.011
Token the
Token ID262
Feature activation+2.51e-03

Pos logit contributions
J+0.017
Jen+0.016
ia+0.015
ves+0.014
ila+0.014
Neg logit contributions
ivering-0.019
ening-0.018
 asleep-0.018
 anymore-0.018
 about-0.018
Token other
Token ID584
Feature activation+6.13e-02

Pos logit contributions
J+0.004
ves+0.003
ia+0.003
Jen+0.003
 Jen+0.003
Neg logit contributions
ivering-0.005
 lately-0.004
ishly-0.004
 asleep-0.004
ening-0.004
Token one
Token ID530
Feature activation+2.83e-02

Pos logit contributions
J+0.089
ia+0.082
ves+0.081
Jen+0.081
 Jen+0.080
Neg logit contributions
ivering-0.122
ening-0.105
 asleep-0.104
 lately-0.103
ishly-0.102
Token guess
Token ID4724
Feature activation+8.96e-02

Pos logit contributions
J+0.047
Jen+0.044
ves+0.044
 Jen+0.042
ia+0.042
Neg logit contributions
ivering-0.048
 anymore-0.042
ening-0.041
 asleep-0.041
 lately-0.041
Token where
Token ID810
Feature activation+1.09e-02

Pos logit contributions
J+0.139
Jen+0.130
ia+0.120
Ar+0.117
 Lia+0.117
Neg logit contributions
ivering-0.148
 anymore-0.136
 about-0.136
ening-0.135
 lately-0.135
Token it
Token ID340
Feature activation+4.33e-03

Pos logit contributions
J+0.016
Jen+0.015
ia+0.014
ves+0.014
 Lia+0.013
Neg logit contributions
 asleep-0.019
ivering-0.019
 lately-0.018
ening-0.018
 anymore-0.018
Token was
Token ID373
Feature activation+5.44e-03

Pos logit contributions
J+0.006
ves+0.005
ia+0.005
Jen+0.005
 Jen+0.005
Neg logit contributions
ivering-0.009
 lately-0.008
 asleep-0.008
ishly-0.008
ening-0.008
Token.
Token ID13
Feature activation+7.74e-03

Pos logit contributions
J+0.008
ves+0.007
ia+0.007
Jen+0.007
 Jen+0.007
Neg logit contributions
ivering-0.011
 lately-0.009
ishly-0.009
ening-0.009
 asleep-0.009
Token
Token ID198
Feature activation+5.96e-03

Pos logit contributions
ves+0.014
J+0.013
ia+0.013
kins+0.012
 cor+0.012
Neg logit contributions
 Playing-0.010
 about-0.010
 anymore-0.010
 Eating-0.010
ivering-0.009
Token a
Token ID257
Feature activation+3.41e-02

Pos logit contributions
J+0.037
Jen+0.036
ia+0.034
ves+0.034
Dan+0.031
Neg logit contributions
 lately-0.039
 asleep-0.039
 about-0.037
 such-0.035
 operating-0.035
Token spoon
Token ID24556
Feature activation-2.85e-02

Pos logit contributions
J+0.046
ves+0.043
ia+0.042
Jen+0.042
 Jen+0.042
Neg logit contributions
ivering-0.068
 asleep-0.062
 lately-0.059
ishly-0.058
 unatt-0.058
Token,
Token ID11
Feature activation+2.28e-02

Pos logit contributions
ivering+0.055
 lately+0.048
ishly+0.047
ening+0.046
 asleep+0.046
Neg logit contributions
J-0.042
ves-0.040
ia-0.039
 Jen-0.038
Jen-0.038
Token a
Token ID257
Feature activation+4.34e-02

Pos logit contributions
J+0.036
ves+0.035
ia+0.034
Jen+0.034
 Jen+0.031
Neg logit contributions
ivering-0.039
 lately-0.036
 asleep-0.036
ishly-0.035
 unatt-0.034
Token sho
Token ID7354
Feature activation-3.90e-02

Pos logit contributions
J+0.057
ves+0.053
ia+0.053
Jen+0.052
 Jen+0.051
Neg logit contributions
ivering-0.088
 lately-0.078
 asleep-0.078
ishly-0.077
ening-0.076
Tokeneb
Token ID1765
Feature activation+8.93e-02

Pos logit contributions
ivering+0.067
 asleep+0.058
 lately+0.057
 unatt+0.057
ishly+0.054
Neg logit contributions
J-0.065
Jen-0.062
ia-0.062
ves-0.062
 Jen-0.061
Tokenox
Token ID1140
Feature activation+3.84e-02

Pos logit contributions
J+0.137
Jen+0.125
 tad+0.121
Ah+0.118
Quick+0.112
Neg logit contributions
ivering-0.148
pping-0.142
ening-0.132
owing-0.130
 asleep-0.130
Token and
Token ID290
Feature activation+4.39e-02

Pos logit contributions
ves+0.053
J+0.053
ia+0.052
 Jen+0.050
 Lia+0.049
Neg logit contributions
ivering-0.075
 lately-0.065
ishly-0.064
 unatt-0.063
ening-0.062
Token a
Token ID257
Feature activation+4.68e-02

Pos logit contributions
J+0.068
Jen+0.062
ia+0.060
ves+0.059
Dan+0.057
Neg logit contributions
 asleep-0.073
 lately-0.071
ivering-0.068
 about-0.068
 streaming-0.066
Token rubber
Token ID14239
Feature activation+9.09e-03

Pos logit contributions
J+0.061
ves+0.056
ia+0.056
Jen+0.055
 Jen+0.054
Neg logit contributions
ivering-0.096
 asleep-0.086
 lately-0.084
ishly-0.083
ening-0.083
Token band
Token ID4097
Feature activation+2.36e-02

Pos logit contributions
J+0.010
ves+0.010
ia+0.009
Jen+0.009
 Jen+0.009
Neg logit contributions
ivering-0.020
 lately-0.018
ishly-0.018
 asleep-0.018
ening-0.018
Token food
Token ID2057
Feature activation-2.15e-02

Pos logit contributions
J+0.011
ves+0.010
ia+0.010
Jen+0.010
 Lia+0.010
Neg logit contributions
ivering-0.012
 lately-0.010
 asleep-0.010
ishly-0.010
ening-0.010
Token for
Token ID329
Feature activation-1.03e-02

Pos logit contributions
ivering+0.044
ishly+0.036
ening+0.036
istent+0.036
pping+0.035
Neg logit contributions
ves-0.029
ia-0.029
J-0.029
 Jen-0.029
 they-0.028
Token the
Token ID262
Feature activation+2.74e-03

Pos logit contributions
ivering+0.016
 asleep+0.016
 lately+0.016
 anymore+0.015
ening+0.015
Neg logit contributions
J-0.016
Jen-0.016
ia-0.015
ves-0.015
ila-0.014
Token hungry
Token ID14720
Feature activation+2.43e-02

Pos logit contributions
ves+0.005
J+0.005
ia+0.005
 Lia+0.004
ila+0.004
Neg logit contributions
ivering-0.004
 unatt-0.004
 lately-0.004
 asleep-0.004
 suffering-0.004
Token je
Token ID11223
Feature activation+3.62e-02

Pos logit contributions
J+0.034
ves+0.031
ia+0.029
Jen+0.029
 Lia+0.029
Neg logit contributions
ivering-0.048
 lately-0.045
 asleep-0.044
ening-0.043
 unatt-0.042
Tokenep
Token ID538
Feature activation+8.92e-02

Pos logit contributions
 Jen+0.049
 Lia+0.048
ia+0.048
J+0.047
 Mia+0.044
Neg logit contributions
ivering-0.076
 unatt-0.066
pping-0.064
opl-0.059
 asleep-0.059
Token.
Token ID13
Feature activation+2.46e-03

Pos logit contributions
J+0.132
ves+0.125
ia+0.123
Jen+0.121
 Jen+0.120
Neg logit contributions
ivering-0.168
 lately-0.147
ishly-0.144
ening-0.143
 asleep-0.142
Token
Token ID198
Feature activation+4.34e-03

Pos logit contributions
J+0.004
ves+0.004
ia+0.004
Jen+0.004
ila+0.004
Neg logit contributions
ivering-0.003
 lately-0.003
ishly-0.003
 asleep-0.003
 Playing-0.003
Token
Token ID198
Feature activation+9.29e-04

Pos logit contributions
J+0.007
ia+0.007
 Jen+0.007
ves+0.007
 flag+0.007
Neg logit contributions
ivering-0.006
 lately-0.006
 about-0.006
Charl-0.005
 asleep-0.005
TokenThe
Token ID464
Feature activation+2.54e-03

Pos logit contributions
 Jen+0.001
ia+0.001
J+0.001
ves+0.001
 Lia+0.001
Neg logit contributions
ivering-0.002
 lately-0.002
pping-0.002
Charl-0.002
ening-0.002
Token family
Token ID1641
Feature activation-1.12e-02

Pos logit contributions
ves+0.005
J+0.004
 Lia+0.004
ia+0.004
ila+0.004
Neg logit contributions
ivering-0.004
 weeping-0.004
 unatt-0.004
 suffering-0.003
 stranded-0.003
Token nice
Token ID3621
Feature activation-7.30e-03

Pos logit contributions
J+0.002
 Jen+0.002
ves+0.002
ia+0.002
 Lia+0.002
Neg logit contributions
ivering-0.004
 lately-0.003
ishly-0.003
ening-0.003
 asleep-0.003
Token to
Token ID284
Feature activation+1.58e-02

Pos logit contributions
ivering+0.016
ishly+0.014
ening+0.013
 streaming+0.013
istent+0.013
Neg logit contributions
J-0.009
ia-0.008
 Jen-0.008
ves-0.008
 two-0.008
Token you
Token ID345
Feature activation+3.01e-02

Pos logit contributions
J+0.024
ves+0.022
ia+0.022
 Jen+0.022
Jen+0.022
Neg logit contributions
ivering-0.030
 lately-0.026
ishly-0.025
ening-0.025
 asleep-0.025
Token too
Token ID1165
Feature activation+1.03e-02

Pos logit contributions
J+0.038
ves+0.037
ia+0.036
 Lia+0.035
 Jen+0.034
Neg logit contributions
ivering-0.062
ening-0.054
ishly-0.054
 lately-0.054
 streaming-0.053
Token.
Token ID13
Feature activation+5.29e-03

Pos logit contributions
J+0.013
ves+0.013
ia+0.013
 Jen+0.012
Jen+0.012
Neg logit contributions
ivering-0.021
ishly-0.019
 lately-0.019
ening-0.018
 asleep-0.018
Token Will
Token ID2561
Feature activation+8.91e-02

Pos logit contributions
J+0.009
ves+0.009
ia+0.009
Jen+0.009
 Jen+0.008
Neg logit contributions
ivering-0.008
 lately-0.007
ishly-0.007
 asleep-0.007
ening-0.007
Token you
Token ID345
Feature activation+1.64e-02

Pos logit contributions
J+0.104
ves+0.102
ia+0.098
 Jen+0.094
 Lia+0.092
Neg logit contributions
ivering-0.197
ishly-0.173
 asleep-0.171
ening-0.171
 lately-0.170
Token try
Token ID1949
Feature activation+1.70e-02

Pos logit contributions
J+0.020
ves+0.020
ia+0.019
 Lia+0.018
 Jen+0.018
Neg logit contributions
ivering-0.035
 lately-0.031
ening-0.031
 unatt-0.030
ishly-0.030
Token,
Token ID11
Feature activation-5.78e-03

Pos logit contributions
J+0.022
ves+0.021
ia+0.020
 Jen+0.020
 Lia+0.020
Neg logit contributions
ivering-0.037
ishly-0.032
 lately-0.031
 unatt-0.031
ening-0.030
Token Anna
Token ID11735
Feature activation+2.04e-02

Pos logit contributions
ivering+0.011
 lately+0.010
ishly+0.010
ening+0.010
 asleep+0.010
Neg logit contributions
J-0.008
ves-0.008
ia-0.008
Jen-0.008
 Jen-0.007
Token?"
Token ID1701
Feature activation+1.80e-02

Pos logit contributions
ves+0.025
ia+0.024
 they+0.023
J+0.023
 two+0.023
Neg logit contributions
ivering-0.043
 streaming-0.039
ening-0.038
ishly-0.037
 unatt-0.036
Token You
Token ID921
Feature activation+2.19e-02

Pos logit contributions
J+0.004
 Jen+0.004
ia+0.004
Jen+0.004
ves+0.004
Neg logit contributions
ivering-0.004
 lately-0.003
ening-0.003
ishly-0.003
 unatt-0.003
Token are
Token ID389
Feature activation-1.20e-02

Pos logit contributions
 two+0.025
J+0.024
ves+0.023
ia+0.023
 other+0.022
Neg logit contributions
ivering-0.050
ening-0.044
 lately-0.044
ishly-0.042
 unatt-0.041
Token very
Token ID845
Feature activation-1.78e-02

Pos logit contributions
ivering+0.031
ening+0.028
ishly+0.028
istent+0.028
 lately+0.027
Neg logit contributions
 two-0.011
 Jen-0.011
 Lia-0.010
ia-0.010
J-0.009
Token kind
Token ID1611
Feature activation-4.76e-03

Pos logit contributions
ivering+0.038
 lately+0.034
ishly+0.033
 asleep+0.032
ening+0.032
Neg logit contributions
J-0.022
ves-0.021
ia-0.020
Jen-0.020
 Jen-0.020
Token.
Token ID13
Feature activation+4.91e-03

Pos logit contributions
ivering+0.010
ishly+0.009
ening+0.009
pping+0.009
 unatt+0.009
Neg logit contributions
J-0.006
ia-0.006
 Jen-0.006
ves-0.005
 Lia-0.005
Token Will
Token ID2561
Feature activation+8.91e-02

Pos logit contributions
J+0.008
ves+0.008
ia+0.008
 Jen+0.008
Jen+0.008
Neg logit contributions
ivering-0.008
 lately-0.007
ishly-0.007
ening-0.007
 asleep-0.007
Token you
Token ID345
Feature activation+1.62e-02

Pos logit contributions
ves+0.101
J+0.099
ia+0.097
 Jen+0.093
ila+0.089
Neg logit contributions
ivering-0.201
ishly-0.178
ening-0.173
 asleep-0.173
 streaming-0.171
Token play
Token ID711
Feature activation+1.87e-02

Pos logit contributions
ves+0.017
ia+0.017
 two+0.016
J+0.016
 Lia+0.016
Neg logit contributions
ivering-0.037
ening-0.033
 lately-0.033
 unatt-0.032
 streaming-0.031
Token with
Token ID351
Feature activation+6.14e-03

Pos logit contributions
J+0.025
ves+0.024
ia+0.024
 Lia+0.023
 Jen+0.022
Neg logit contributions
ivering-0.037
ening-0.034
ishly-0.034
istent-0.033
 streaming-0.033
Token me
Token ID502
Feature activation+1.33e-02

Pos logit contributions
ves+0.010
J+0.010
ia+0.010
 Jen+0.010
 Lia+0.009
Neg logit contributions
ivering-0.011
ishly-0.009
ening-0.009
istent-0.009
 lately-0.009
Token when
Token ID618
Feature activation+1.76e-02

Pos logit contributions
ia+0.019
J+0.019
ves+0.019
 Jen+0.018
ila+0.017
Neg logit contributions
ivering-0.025
ishly-0.023
ening-0.022
 streaming-0.022
istent-0.021
Token,
Token ID11
Feature activation+6.56e-03

Pos logit contributions
J+0.074
ves+0.071
ia+0.069
 Jen+0.068
Jen+0.068
Neg logit contributions
ivering-0.080
 lately-0.068
ishly-0.067
ening-0.066
 asleep-0.065
Token and
Token ID290
Feature activation+1.47e-02

Pos logit contributions
J+0.010
ves+0.010
ia+0.010
Jen+0.010
 Jen+0.010
Neg logit contributions
ivering-0.012
 lately-0.010
ishly-0.010
ening-0.010
 asleep-0.010
Token the
Token ID262
Feature activation+1.36e-02

Pos logit contributions
J+0.023
ia+0.022
ves+0.022
Jen+0.022
 Lia+0.020
Neg logit contributions
ivering-0.025
 lately-0.023
 asleep-0.023
ening-0.022
 unatt-0.022
Token merry
Token ID44570
Feature activation+2.22e-02

Pos logit contributions
ia+0.018
ves+0.018
J+0.018
Jen+0.017
 Lia+0.016
Neg logit contributions
ivering-0.027
 asleep-0.025
 unatt-0.025
 lately-0.025
ening-0.024
Token-
Token ID12
Feature activation+4.84e-02

Pos logit contributions
J+0.037
 Lia+0.035
Jen+0.034
 Jen+0.033
Jud+0.033
Neg logit contributions
ivering-0.039
ening-0.034
 lately-0.032
 unatt-0.032
 asleep-0.032
Tokengo
Token ID2188
Feature activation+8.90e-02

Pos logit contributions
 Lia+0.091
ia+0.091
J+0.089
Jud+0.087
 tad+0.086
Neg logit contributions
ivering-0.063
opl-0.056
 unatt-0.055
pping-0.051
he-0.050
Token-
Token ID12
Feature activation+4.91e-02

Pos logit contributions
J+0.164
Jud+0.156
 Lia+0.155
ia+0.152
Jen+0.149
Neg logit contributions
ivering-0.125
ening-0.110
opl-0.109
pping-0.109
 anymore-0.108
Tokenround
Token ID744
Feature activation+4.00e-02

Pos logit contributions
ia+0.099
 Lia+0.099
J+0.098
 tad+0.096
kins+0.092
Neg logit contributions
ivering-0.054
opl-0.053
 lately-0.048
 unatt-0.048
pping-0.047
Token.
Token ID13
Feature activation+2.67e-03

Pos logit contributions
J+0.059
ves+0.056
ia+0.055
Jen+0.054
 Jen+0.053
Neg logit contributions
ivering-0.076
 lately-0.067
ishly-0.065
ening-0.065
 asleep-0.064
Token He
Token ID679
Feature activation+1.62e-02

Pos logit contributions
J+0.005
ves+0.005
ia+0.005
Jen+0.004
 Jen+0.004
Neg logit contributions
ivering-0.004
 lately-0.004
ishly-0.004
 asleep-0.003
ening-0.003
Token had
Token ID550
Feature activation-4.21e-03

Pos logit contributions
J+0.023
ves+0.022
ia+0.021
Jen+0.021
 Jen+0.021
Neg logit contributions
ivering-0.031
 lately-0.028
ishly-0.027
 asleep-0.027
ening-0.027
Token big
Token ID1263
Feature activation-5.41e-03

Pos logit contributions
J+0.016
ves+0.015
ia+0.015
 Lia+0.014
 Jen+0.014
Neg logit contributions
ivering-0.030
 asleep-0.027
ening-0.026
 lately-0.026
 unatt-0.026
Token rock
Token ID3881
Feature activation-1.74e-02

Pos logit contributions
ivering+0.012
 lately+0.011
ishly+0.011
pping+0.011
 unatt+0.011
Neg logit contributions
J-0.006
 Jen-0.006
ia-0.005
Jen-0.005
ves-0.005
Token near
Token ID1474
Feature activation+2.00e-02

Pos logit contributions
ivering+0.031
 lately+0.027
ishly+0.026
ening+0.026
 asleep+0.026
Neg logit contributions
J-0.027
ves-0.026
ia-0.026
 Jen-0.026
Jen-0.026
Token the
Token ID262
Feature activation+1.25e-02

Pos logit contributions
ves+0.036
J+0.034
ia+0.033
Jen+0.032
lan+0.032
Neg logit contributions
ivering-0.028
 asleep-0.026
 lately-0.026
 anymore-0.026
ening-0.025
Token je
Token ID11223
Feature activation+3.57e-02

Pos logit contributions
J+0.016
ia+0.015
ves+0.014
Jen+0.014
 Jen+0.014
Neg logit contributions
ivering-0.027
 lately-0.024
ishly-0.023
ening-0.023
 asleep-0.023
Tokenep
Token ID538
Feature activation+8.88e-02

Pos logit contributions
J+0.041
 Jen+0.040
ia+0.039
ves+0.039
 Lia+0.038
Neg logit contributions
ivering-0.079
 unatt-0.069
pping-0.067
 asleep-0.066
ishly-0.066
Token.
Token ID13
Feature activation+4.63e-03

Pos logit contributions
J+0.147
ves+0.136
Jen+0.133
ia+0.133
 Lia+0.131
Neg logit contributions
ivering-0.153
ening-0.131
ishly-0.129
 lately-0.129
pping-0.128
Token She
Token ID1375
Feature activation+4.40e-03

Pos logit contributions
ves+0.010
J+0.010
ia+0.009
Jen+0.009
 Jen+0.009
Neg logit contributions
ivering-0.005
 lately-0.005
 asleep-0.004
ishly-0.004
ening-0.004
Token has
Token ID468
Feature activation+6.76e-03

Pos logit contributions
ia+0.005
J+0.005
 Lia+0.005
ves+0.005
 Jen+0.005
Neg logit contributions
ivering-0.010
 lately-0.009
 unatt-0.008
ishly-0.008
 asleep-0.008
Token an
Token ID281
Feature activation-1.22e-02

Pos logit contributions
J+0.009
ves+0.008
ia+0.008
Jen+0.008
 Lia+0.008
Neg logit contributions
ivering-0.014
 lately-0.012
 asleep-0.012
ishly-0.012
ening-0.012
Token idea
Token ID2126
Feature activation+1.37e-02

Pos logit contributions
ivering+0.028
 asleep+0.026
 lately+0.025
ishly+0.025
 unatt+0.025
Neg logit contributions
ia-0.012
J-0.012
 Jen-0.011
ves-0.011
Jen-0.011
Tokenaw
Token ID707
Feature activation+6.19e-02

Pos logit contributions
J+0.078
ves+0.074
Jen+0.073
ia+0.072
 Jen+0.071
Neg logit contributions
ivering-0.082
 lately-0.071
ening-0.070
 asleep-0.070
ishly-0.069
Token,
Token ID11
Feature activation+1.66e-02

Pos logit contributions
J+0.106
ves+0.099
Jen+0.097
ia+0.097
 Jen+0.096
Neg logit contributions
ivering-0.104
 lately-0.089
ishly-0.087
ening-0.087
 asleep-0.087
Token the
Token ID262
Feature activation+8.66e-03

Pos logit contributions
J+0.023
ves+0.022
ia+0.022
Jen+0.021
 Jen+0.021
Neg logit contributions
ivering-0.033
 lately-0.029
ishly-0.028
ening-0.028
 asleep-0.028
Token merry
Token ID44570
Feature activation+2.86e-02

Pos logit contributions
J+0.010
ves+0.009
ia+0.009
Jen+0.009
 Jen+0.009
Neg logit contributions
ivering-0.019
 lately-0.017
 asleep-0.017
ishly-0.017
ening-0.017
Token-
Token ID12
Feature activation+5.22e-02

Pos logit contributions
J+0.045
Jen+0.038
ves+0.038
 Lia+0.038
Jud+0.037
Neg logit contributions
ivering-0.053
ening-0.047
 anymore-0.045
 lately-0.044
 asleep-0.044
Tokengo
Token ID2188
Feature activation+8.87e-02

Pos logit contributions
J+0.100
Jud+0.094
 clues+0.093
 Lia+0.093
 third+0.092
Neg logit contributions
ivering-0.065
opl-0.054
he-0.052
 unatt-0.052
 around-0.052
Token-
Token ID12
Feature activation+5.51e-02

Pos logit contributions
J+0.176
Jud+0.155
Jen+0.148
Ah+0.145
Lisa+0.143
Neg logit contributions
ivering-0.117
ening-0.110
 anymore-0.109
 asleep-0.099
opl-0.096
Tokenround
Token ID744
Feature activation+4.13e-02

Pos logit contributions
J+0.127
 Lia+0.121
ia+0.121
Jud+0.120
 third+0.119
Neg logit contributions
ivering-0.040
opl-0.039
 anymore-0.033
 unatt-0.033
 around-0.032
Token.
Token ID13
Feature activation+1.10e-02

Pos logit contributions
J+0.060
ves+0.057
ia+0.056
Jen+0.055
 Jen+0.055
Neg logit contributions
ivering-0.079
 lately-0.069
ishly-0.068
ening-0.067
 asleep-0.067
Token They
Token ID1119
Feature activation+2.46e-02

Pos logit contributions
J+0.015
ves+0.014
ia+0.013
Jen+0.013
 Jen+0.012
Neg logit contributions
ivering-0.021
 lately-0.020
 asleep-0.020
ishly-0.019
 anymore-0.019
Token think
Token ID892
Feature activation+4.21e-02

Pos logit contributions
J+0.029
 Jen+0.029
 Lia+0.028
ia+0.027
ila+0.026
Neg logit contributions
ivering-0.056
 lately-0.050
ening-0.048
 unatt-0.047
ishly-0.046
Token mom
Token ID1995
Feature activation-2.95e-02

Pos logit contributions
J+0.008
ves+0.007
Jen+0.007
 Jen+0.006
 Lia+0.006
Neg logit contributions
ivering-0.022
 asleep-0.019
 lately-0.019
ishly-0.019
 unatt-0.019
Tokenmy
Token ID1820
Feature activation-1.86e-02

Pos logit contributions
ivering+0.042
 lately+0.035
ishly+0.034
ening+0.034
 asleep+0.034
Neg logit contributions
J-0.058
ves-0.055
ia-0.055
Jen-0.054
 Jen-0.054
Token surprised
Token ID6655
Feature activation-6.72e-03

Pos logit contributions
ivering+0.038
 lately+0.034
ening+0.033
ishly+0.033
 asleep+0.033
Neg logit contributions
J-0.025
ves-0.023
ia-0.023
 Jen-0.022
Jen-0.022
Token him
Token ID683
Feature activation-6.63e-03

Pos logit contributions
ivering+0.009
 lately+0.007
ishly+0.007
 asleep+0.007
ening+0.007
Neg logit contributions
J-0.014
ia-0.014
 Jen-0.014
ves-0.013
Jen-0.013
Token with
Token ID351
Feature activation-6.43e-03

Pos logit contributions
ivering+0.012
 lately+0.011
ening+0.011
ishly+0.010
 asleep+0.010
Neg logit contributions
J-0.009
ves-0.009
 Jen-0.009
ia-0.009
 Lia-0.008
Token freshly
Token ID29026
Feature activation-1.06e-01

Pos logit contributions
ivering+0.016
 lately+0.015
ening+0.014
ishly+0.014
pping+0.014
Neg logit contributions
J-0.006
 Jen-0.005
ves-0.005
Jen-0.005
ia-0.005
Token baked
Token ID22979
Feature activation-1.24e-02

Pos logit contributions
ivering+0.175
pping+0.153
 unatt+0.146
 asleep+0.144
 lately+0.143
Neg logit contributions
 Lia-0.166
ia-0.164
J-0.162
ves-0.159
 Jen-0.157
Token cookies
Token ID14746
Feature activation-2.80e-02

Pos logit contributions
ivering+0.026
 lately+0.023
ishly+0.023
 asleep+0.023
ening+0.022
Neg logit contributions
J-0.016
ves-0.015
ia-0.015
Jen-0.014
 Jen-0.014
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
ivering+0.061
ening+0.054
 lately+0.053
ishly+0.051
istent+0.051
Neg logit contributions
J-0.034
ves-0.033
ia-0.031
 Jen-0.031
 they-0.030
Token Tim
Token ID5045
Feature activation+2.48e-02

Pos logit contributions
ivering+0.022
ening+0.019
pping+0.019
 unatt+0.019
 lately+0.019
Neg logit contributions
 Jen-0.014
J-0.014
Jen-0.013
ia-0.013
 Lia-0.012
Tokenmy
Token ID1820
Feature activation-9.14e-03

Pos logit contributions
J+0.045
ia+0.044
 Jen+0.043
Jen+0.042
 two+0.040
Neg logit contributions
ivering-0.036
 lately-0.034
 unatt-0.031
ishly-0.031
ening-0.030
Token
Token ID198
Feature activation-2.63e-03

Pos logit contributions
ves+0.000
J+0.000
 Jen+0.000
ia+0.000
 Lia+0.000
Neg logit contributions
ivering-0.000
Charl-0.000
 lately-0.000
ishly-0.000
pping-0.000
Token"
Token ID1
Feature activation-2.17e-02

Pos logit contributions
ivering+0.005
Charl+0.005
 lately+0.005
ishly+0.005
pping+0.005
Neg logit contributions
 Jen-0.003
ves-0.003
ia-0.003
 Lia-0.003
J-0.003
TokenI
Token ID40
Feature activation-1.59e-02

Pos logit contributions
ivering+0.041
 lately+0.037
ishly+0.035
Charl+0.034
 asleep+0.034
Neg logit contributions
ves-0.031
ia-0.030
J-0.030
 Jen-0.029
 Lia-0.028
Token'm
Token ID1101
Feature activation-1.47e-02

Pos logit contributions
ivering+0.032
 lately+0.028
ishly+0.028
ening+0.028
 unatt+0.028
Neg logit contributions
J-0.022
ves-0.020
ia-0.020
 Jen-0.020
Jen-0.020
Token just
Token ID655
Feature activation-9.47e-03

Pos logit contributions
ivering+0.026
 lately+0.022
ening+0.022
 unatt+0.022
ishly+0.022
Neg logit contributions
 Jen-0.023
J-0.023
ia-0.022
 Lia-0.022
ves-0.022
Token washing
Token ID20518
Feature activation-1.03e-01

Pos logit contributions
ivering+0.015
ishly+0.013
 lately+0.013
 unatt+0.012
ening+0.012
Neg logit contributions
 Jen-0.016
J-0.016
ia-0.015
 Lia-0.015
Jen-0.015
Token,"
Token ID553
Feature activation+2.03e-02

Pos logit contributions
ivering+0.216
 unatt+0.181
ishly+0.180
istent+0.179
opl+0.179
Neg logit contributions
J-0.123
ves-0.122
 two-0.121
 Jen-0.114
ia-0.114
Token she
Token ID673
Feature activation-3.48e-02

Pos logit contributions
J+0.027
ves+0.026
ia+0.025
Jen+0.025
 Jen+0.024
Neg logit contributions
ivering-0.040
 lately-0.036
ishly-0.036
 asleep-0.035
ening-0.035
Token said
Token ID531
Feature activation+8.04e-03

Pos logit contributions
ivering+0.064
ishly+0.057
 lately+0.057
 asleep+0.054
ening+0.053
Neg logit contributions
J-0.050
Jen-0.048
ves-0.048
ia-0.046
 Jen-0.046
Token.
Token ID13
Feature activation-7.85e-03

Pos logit contributions
J+0.012
ves+0.011
ia+0.011
Jen+0.011
 Jen+0.010
Neg logit contributions
ivering-0.016
 lately-0.014
ishly-0.013
ening-0.013
 asleep-0.013
Token "
Token ID366
Feature activation-7.96e-03

Pos logit contributions
ivering+0.015
 lately+0.013
ishly+0.013
 asleep+0.013
ening+0.013
Neg logit contributions
J-0.011
ves-0.011
ia-0.011
Jen-0.010
 Jen-0.010
Token went
Token ID1816
Feature activation-1.04e-02

Pos logit contributions
ivering+0.002
ishly+0.002
 asleep+0.002
ening+0.002
 lately+0.002
Neg logit contributions
J-0.002
Jen-0.002
ves-0.002
ia-0.002
 Lia-0.002
Token home
Token ID1363
Feature activation-1.05e-02

Pos logit contributions
ivering+0.017
 lately+0.014
ishly+0.014
 asleep+0.014
ening+0.014
Neg logit contributions
J-0.018
ves-0.018
ia-0.017
Jen-0.017
 Jen-0.017
Token and
Token ID290
Feature activation-8.93e-03

Pos logit contributions
ivering+0.021
ening+0.019
 lately+0.019
opl+0.019
ishly+0.019
Neg logit contributions
J-0.014
 Jen-0.013
ves-0.012
ia-0.012
 they-0.012
Token enjoyed
Token ID8359
Feature activation-8.09e-03

Pos logit contributions
ivering+0.018
 lately+0.016
ishly+0.015
ening+0.015
 asleep+0.015
Neg logit contributions
J-0.012
ves-0.012
ia-0.011
Jen-0.011
 Jen-0.011
Token his
Token ID465
Feature activation-1.45e-02

Pos logit contributions
ivering+0.016
 lately+0.014
ishly+0.013
ening+0.013
 asleep+0.013
Neg logit contributions
J-0.012
ves-0.011
ia-0.011
Jen-0.011
 Jen-0.011
Token freshly
Token ID29026
Feature activation-1.01e-01

Pos logit contributions
ivering+0.025
 asleep+0.023
 unatt+0.023
ening+0.022
 lately+0.022
Neg logit contributions
J-0.023
 Lia-0.021
Jen-0.021
ves-0.020
 Jen-0.020
Token caught
Token ID4978
Feature activation-2.53e-03

Pos logit contributions
ivering+0.172
pping+0.146
ening+0.143
 unatt+0.141
opl+0.141
Neg logit contributions
 Lia-0.161
J-0.156
 Jen-0.148
ia-0.147
Jen-0.142
Token fish
Token ID5916
Feature activation-1.04e-02

Pos logit contributions
ivering+0.005
 lately+0.004
ishly+0.004
ening+0.004
 asleep+0.004
Neg logit contributions
J-0.003
ves-0.003
ia-0.003
 Jen-0.003
Jen-0.003
Token.
Token ID13
Feature activation-1.67e-03

Pos logit contributions
ivering+0.020
 lately+0.018
ening+0.017
ishly+0.017
 asleep+0.017
Neg logit contributions
J-0.015
ves-0.014
ia-0.014
 Jen-0.013
Jen-0.013
Token<|endoftext|>
Token ID50256
Feature activation-3.95e-02

Pos logit contributions
ivering+0.003
 lately+0.003
ening+0.003
ishly+0.003
 unatt+0.003
Neg logit contributions
J-0.002
ia-0.002
 Jen-0.002
ves-0.002
Jen-0.002
TokenOnce
Token ID7454
Feature activation-9.31e-03

Pos logit contributions
ivering+0.072
 lately+0.063
 asleep+0.062
ening+0.061
ishly+0.061
Neg logit contributions
J-0.060
ves-0.057
ia-0.056
Jen-0.055
 Jen-0.054
Token
Token ID198
Feature activation+2.15e-03

Pos logit contributions
ivering+0.005
 lately+0.005
ishly+0.005
 asleep+0.005
ening+0.005
Neg logit contributions
J-0.004
ves-0.004
ia-0.004
Jen-0.004
 Jen-0.004
Token
Token ID198
Feature activation-1.13e-03

Pos logit contributions
J+0.003
ves+0.003
ia+0.003
 Jen+0.003
Jen+0.003
Neg logit contributions
ivering-0.004
 lately-0.004
 asleep-0.003
ening-0.003
ishly-0.003
TokenWhile
Token ID3633
Feature activation+2.35e-02

Pos logit contributions
ivering+0.003
 lately+0.002
Charl+0.002
pping+0.002
ishly+0.002
Neg logit contributions
 Jen-0.001
ia-0.001
ves-0.001
J-0.001
 Lia-0.001
Token Lily
Token ID20037
Feature activation+5.23e-03

Pos logit contributions
J+0.030
ves+0.030
ia+0.029
Jen+0.028
 Lia+0.027
Neg logit contributions
ivering-0.047
 lately-0.044
 asleep-0.043
ening-0.041
ishly-0.041
Token was
Token ID373
Feature activation-2.25e-02

Pos logit contributions
J+0.006
ia+0.005
ves+0.005
Jen+0.005
 Jen+0.005
Neg logit contributions
ivering-0.012
 lately-0.011
 asleep-0.011
ishly-0.011
 unatt-0.011
Token washing
Token ID20518
Feature activation-9.83e-02

Pos logit contributions
opl+0.040
ivering+0.039
ishly+0.039
ening+0.037
 impact+0.035
Neg logit contributions
J-0.032
 two-0.032
 they-0.032
ves-0.030
 Jen-0.030
Token her
Token ID607
Feature activation-1.16e-02

Pos logit contributions
ivering+0.235
opl+0.204
istent+0.202
 lately+0.197
 unatt+0.197
Neg logit contributions
J-0.100
ves-0.098
 other-0.094
 two-0.093
 they-0.091
Token hair
Token ID4190
Feature activation-2.83e-02

Pos logit contributions
ivering+0.024
 lately+0.021
ishly+0.021
ening+0.021
pping+0.020
Neg logit contributions
J-0.015
ia-0.015
ves-0.015
 Jen-0.014
 Lia-0.014
Token,
Token ID11
Feature activation-1.49e-02

Pos logit contributions
ivering+0.057
opl+0.049
ening+0.049
 lately+0.049
ishly+0.049
Neg logit contributions
ves-0.038
J-0.037
 Jen-0.034
 they-0.034
ia-0.034
Token she
Token ID673
Feature activation-1.92e-02

Pos logit contributions
ivering+0.026
 lately+0.025
 asleep+0.024
ishly+0.023
 unatt+0.023
Neg logit contributions
ia-0.021
J-0.021
ves-0.021
Jen-0.020
Dan-0.019
Token felt
Token ID2936
Feature activation-2.63e-02

Pos logit contributions
ivering+0.036
 lately+0.031
 asleep+0.030
ening+0.030
ishly+0.030
Neg logit contributions
J-0.029
ves-0.028
ia-0.027
Jen-0.027
 Jen-0.027
Token
Token ID198
Feature activation-6.49e-03

Pos logit contributions
ivering+0.004
 lately+0.003
Charl+0.003
 asleep+0.003
 Playing+0.003
Neg logit contributions
ves-0.003
 flag-0.003
ia-0.003
J-0.003
 Lia-0.003
TokenThe
Token ID464
Feature activation-2.75e-03

Pos logit contributions
ivering+0.013
 lately+0.011
Charl+0.011
ishly+0.011
pping+0.010
Neg logit contributions
ves-0.008
ia-0.008
 Jen-0.008
 Lia-0.008
J-0.007
Token young
Token ID1862
Feature activation+4.10e-02

Pos logit contributions
ivering+0.006
ishly+0.005
 lately+0.005
 asleep+0.005
 unatt+0.005
Neg logit contributions
J-0.003
ves-0.003
Jen-0.003
 Jen-0.003
ia-0.003
Token woman
Token ID2415
Feature activation-1.78e-02

Pos logit contributions
J+0.044
ves+0.042
Jen+0.039
ia+0.039
 Jen+0.038
Neg logit contributions
ivering-0.092
 lately-0.085
ishly-0.084
ening-0.084
 asleep-0.083
Token stopped
Token ID5025
Feature activation-1.50e-02

Pos logit contributions
ivering+0.037
 lately+0.033
 unatt+0.032
 asleep+0.032
ening+0.031
Neg logit contributions
J-0.023
ves-0.022
ia-0.022
 Jen-0.021
Jen-0.020
Token washing
Token ID20518
Feature activation-9.64e-02

Pos logit contributions
ivering+0.029
 lately+0.026
 unatt+0.025
ishly+0.024
pping+0.024
Neg logit contributions
J-0.021
 Jen-0.021
ia-0.019
 Lia-0.019
 two-0.019
Token her
Token ID607
Feature activation-2.31e-02

Pos logit contributions
ivering+0.209
 lately+0.177
 unatt+0.173
pping+0.171
ishly+0.170
Neg logit contributions
J-0.120
ves-0.115
 Jen-0.110
ia-0.108
 Lia-0.105
Token clothes
Token ID8242
Feature activation-3.94e-02

Pos logit contributions
ivering+0.047
 lately+0.042
pping+0.040
ening+0.040
ishly+0.039
Neg logit contributions
J-0.029
ves-0.029
ia-0.029
 Jen-0.027
 Lia-0.026
Token and
Token ID290
Feature activation-1.94e-03

Pos logit contributions
ivering+0.081
ening+0.071
 lately+0.070
opl+0.070
Charl+0.070
Neg logit contributions
J-0.046
ves-0.044
 they-0.042
 two-0.042
ia-0.040
Token smiled
Token ID13541
Feature activation-7.58e-03

Pos logit contributions
ivering+0.004
 lately+0.004
ening+0.004
ishly+0.004
 unatt+0.003
Neg logit contributions
J-0.002
ves-0.002
 Jen-0.002
ia-0.002
Jen-0.002
Token at
Token ID379
Feature activation-6.17e-04

Pos logit contributions
ivering+0.017
pping+0.015
opl+0.015
 unatt+0.015
 lately+0.015
Neg logit contributions
J-0.008
ia-0.007
 Jen-0.007
 two-0.007
 second-0.007
Token there
Token ID612
Feature activation-1.75e-04

Pos logit contributions
ivering+0.011
 lately+0.009
ishly+0.009
ening+0.009
 asleep+0.009
Neg logit contributions
J-0.010
 Jen-0.009
ia-0.009
ves-0.009
Jen-0.009
Token,
Token ID11
Feature activation-2.02e-02

Pos logit contributions
ivering+0.000
ishly+0.000
ening+0.000
opl+0.000
 lately+0.000
Neg logit contributions
J-0.000
 Jen-0.000
ia-0.000
ves-0.000
Jen-0.000
Token her
Token ID607
Feature activation+5.00e-03

Pos logit contributions
 lately+0.034
ivering+0.033
 asleep+0.032
 unatt+0.031
ening+0.029
Neg logit contributions
ves-0.031
ia-0.030
Jen-0.030
J-0.028
 Lia-0.028
Token mom
Token ID1995
Feature activation-3.02e-02

Pos logit contributions
J+0.004
ves+0.004
Jen+0.004
 Lia+0.003
 Jen+0.003
Neg logit contributions
ivering-0.013
 asleep-0.012
 lately-0.012
ishly-0.011
 unatt-0.011
Token was
Token ID373
Feature activation-2.18e-02

Pos logit contributions
ivering+0.061
 lately+0.054
ishly+0.053
ening+0.052
 asleep+0.052
Neg logit contributions
J-0.042
ves-0.039
ia-0.038
Jen-0.038
 Jen-0.038
Token frying
Token ID45366
Feature activation-9.50e-02

Pos logit contributions
ivering+0.039
ishly+0.038
ening+0.038
opl+0.036
istent+0.036
Neg logit contributions
J-0.036
 two-0.030
 Jen-0.030
Jen-0.029
 second-0.029
Token a
Token ID257
Feature activation+4.02e-03

Pos logit contributions
ivering+0.211
ishly+0.189
istent+0.187
ening+0.185
opl+0.182
Neg logit contributions
J-0.116
 Jen-0.103
ves-0.103
ia-0.102
Jen-0.098
Token tuna
Token ID38883
Feature activation-2.98e-02

Pos logit contributions
J+0.004
ves+0.004
ia+0.004
Jen+0.004
 Jen+0.003
Neg logit contributions
ivering-0.009
 lately-0.009
ishly-0.009
ening-0.008
pping-0.008
Token steak
Token ID26320
Feature activation-3.20e-02

Pos logit contributions
ivering+0.060
ening+0.052
 lately+0.052
ishly+0.052
 unatt+0.051
Neg logit contributions
J-0.039
ves-0.038
ia-0.038
 Jen-0.035
Jen-0.035
Token.
Token ID13
Feature activation-5.24e-03

Pos logit contributions
ivering+0.067
ishly+0.058
ening+0.057
 lately+0.056
opl+0.055
Neg logit contributions
ves-0.040
J-0.040
ia-0.039
 Jen-0.037
 they-0.036
Token It
Token ID632
Feature activation+1.41e-02

Pos logit contributions
ivering+0.009
 lately+0.008
ishly+0.008
ening+0.008
 unatt+0.008
Neg logit contributions
J-0.009
ves-0.008
ia-0.008
 Jen-0.008
Jen-0.008
Token.
Token ID13
Feature activation-1.98e-02

Pos logit contributions
ivering+0.035
opl+0.030
 lately+0.030
 unatt+0.030
ishly+0.029
Neg logit contributions
J-0.016
ves-0.014
ia-0.014
 Jen-0.013
 they-0.013
Token<|endoftext|>
Token ID50256
Feature activation-4.27e-02

Pos logit contributions
ivering+0.033
 lately+0.028
ishly+0.027
ening+0.027
 unatt+0.027
Neg logit contributions
J-0.034
ves-0.032
ia-0.032
 Jen-0.031
Jen-0.031
TokenBob
Token ID18861
Feature activation+4.18e-03

Pos logit contributions
ivering+0.074
 lately+0.064
ishly+0.062
 asleep+0.062
ening+0.062
Neg logit contributions
J-0.070
ves-0.066
ia-0.065
Jen-0.064
 Jen-0.064
Tokenbie
Token ID12590
Feature activation-3.54e-02

Pos logit contributions
J+0.005
 Jen+0.004
ia+0.004
Jen+0.004
ila+0.004
Neg logit contributions
ivering-0.010
 unatt-0.008
 lately-0.008
ishly-0.008
 asleep-0.008
Token was
Token ID373
Feature activation-2.59e-02

Pos logit contributions
ivering+0.080
 lately+0.071
 unatt+0.070
ishly+0.069
ening+0.068
Neg logit contributions
J-0.039
ia-0.038
ves-0.037
 Jen-0.036
Jen-0.034
Token washing
Token ID20518
Feature activation-9.50e-02

Pos logit contributions
ivering+0.048
ishly+0.044
ening+0.042
 lately+0.041
istent+0.041
Neg logit contributions
J-0.037
 two-0.037
 Jen-0.036
ia-0.033
 second-0.032
Token the
Token ID262
Feature activation-1.27e-02

Pos logit contributions
ivering+0.224
istent+0.196
opl+0.191
ishly+0.191
Charl+0.190
Neg logit contributions
J-0.095
 other-0.094
 two-0.090
 they-0.088
ves-0.086
Token dishes
Token ID16759
Feature activation-2.15e-02

Pos logit contributions
ivering+0.026
 lately+0.023
ishly+0.023
ening+0.022
 asleep+0.022
Neg logit contributions
J-0.016
ves-0.015
ia-0.015
Jen-0.015
 Jen-0.015
Token in
Token ID287
Feature activation-9.13e-03

Pos logit contributions
ivering+0.046
ishly+0.039
Charl+0.039
opl+0.038
ening+0.038
Neg logit contributions
J-0.027
 they-0.024
ves-0.024
 two-0.024
 Jen-0.024
Token the
Token ID262
Feature activation-1.28e-02

Pos logit contributions
ivering+0.019
ishly+0.017
 lately+0.017
ening+0.016
 asleep+0.016
Neg logit contributions
J-0.012
 Jen-0.011
Jen-0.011
ia-0.011
ves-0.011
Token kitchen
Token ID9592
Feature activation+9.64e-03

Pos logit contributions
ivering+0.024
 lately+0.021
ishly+0.020
ening+0.020
pping+0.020
Neg logit contributions
J-0.019
 Jen-0.017
ia-0.017
Jen-0.017
ves-0.017
Token The
Token ID383
Feature activation+1.21e-02

Pos logit contributions
ivering+0.008
 lately+0.007
ishly+0.007
ening+0.007
 asleep+0.007
Neg logit contributions
J-0.005
ves-0.005
ia-0.005
Jen-0.005
 Jen-0.005
Token polar
Token ID13559
Feature activation+3.56e-02

Pos logit contributions
J+0.024
ves+0.024
ia+0.023
 Lia+0.022
 Jen+0.022
Neg logit contributions
ivering-0.018
 asleep-0.015
 lately-0.014
 unatt-0.014
ishly-0.014
Token bear
Token ID6842
Feature activation-1.92e-03

Pos logit contributions
J+0.057
ves+0.054
ia+0.054
Jen+0.053
 Jen+0.053
Neg logit contributions
ivering-0.061
 lately-0.056
ishly-0.052
ening-0.052
 asleep-0.052
Token had
Token ID550
Feature activation-3.41e-03

Pos logit contributions
ivering+0.004
 lately+0.004
ening+0.004
 unatt+0.004
 asleep+0.004
Neg logit contributions
ves-0.002
J-0.002
ia-0.002
 Jen-0.002
Jen-0.002
Token been
Token ID587
Feature activation-2.29e-02

Pos logit contributions
ivering+0.007
 asleep+0.007
 lately+0.007
 unatt+0.006
 streaming+0.006
Neg logit contributions
J-0.004
ia-0.004
ves-0.004
Jen-0.004
 Lia-0.004
Token living
Token ID2877
Feature activation-9.49e-02

Pos logit contributions
ivering+0.039
ishly+0.034
 lately+0.034
ening+0.033
 unatt+0.032
Neg logit contributions
J-0.038
ves-0.036
 Jen-0.035
ia-0.035
Jen-0.034
Token in
Token ID287
Feature activation-3.24e-02

Pos logit contributions
ivering+0.197
ishly+0.187
istent+0.178
opl+0.173
ening+0.162
Neg logit contributions
J-0.134
 Jen-0.123
 other-0.121
 two-0.120
ia-0.114
Token the
Token ID262
Feature activation-2.89e-02

Pos logit contributions
ivering+0.082
ishly+0.073
 lately+0.071
ening+0.071
 unatt+0.070
Neg logit contributions
J-0.029
 Jen-0.027
ves-0.026
ia-0.026
Jen-0.025
Token ig
Token ID45329
Feature activation-5.35e-03

Pos logit contributions
ivering+0.049
 lately+0.042
ishly+0.042
ening+0.042
 asleep+0.040
Neg logit contributions
J-0.048
Jen-0.046
ia-0.045
 Jen-0.045
ves-0.045
Tokenloo
Token ID29680
Feature activation-7.41e-03

Pos logit contributions
ivering+0.011
ishly+0.010
 lately+0.010
ening+0.010
 asleep+0.010
Neg logit contributions
J-0.007
ia-0.007
Jen-0.007
ves-0.007
 Jen-0.006
Token for
Token ID329
Feature activation-2.95e-02

Pos logit contributions
ivering+0.014
ishly+0.012
Charl+0.012
 streaming+0.012
ening+0.012
Neg logit contributions
J-0.010
ia-0.010
ves-0.010
 Jen-0.010
 two-0.010
Token happened
Token ID3022
Feature activation-4.20e-03

Pos logit contributions
ves+0.002
J+0.002
ia+0.001
 Jen+0.001
Jen+0.001
Neg logit contributions
ivering-0.003
ishly-0.003
 lately-0.003
 unatt-0.003
 asleep-0.003
Token.
Token ID13
Feature activation-5.26e-03

Pos logit contributions
ivering+0.009
ishly+0.008
 lately+0.008
ening+0.008
 asleep+0.008
Neg logit contributions
J-0.005
ves-0.005
ia-0.005
 Jen-0.004
Jen-0.004
Token As
Token ID1081
Feature activation+4.03e-02

Pos logit contributions
ivering+0.011
 unatt+0.010
pping+0.010
opl+0.009
ening+0.009
Neg logit contributions
 Jen-0.007
ves-0.006
 two-0.006
 third-0.006
ia-0.006
Token George
Token ID4502
Feature activation+2.69e-03

Pos logit contributions
J+0.037
ves+0.033
ia+0.033
Jen+0.032
 Jen+0.031
Neg logit contributions
ivering-0.098
 lately-0.091
 asleep-0.089
ening-0.088
ishly-0.087
Token was
Token ID373
Feature activation-1.71e-02

Pos logit contributions
J+0.004
ves+0.004
ia+0.004
Jen+0.004
 Jen+0.003
Neg logit contributions
ivering-0.005
 lately-0.005
 asleep-0.004
ening-0.004
ishly-0.004
Token washing
Token ID20518
Feature activation-9.46e-02

Pos logit contributions
ivering+0.028
 lately+0.024
ening+0.024
ishly+0.023
istent+0.023
Neg logit contributions
ves-0.029
J-0.029
ia-0.028
 Jen-0.028
 Lia-0.027
Token his
Token ID465
Feature activation-4.78e-03

Pos logit contributions
ivering+0.215
 lately+0.178
 unatt+0.177
istent+0.177
ishly+0.177
Neg logit contributions
ves-0.110
J-0.102
 Jen-0.101
 two-0.099
ia-0.098
Token hands
Token ID2832
Feature activation-5.45e-02

Pos logit contributions
ivering+0.010
 lately+0.009
ishly+0.008
ening+0.008
 asleep+0.008
Neg logit contributions
J-0.007
ves-0.006
ia-0.006
Jen-0.006
 Jen-0.006
Token outside
Token ID2354
Feature activation-7.44e-03

Pos logit contributions
ivering+0.109
 lately+0.091
Charl+0.091
opl+0.090
ening+0.090
Neg logit contributions
 Jen-0.069
J-0.069
ves-0.069
 they-0.068
 two-0.065
Token,
Token ID11
Feature activation-1.45e-02

Pos logit contributions
ivering+0.016
Charl+0.014
ishly+0.013
pping+0.013
 lately+0.013
Neg logit contributions
 Jen-0.010
J-0.009
ia-0.009
 they-0.009
ves-0.008
Token he
Token ID339
Feature activation-1.74e-03

Pos logit contributions
ivering+0.035
pping+0.030
opl+0.030
ening+0.030
 unatt+0.030
Neg logit contributions
ves-0.015
J-0.014
 Jen-0.014
 they-0.014
 two-0.013
Token named
Token ID3706
Feature activation+1.63e-02

Pos logit contributions
ivering+0.017
 lately+0.015
ishly+0.015
ening+0.015
 asleep+0.015
Neg logit contributions
J-0.016
ves-0.015
ia-0.015
Jen-0.014
 Jen-0.014
Token Lucy
Token ID22162
Feature activation-1.45e-04

Pos logit contributions
ves+0.024
J+0.022
ia+0.020
Jen+0.020
Ar+0.020
Neg logit contributions
ivering-0.030
ishly-0.029
 lately-0.028
 asleep-0.027
 weeping-0.027
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
ivering+0.000
 lately+0.000
 unatt+0.000
ening+0.000
ishly+0.000
Neg logit contributions
J-0.000
 Jen-0.000
ia-0.000
ves-0.000
 Lia-0.000
Token Lucy
Token ID22162
Feature activation-4.52e-03

Pos logit contributions
ivering+0.033
pping+0.030
 unatt+0.029
ening+0.027
opl+0.027
Neg logit contributions
 Jen-0.019
 Lia-0.018
 Mia-0.017
ia-0.017
Jen-0.017
Token was
Token ID373
Feature activation-1.14e-02

Pos logit contributions
ivering+0.010
 lately+0.009
 unatt+0.009
 asleep+0.009
ening+0.009
Neg logit contributions
J-0.005
ia-0.005
ves-0.005
 Jen-0.005
Jen-0.004
Token washing
Token ID20518
Feature activation-9.45e-02

Pos logit contributions
ivering+0.019
 lately+0.017
ening+0.017
ishly+0.016
 unatt+0.016
Neg logit contributions
J-0.019
 Jen-0.018
ia-0.018
 Lia-0.018
Jen-0.018
Token her
Token ID607
Feature activation-5.69e-03

Pos logit contributions
ivering+0.202
 unatt+0.175
 lately+0.173
 asleep+0.170
istent+0.170
Neg logit contributions
J-0.117
ves-0.112
 Jen-0.112
 Lia-0.110
ia-0.109
Token hands
Token ID2832
Feature activation-5.28e-02

Pos logit contributions
ivering+0.013
 lately+0.012
pping+0.011
ening+0.011
istent+0.011
Neg logit contributions
ia-0.006
ves-0.006
 Jen-0.006
J-0.006
 Lia-0.005
Token.
Token ID13
Feature activation-8.07e-03

Pos logit contributions
ivering+0.107
opl+0.091
 unatt+0.090
ening+0.089
ishly+0.089
Neg logit contributions
J-0.066
ves-0.064
 two-0.063
 Jen-0.062
ia-0.062
Token Spot
Token ID15899
Feature activation-4.13e-03

Pos logit contributions
ivering+0.018
 unatt+0.016
pping+0.015
ening+0.015
 impact+0.014
Neg logit contributions
 Jen-0.011
 Lia-0.011
 Mia-0.010
ia-0.010
 they-0.010
Token wanted
Token ID2227
Feature activation+2.89e-02

Pos logit contributions
ivering+0.009
 lately+0.009
 unatt+0.008
ening+0.008
 asleep+0.008
Neg logit contributions
J-0.005
ia-0.004
ves-0.004
 Jen-0.004
 Lia-0.004
Token
Token ID198
Feature activation+9.04e-04

Pos logit contributions
ivering+0.009
 lately+0.008
ishly+0.008
 asleep+0.008
ening+0.008
Neg logit contributions
J-0.007
ves-0.007
ia-0.007
Jen-0.006
 Jen-0.006
Token
Token ID198
Feature activation-1.51e-03

Pos logit contributions
J+0.001
ves+0.001
ia+0.001
 Jen+0.001
Jen+0.001
Neg logit contributions
ivering-0.002
 lately-0.002
 asleep-0.001
ening-0.001
ishly-0.001
TokenAs
Token ID1722
Feature activation+3.28e-02

Pos logit contributions
ivering+0.003
 lately+0.003
pping+0.003
Charl+0.003
ening+0.003
Neg logit contributions
 Jen-0.002
ia-0.001
ves-0.001
J-0.001
 Lia-0.001
Token Lily
Token ID20037
Feature activation+1.23e-03

Pos logit contributions
ves+0.030
J+0.029
ia+0.029
Land+0.027
Jen+0.027
Neg logit contributions
ivering-0.072
 lately-0.072
 asleep-0.072
 anymore-0.066
 about-0.066
Token was
Token ID373
Feature activation-1.93e-02

Pos logit contributions
J+0.001
ves+0.001
ia+0.001
Jen+0.001
 Jen+0.001
Neg logit contributions
ivering-0.003
 lately-0.003
 unatt-0.003
 asleep-0.002
ening-0.002
Token washing
Token ID20518
Feature activation-9.32e-02

Pos logit contributions
ivering+0.034
ening+0.031
opl+0.031
 lately+0.030
 unatt+0.030
Neg logit contributions
ves-0.028
 two-0.027
 they-0.027
J-0.027
 second-0.025
Token the
Token ID262
Feature activation-9.14e-03

Pos logit contributions
ivering+0.207
 lately+0.177
opl+0.175
 unatt+0.174
ening+0.172
Neg logit contributions
J-0.111
ves-0.107
 Jen-0.098
ia-0.096
 Lia-0.095
Token dishes
Token ID16759
Feature activation-2.09e-02

Pos logit contributions
ivering+0.020
ishly+0.019
 lately+0.018
 streaming+0.017
opl+0.017
Neg logit contributions
J-0.010
 other-0.010
 two-0.009
 third-0.009
ves-0.009
Token,
Token ID11
Feature activation-8.01e-03

Pos logit contributions
ivering+0.042
opl+0.036
ening+0.036
Charl+0.035
ishly+0.035
Neg logit contributions
J-0.028
 they-0.028
ves-0.026
 Jen-0.026
 two-0.025
Token she
Token ID673
Feature activation-1.15e-02

Pos logit contributions
ivering+0.013
 lately+0.013
 asleep+0.013
ishly+0.012
 unatt+0.012
Neg logit contributions
ia-0.012
ves-0.012
J-0.012
Jen-0.012
Dan-0.011
Token saw
Token ID2497
Feature activation+1.98e-02

Pos logit contributions
ivering+0.022
 lately+0.019
ishly+0.019
 asleep+0.019
ening+0.019
Neg logit contributions
J-0.017
ves-0.016
ia-0.016
Jen-0.016
 Jen-0.015
Token saw
Token ID2497
Feature activation+1.92e-02

Pos logit contributions
ivering+0.021
 lately+0.018
ishly+0.018
 asleep+0.018
ening+0.018
Neg logit contributions
J-0.015
ves-0.014
ia-0.014
Jen-0.014
 Jen-0.014
Token her
Token ID607
Feature activation-1.40e-02

Pos logit contributions
J+0.024
ves+0.023
ia+0.023
Jen+0.022
 Lia+0.020
Neg logit contributions
ivering-0.038
 lately-0.036
ishly-0.035
 asleep-0.035
ening-0.034
Token mother
Token ID2802
Feature activation-3.98e-02

Pos logit contributions
ivering+0.035
 lately+0.032
ishly+0.031
ening+0.031
 asleep+0.031
Neg logit contributions
J-0.012
ves-0.011
ia-0.011
Jen-0.010
 Jen-0.010
Token holding
Token ID4769
Feature activation-5.95e-02

Pos logit contributions
ivering+0.064
 lately+0.059
 unatt+0.055
ening+0.054
ishly+0.054
Neg logit contributions
J-0.065
 Jen-0.063
ia-0.061
ves-0.061
Jen-0.060
Token a
Token ID257
Feature activation-4.50e-03

Pos logit contributions
ivering+0.134
 lately+0.121
ishly+0.118
ening+0.118
 asleep+0.118
Neg logit contributions
J-0.066
ves-0.062
ia-0.060
Jen-0.059
 Jen-0.058
Token freshly
Token ID29026
Feature activation-9.30e-02

Pos logit contributions
ivering+0.011
 lately+0.010
ishly+0.009
pping+0.009
ening+0.009
Neg logit contributions
J-0.005
ves-0.004
ia-0.004
Jen-0.004
 Jen-0.004
Token-
Token ID12
Feature activation-6.07e-03

Pos logit contributions
ivering+0.166
 lately+0.142
ening+0.140
 asleep+0.138
 unatt+0.137
Neg logit contributions
J-0.144
ves-0.136
ia-0.136
 Lia-0.135
 Jen-0.133
Tokenb
Token ID65
Feature activation+8.79e-03

Pos logit contributions
ivering+0.009
 lately+0.009
ening+0.008
Charl+0.008
 unatt+0.008
Neg logit contributions
ves-0.010
ia-0.010
 Lia-0.010
kins-0.009
 Jen-0.009
Tokenaked
Token ID4335
Feature activation+2.63e-02

Pos logit contributions
J+0.012
ves+0.011
ia+0.010
Jen+0.010
 Jen+0.010
Neg logit contributions
ivering-0.018
 lately-0.016
ishly-0.016
 asleep-0.016
ening-0.016
Token muff
Token ID27563
Feature activation-6.10e-02

Pos logit contributions
J+0.045
ves+0.043
ia+0.042
 Jen+0.042
Jen+0.041
Neg logit contributions
ivering-0.044
 lately-0.037
ishly-0.036
 asleep-0.035
 unatt-0.035
Tokenin
Token ID259
Feature activation+3.32e-03

Pos logit contributions
ivering+0.109
 lately+0.097
ishly+0.096
 asleep+0.095
ening+0.094
Neg logit contributions
J-0.098
ves-0.092
ia-0.091
Jen-0.088
 Jen-0.087
Token€
Token ID26391
Feature activation+9.36e-03

Pos logit contributions
ivering+0.039
 asleep+0.037
 lately+0.035
 unatt+0.033
ening+0.032
Neg logit contributions
J-0.041
Jen-0.040
ia-0.040
ves-0.038
 Jen-0.038
Token�
Token ID129
Feature activation-1.26e-02

Pos logit contributions
J+0.013
ves+0.012
ia+0.012
Jen+0.012
 Jen+0.012
Neg logit contributions
ivering-0.018
 lately-0.016
ishly-0.016
ening-0.016
 asleep-0.016
Token�
Token ID241
Feature activation-1.84e-02

Pos logit contributions
ivering+0.019
 asleep+0.018
 lately+0.017
 unatt+0.017
 streaming+0.016
Neg logit contributions
ia-0.022
J-0.022
ves-0.022
Jen-0.022
 Jen-0.022
TokenI
Token ID40
Feature activation-2.48e-02

Pos logit contributions
ivering+0.035
 lately+0.032
ening+0.030
 asleep+0.030
pping+0.029
Neg logit contributions
ves-0.025
ia-0.025
J-0.024
 Lia-0.023
 Jen-0.022
Token am
Token ID716
Feature activation-2.99e-02

Pos logit contributions
ivering+0.051
ishly+0.046
ening+0.045
 lately+0.045
 asleep+0.045
Neg logit contributions
J-0.033
ia-0.030
ves-0.030
Jen-0.030
 Jen-0.030
Token blo
Token ID24924
Feature activation-9.28e-02

Pos logit contributions
ivering+0.061
ening+0.053
ishly+0.052
 unatt+0.050
 lately+0.050
Neg logit contributions
 Jen-0.042
J-0.040
ia-0.039
 two-0.038
 Lia-0.038
Tokenoming
Token ID3383
Feature activation-2.76e-02

Pos logit contributions
ivering+0.146
 lately+0.139
ishly+0.134
ening+0.131
 unatt+0.130
Neg logit contributions
J-0.141
ila-0.134
ia-0.128
 Lia-0.125
 two-0.125
Token!
Token ID0
Feature activation-1.49e-02

Pos logit contributions
ivering+0.053
ening+0.044
pping+0.044
istent+0.044
 lately+0.044
Neg logit contributions
J-0.039
ia-0.038
ves-0.037
 Jen-0.037
 Lia-0.037
Tokenâ
Token ID22940
Feature activation-1.50e-02

Pos logit contributions
ivering+0.022
 lately+0.019
ishly+0.018
 asleep+0.018
ening+0.017
Neg logit contributions
J-0.028
ves-0.027
ia-0.027
Jen-0.026
 Lia-0.025
Token€
Token ID26391
Feature activation+1.34e-02

Pos logit contributions
ivering+0.026
 asleep+0.025
 lately+0.023
 unatt+0.023
 streaming+0.022
Neg logit contributions
J-0.024
Jen-0.023
ia-0.022
 Jen-0.022
ves-0.021
Token said
Token ID531
Feature activation+1.43e-02

Pos logit contributions
J+0.021
ves+0.020
ia+0.019
Jen+0.019
 Jen+0.019
Neg logit contributions
ivering-0.024
 lately-0.021
ishly-0.021
ening-0.021
 asleep-0.020
Token,
Token ID11
Feature activation-6.26e-03

Pos logit contributions
J+0.007
ves+0.007
ia+0.007
 Jen+0.007
Jen+0.007
Neg logit contributions
ivering-0.008
 lately-0.007
ening-0.007
ishly-0.007
 unatt-0.007
Token Lily
Token ID20037
Feature activation+1.98e-02

Pos logit contributions
ivering+0.012
 lately+0.011
 asleep+0.011
ishly+0.011
 unatt+0.010
Neg logit contributions
J-0.009
ves-0.008
ia-0.008
Jen-0.008
 Lia-0.008
Token noticed
Token ID6810
Feature activation-9.94e-03

Pos logit contributions
J+0.027
ia+0.025
ves+0.025
 Jen+0.024
Jen+0.024
Neg logit contributions
ivering-0.040
ishly-0.035
 lately-0.035
ening-0.035
 unatt-0.034
Token that
Token ID326
Feature activation-2.11e-02

Pos logit contributions
ivering+0.020
ishly+0.017
 lately+0.017
ening+0.017
istent+0.017
Neg logit contributions
J-0.014
 Jen-0.013
ves-0.013
ia-0.013
 Lia-0.012
Token her
Token ID607
Feature activation-2.26e-03

Pos logit contributions
ivering+0.051
ishly+0.045
istent+0.044
pping+0.044
ening+0.043
Neg logit contributions
J-0.023
 Jen-0.022
ves-0.021
 Lia-0.020
 they-0.020
Token herbs
Token ID25411
Feature activation-9.25e-02

Pos logit contributions
ivering+0.005
 lately+0.005
ishly+0.005
ening+0.005
pping+0.005
Neg logit contributions
J-0.002
ia-0.002
ves-0.002
 Jen-0.002
Jen-0.002
Token were
Token ID547
Feature activation-8.11e-03

Pos logit contributions
ivering+0.212
opl+0.188
 lately+0.185
Charl+0.184
 asleep+0.182
Neg logit contributions
ves-0.097
 they-0.092
J-0.084
 other-0.084
 two-0.081
Token not
Token ID407
Feature activation+5.68e-03

Pos logit contributions
ivering+0.015
ishly+0.014
opl+0.014
istent+0.013
 unatt+0.013
Neg logit contributions
J-0.011
 two-0.011
ves-0.011
ia-0.011
 other-0.010
Token growing
Token ID3957
Feature activation-6.71e-02

Pos logit contributions
J+0.007
ves+0.007
 Jen+0.007
ia+0.007
 two+0.007
Neg logit contributions
ivering-0.012
ishly-0.011
opl-0.010
 unatt-0.010
 lately-0.010
Token well
Token ID880
Feature activation-4.53e-02

Pos logit contributions
ivering+0.124
ishly+0.110
 lately+0.104
 unatt+0.102
opl+0.101
Neg logit contributions
J-0.099
ves-0.094
ia-0.093
 Jen-0.092
Jen-0.088
Token.
Token ID13
Feature activation-1.26e-02

Pos logit contributions
ivering+0.095
ishly+0.084
opl+0.079
 lately+0.078
ening+0.078
Neg logit contributions
J-0.056
ves-0.054
ia-0.052
 Jen-0.051
 Lia-0.049
Token.
Token ID13
Feature activation-1.82e-03

Pos logit contributions
J+0.007
ves+0.007
ia+0.006
 Jen+0.006
 Lia+0.006
Neg logit contributions
ivering-0.009
 lately-0.007
ishly-0.007
ening-0.007
pping-0.007
Token After
Token ID2293
Feature activation+1.38e-02

Pos logit contributions
ivering+0.003
 lately+0.002
ishly+0.002
 asleep+0.002
 about+0.002
Neg logit contributions
ves-0.003
J-0.003
ia-0.003
 Lia-0.003
ila-0.003
Token she
Token ID673
Feature activation-2.88e-02

Pos logit contributions
ia+0.019
J+0.019
ves+0.019
Jen+0.019
 Lia+0.018
Neg logit contributions
ivering-0.025
 lately-0.024
 asleep-0.023
 streaming-0.022
ishly-0.022
Token was
Token ID373
Feature activation-1.30e-02

Pos logit contributions
ivering+0.056
 lately+0.050
ishly+0.048
ening+0.048
 asleep+0.048
Neg logit contributions
J-0.041
ves-0.039
ia-0.038
Jen-0.037
 Jen-0.037
Token done
Token ID1760
Feature activation-3.78e-02

Pos logit contributions
ivering+0.023
ishly+0.021
ening+0.020
opl+0.019
 lately+0.019
Neg logit contributions
J-0.022
 Jen-0.021
ves-0.020
ia-0.020
 two-0.019
Token washing
Token ID20518
Feature activation-9.20e-02

Pos logit contributions
ivering+0.069
ishly+0.059
 lately+0.058
ening+0.057
 unatt+0.057
Neg logit contributions
J-0.062
ves-0.058
 Jen-0.056
ia-0.054
Jen-0.053
Token,
Token ID11
Feature activation-6.99e-03

Pos logit contributions
ivering+0.212
 lately+0.178
ishly+0.178
istent+0.177
opl+0.176
Neg logit contributions
J-0.107
ves-0.098
 Jen-0.097
ia-0.093
 two-0.091
Token Sally
Token ID25737
Feature activation-8.62e-03

Pos logit contributions
ivering+0.012
 lately+0.011
ishly+0.011
 asleep+0.011
 streaming+0.011
Neg logit contributions
ves-0.011
J-0.011
ia-0.011
Jen-0.010
 Lia-0.010
Token's
Token ID338
Feature activation-1.49e-02

Pos logit contributions
ivering+0.018
 lately+0.017
ishly+0.016
ening+0.016
 unatt+0.016
Neg logit contributions
J-0.011
ia-0.010
ves-0.010
 Jen-0.010
Jen-0.010
Token mom
Token ID1995
Feature activation-3.11e-02

Pos logit contributions
ivering+0.034
 asleep+0.032
 lately+0.031
 unatt+0.031
ishly+0.030
Neg logit contributions
ves-0.015
J-0.014
Jen-0.014
 Lia-0.013
Dan-0.012
Tokenmy
Token ID1820
Feature activation-1.71e-02

Pos logit contributions
ivering+0.042
 lately+0.036
ishly+0.035
 unatt+0.034
ening+0.034
Neg logit contributions
J-0.064
 Jen-0.059
ia-0.059
Jen-0.059
ves-0.057
Token.
Token ID13
Feature activation-6.01e-03

Pos logit contributions
ivering+0.029
 lately+0.025
ishly+0.025
ening+0.025
 asleep+0.024
Neg logit contributions
J-0.022
ves-0.021
ia-0.020
 Jen-0.020
Jen-0.020
Token Lily
Token ID20037
Feature activation+1.13e-02

Pos logit contributions
ivering+0.013
 lately+0.011
 asleep+0.011
ishly+0.011
ening+0.011
Neg logit contributions
J-0.007
ves-0.007
ia-0.007
Jen-0.007
 Jen-0.007
Token didn
Token ID1422
Feature activation-5.48e-03

Pos logit contributions
J+0.016
ves+0.015
ia+0.015
Jen+0.015
 Jen+0.015
Neg logit contributions
ivering-0.022
 lately-0.019
ishly-0.019
 asleep-0.019
ening-0.019
Token't
Token ID470
Feature activation-1.24e-02

Pos logit contributions
ivering+0.011
ening+0.010
 lately+0.010
ishly+0.009
 unatt+0.009
Neg logit contributions
J-0.008
ves-0.007
ia-0.007
Jen-0.007
 Jen-0.007
Token like
Token ID588
Feature activation-1.59e-02

Pos logit contributions
ivering+0.023
ishly+0.021
 asleep+0.020
ening+0.020
 unatt+0.019
Neg logit contributions
J-0.019
 Jen-0.018
Jen-0.017
ia-0.017
ves-0.017
Token washing
Token ID20518
Feature activation-9.14e-02

Pos logit contributions
ivering+0.035
ishly+0.031
 lately+0.028
istent+0.028
ening+0.028
Neg logit contributions
 Jen-0.021
J-0.020
ves-0.019
ia-0.018
 they-0.018
Token her
Token ID607
Feature activation-5.65e-03

Pos logit contributions
ivering+0.199
ishly+0.172
 lately+0.169
 unatt+0.168
 asleep+0.166
Neg logit contributions
J-0.113
ves-0.108
 Jen-0.103
ia-0.100
 Lia-0.097
Token hair
Token ID4190
Feature activation-2.09e-02

Pos logit contributions
ivering+0.011
 lately+0.010
ishly+0.010
ening+0.010
 unatt+0.010
Neg logit contributions
J-0.007
ves-0.007
ia-0.007
 Jen-0.007
 Lia-0.007
Token because
Token ID780
Feature activation-8.38e-03

Pos logit contributions
ivering+0.041
ishly+0.035
ening+0.035
 lately+0.034
Charl+0.034
Neg logit contributions
J-0.029
ves-0.028
 Jen-0.027
ia-0.026
Jen-0.025
Token it
Token ID340
Feature activation-9.18e-03

Pos logit contributions
ivering+0.017
 lately+0.016
 asleep+0.015
ening+0.015
ishly+0.015
Neg logit contributions
J-0.011
ves-0.010
ia-0.010
Jen-0.010
 Jen-0.009
Token took
Token ID1718
Feature activation+5.73e-03

Pos logit contributions
ivering+0.021
 lately+0.019
ishly+0.019
 asleep+0.019
ening+0.019
Neg logit contributions
J-0.010
ves-0.009
Jen-0.008
ia-0.008
 Jen-0.008
Token his
Token ID465
Feature activation-4.12e-03

Pos logit contributions
J+0.025
 Jen+0.022
ves+0.022
Jen+0.022
ia+0.021
Neg logit contributions
ivering-0.059
 lately-0.052
ishly-0.052
ening-0.051
 asleep-0.051
Token mom
Token ID1995
Feature activation-2.49e-02

Pos logit contributions
ivering+0.009
 lately+0.008
 asleep+0.008
ishly+0.008
ening+0.008
Neg logit contributions
J-0.005
ves-0.004
Jen-0.004
ia-0.004
 Lia-0.004
Token.
Token ID13
Feature activation-9.36e-03

Pos logit contributions
ivering+0.038
 lately+0.036
 unatt+0.033
ishly+0.033
Charl+0.033
Neg logit contributions
J-0.042
 Jen-0.040
Jen-0.039
ves-0.039
ia-0.038
Token She
Token ID1375
Feature activation-8.00e-03

Pos logit contributions
ivering+0.014
 lately+0.012
ishly+0.012
 asleep+0.012
ening+0.012
Neg logit contributions
J-0.017
ves-0.016
ia-0.016
Jen-0.015
 Lia-0.015
Token was
Token ID373
Feature activation-7.94e-03

Pos logit contributions
ivering+0.017
 lately+0.015
ishly+0.015
ening+0.015
 asleep+0.015
Neg logit contributions
J-0.010
ves-0.010
ia-0.009
Jen-0.009
 Jen-0.009
Token washing
Token ID20518
Feature activation-9.13e-02

Pos logit contributions
ivering+0.014
ening+0.014
opl+0.014
ishly+0.013
istent+0.013
Neg logit contributions
 Jen-0.012
J-0.012
 two-0.012
Jen-0.011
 second-0.010
Token the
Token ID262
Feature activation-7.69e-03

Pos logit contributions
ivering+0.213
 unatt+0.184
 lately+0.183
istent+0.182
opl+0.182
Neg logit contributions
J-0.098
ves-0.092
 Jen-0.090
 two-0.089
 other-0.083
Token dark
Token ID3223
Feature activation+2.97e-02

Pos logit contributions
ivering+0.016
 lately+0.014
ishly+0.014
ening+0.014
 asleep+0.014
Neg logit contributions
J-0.010
ves-0.009
ia-0.009
Jen-0.009
 Jen-0.009
Token laundry
Token ID25724
Feature activation-2.92e-02

Pos logit contributions
J+0.038
ves+0.034
ia+0.034
 Jen+0.033
Jen+0.033
Neg logit contributions
ivering-0.062
ishly-0.057
 lately-0.055
pping-0.054
 unatt-0.053
Token in
Token ID287
Feature activation-4.35e-03

Pos logit contributions
ivering+0.061
ishly+0.053
 lately+0.053
istent+0.052
opl+0.052
Neg logit contributions
J-0.035
ves-0.035
ia-0.032
 they-0.031
 Jen-0.031
Token the
Token ID262
Feature activation-6.47e-03

Pos logit contributions
ivering+0.010
ishly+0.009
 lately+0.008
ening+0.008
pping+0.008
Neg logit contributions
J-0.005
 Jen-0.005
Jen-0.005
ia-0.005
ves-0.005
TokenOh
Token ID5812
Feature activation+6.20e-03

Pos logit contributions
ivering+0.038
 lately+0.033
 unatt+0.031
Charl+0.030
 streaming+0.030
Neg logit contributions
ves-0.033
ia-0.032
 Jen-0.030
 Lia-0.030
J-0.029
Token Jack
Token ID3619
Feature activation-1.30e-02

Pos logit contributions
 Jen+0.008
J+0.008
ia+0.008
 Lia+0.008
ves+0.008
Neg logit contributions
ivering-0.013
ening-0.011
 lately-0.011
 asleep-0.011
 unatt-0.011
Token,
Token ID11
Feature activation-5.43e-02

Pos logit contributions
ivering+0.024
 lately+0.021
 unatt+0.021
 asleep+0.021
ening+0.021
Neg logit contributions
J-0.019
ia-0.019
 Jen-0.019
 Lia-0.017
ves-0.017
Token I
Token ID314
Feature activation-3.08e-02

Pos logit contributions
ivering+0.111
 asleep+0.093
 lately+0.093
ening+0.093
ishly+0.093
Neg logit contributions
J-0.075
 Jen-0.072
ia-0.071
ves-0.069
Jen-0.068
Token was
Token ID373
Feature activation-2.59e-02

Pos logit contributions
ivering+0.060
ishly+0.053
 lately+0.053
ening+0.053
 asleep+0.052
Neg logit contributions
J-0.045
 Jen-0.041
ia-0.040
Jen-0.040
ves-0.040
Token washing
Token ID20518
Feature activation-9.12e-02

Pos logit contributions
ivering+0.043
ishly+0.041
ening+0.039
 lately+0.038
opl+0.038
Neg logit contributions
J-0.041
 Jen-0.039
 two-0.039
 other-0.037
ila-0.036
Token the
Token ID262
Feature activation-8.37e-03

Pos logit contributions
ivering+0.212
ishly+0.181
istent+0.181
opl+0.177
 streaming+0.175
Neg logit contributions
J-0.096
 two-0.095
 other-0.090
 Jen-0.088
ves-0.086
Token shower
Token ID14643
Feature activation-1.80e-02

Pos logit contributions
ivering+0.017
 lately+0.016
ishly+0.015
ening+0.015
istent+0.015
Neg logit contributions
J-0.011
ves-0.010
ia-0.010
Jen-0.010
 Jen-0.010
Token,
Token ID11
Feature activation-3.49e-03

Pos logit contributions
ivering+0.037
ening+0.032
ishly+0.031
pping+0.031
 streaming+0.031
Neg logit contributions
J-0.023
ves-0.022
 Jen-0.022
ia-0.021
Jen-0.020
Token and
Token ID290
Feature activation+1.72e-02

Pos logit contributions
ivering+0.007
ening+0.006
ishly+0.006
 lately+0.006
 asleep+0.006
Neg logit contributions
J-0.005
 Jen-0.005
ia-0.005
 Lia-0.004
Jen-0.004
Token somehow
Token ID7599
Feature activation+3.91e-02

Pos logit contributions
J+0.021
 Jen+0.020
ves+0.019
ia+0.019
 they+0.018
Neg logit contributions
ivering-0.038
ishly-0.032
ening-0.032
 asleep-0.032
 lately-0.032
Token.
Token ID13
Feature activation-2.90e-03

Pos logit contributions
ivering+0.103
opl+0.091
ishly+0.088
ening+0.088
 unatt+0.085
Neg logit contributions
J-0.048
ves-0.047
 they-0.044
 Jen-0.043
ia-0.042
Token Lily
Token ID20037
Feature activation+1.29e-02

Pos logit contributions
ivering+0.006
 lately+0.006
 asleep+0.006
ishly+0.006
ening+0.006
Neg logit contributions
J-0.003
ves-0.003
ia-0.003
Jen-0.003
 Jen-0.003
Token didn
Token ID1422
Feature activation-6.73e-03

Pos logit contributions
J+0.017
ves+0.016
ia+0.016
Jen+0.015
 Jen+0.014
Neg logit contributions
ivering-0.027
 lately-0.025
 asleep-0.025
 unatt-0.025
ening-0.024
Token't
Token ID470
Feature activation-1.21e-02

Pos logit contributions
ivering+0.014
ening+0.012
 lately+0.012
ishly+0.012
 unatt+0.012
Neg logit contributions
J-0.009
ves-0.009
ia-0.008
Jen-0.008
 Jen-0.008
Token like
Token ID588
Feature activation-1.35e-02

Pos logit contributions
ivering+0.020
ishly+0.017
 lately+0.017
 asleep+0.016
ening+0.016
Neg logit contributions
J-0.021
ves-0.020
ia-0.020
 Jen-0.020
Jen-0.020
Token washing
Token ID20518
Feature activation-9.11e-02

Pos logit contributions
ivering+0.032
ishly+0.028
 unatt+0.026
istent+0.025
opl+0.025
Neg logit contributions
 Jen-0.016
J-0.016
ves-0.015
 they-0.015
 other-0.015
Token her
Token ID607
Feature activation-4.35e-03

Pos logit contributions
ivering+0.209
ishly+0.184
 unatt+0.180
opl+0.178
istent+0.175
Neg logit contributions
J-0.100
ves-0.099
 Jen-0.090
 other-0.089
 two-0.088
Token hair
Token ID4190
Feature activation-1.96e-02

Pos logit contributions
ivering+0.009
 lately+0.008
ishly+0.008
 unatt+0.008
ening+0.008
Neg logit contributions
ves-0.005
J-0.005
ia-0.005
 Jen-0.005
 Lia-0.005
Token because
Token ID780
Feature activation-7.82e-03

Pos logit contributions
ivering+0.039
ishly+0.034
ening+0.033
 lately+0.033
Charl+0.033
Neg logit contributions
ves-0.026
J-0.025
 Jen-0.024
ia-0.023
 they-0.023
Token the
Token ID262
Feature activation+1.99e-03

Pos logit contributions
ivering+0.018
ishly+0.016
 lately+0.016
ening+0.016
 asleep+0.016
Neg logit contributions
J-0.009
ves-0.008
ia-0.008
 Jen-0.008
Jen-0.008
Token shampoo
Token ID47259
Feature activation-1.53e-02

Pos logit contributions
J+0.002
ves+0.002
 other+0.002
Jen+0.002
 Jen+0.002
Neg logit contributions
ivering-0.005
ishly-0.004
 lately-0.004
ening-0.004
 unatt-0.004
Token day
Token ID1110
Feature activation-7.22e-03

Pos logit contributions
J+0.056
ves+0.053
ia+0.050
Jen+0.050
 Lia+0.050
Neg logit contributions
ivering-0.085
 lately-0.076
ening-0.073
 asleep-0.073
ishly-0.072
Token,
Token ID11
Feature activation-2.17e-02

Pos logit contributions
ivering+0.008
 lately+0.007
ening+0.006
 streaming+0.006
ishly+0.006
Neg logit contributions
ves-0.015
J-0.015
ia-0.015
Jen-0.015
 Lia-0.014
Token while
Token ID981
Feature activation+2.31e-03

Pos logit contributions
 lately+0.031
ivering+0.030
 streaming+0.028
ishly+0.027
 about+0.026
Neg logit contributions
ves-0.039
ia-0.038
J-0.035
ila-0.034
 Lia-0.034
Token Sammy
Token ID44067
Feature activation-1.65e-02

Pos logit contributions
ia+0.004
ves+0.004
J+0.004
 Lia+0.004
Jen+0.004
Neg logit contributions
ivering-0.003
 lately-0.003
 streaming-0.003
 asleep-0.003
 weeping-0.003
Token was
Token ID373
Feature activation-1.80e-02

Pos logit contributions
ivering+0.039
 lately+0.037
ishly+0.036
 unatt+0.035
ening+0.035
Neg logit contributions
J-0.016
ia-0.014
Jen-0.014
ves-0.013
 Jen-0.013
Token washing
Token ID20518
Feature activation-9.08e-02

Pos logit contributions
ivering+0.030
ishly+0.028
opl+0.028
ening+0.027
 lately+0.027
Neg logit contributions
 two-0.028
J-0.027
 Jen-0.026
ves-0.026
 other-0.025
Token the
Token ID262
Feature activation-1.02e-02

Pos logit contributions
ivering+0.236
opl+0.204
istent+0.202
ishly+0.202
Charl+0.202
Neg logit contributions
 other-0.074
 two-0.072
J-0.069
ves-0.068
 Jen-0.064
Token bell
Token ID8966
Feature activation+2.95e-03

Pos logit contributions
ivering+0.021
 lately+0.019
ishly+0.019
istent+0.018
pping+0.018
Neg logit contributions
J-0.013
Jen-0.012
 other-0.012
ves-0.012
 two-0.012
Token,
Token ID11
Feature activation-1.36e-02

Pos logit contributions
ves+0.004
 Jen+0.004
J+0.004
ia+0.004
 they+0.004
Neg logit contributions
ivering-0.006
Charl-0.005
 lately-0.005
ishly-0.005
ening-0.005
Token he
Token ID339
Feature activation-7.28e-04

Pos logit contributions
ivering+0.021
 lately+0.020
 streaming+0.019
 asleep+0.019
ishly+0.018
Neg logit contributions
ia-0.023
ves-0.022
J-0.022
Jen-0.021
 Lia-0.020
Token heard
Token ID2982
Feature activation+1.98e-02

Pos logit contributions
ivering+0.001
 lately+0.001
 asleep+0.001
 unatt+0.001
ening+0.001
Neg logit contributions
J-0.001
ves-0.001
Jen-0.001
 Jen-0.001
ia-0.001
Token want
Token ID765
Feature activation+5.12e-02

Pos logit contributions
J+0.026
ia+0.024
 Jen+0.024
ves+0.024
Jen+0.023
Neg logit contributions
ivering-0.041
 lately-0.036
ening-0.035
 asleep-0.034
ishly-0.034
Token to
Token ID284
Feature activation-2.35e-03

Pos logit contributions
Jen+0.089
J+0.089
ves+0.087
ia+0.087
 Lia+0.082
Neg logit contributions
ivering-0.072
 asleep-0.070
 lately-0.070
 anymore-0.067
 about-0.066
Token mix
Token ID5022
Feature activation-1.78e-02

Pos logit contributions
ivering+0.004
 anymore+0.003
opl+0.003
 lately+0.003
 regret+0.003
Neg logit contributions
J-0.004
ves-0.004
ia-0.003
Jen-0.003
 Lia-0.003
Token more
Token ID517
Feature activation+5.18e-02

Pos logit contributions
ivering+0.031
 anymore+0.030
 lately+0.030
ening+0.029
 asleep+0.029
Neg logit contributions
J-0.025
Jen-0.024
ves-0.023
ia-0.023
 Jen-0.021
Token colors
Token ID7577
Feature activation+3.82e-02

Pos logit contributions
J+0.074
Jen+0.073
 Jen+0.066
 Lia+0.065
ia+0.064
Neg logit contributions
ivering-0.092
ening-0.087
 lately-0.087
 about-0.086
 anymore-0.086
Token tomorrow
Token ID9439
Feature activation+5.38e-02

Pos logit contributions
J+0.058
ves+0.054
ia+0.054
Jen+0.053
 Jen+0.052
Neg logit contributions
ivering-0.071
 lately-0.062
ishly-0.060
 asleep-0.060
ening-0.060
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
J+0.101
Jen+0.097
ves+0.089
 tad+0.089
ia+0.089
Neg logit contributions
 anymore-0.074
 lately-0.073
ivering-0.072
 asleep-0.067
 about-0.067
Token<|endoftext|>
Token ID50256
Feature activation-3.41e-02

Pos logit contributions
ves+0.016
J+0.016
ia+0.015
 tad+0.014
ull+0.014
Neg logit contributions
 lately-0.016
ivering-0.015
 Playing-0.015
 about-0.014
 asleep-0.014
TokenL
Token ID43
Feature activation+1.42e-02

Pos logit contributions
ivering+0.056
 lately+0.049
ishly+0.047
 asleep+0.047
ening+0.047
Neg logit contributions
J-0.058
ves-0.056
ia-0.055
Jen-0.054
 Jen-0.054
Tokenily
Token ID813
Feature activation+4.41e-03

Pos logit contributions
 tad+0.014
Ar+0.014
Y+0.012
Land+0.012
Ah+0.012
Neg logit contributions
 about-0.030
 anymore-0.027
ivering-0.027
pping-0.026
he-0.026
Token loved
Token ID6151
Feature activation+6.41e-03

Pos logit contributions
ia+0.005
J+0.005
 Jen+0.005
ila+0.005
Jen+0.005
Neg logit contributions
ivering-0.010
ishly-0.009
 unatt-0.009
istent-0.008
 lately-0.008
Token and
Token ID290
Feature activation-1.08e-02

Pos logit contributions
ivering+0.052
 lately+0.044
 unatt+0.043
ishly+0.043
opl+0.042
Neg logit contributions
J-0.031
ves-0.030
 Jen-0.029
ia-0.029
 Lia-0.028
Token then
Token ID788
Feature activation+2.18e-02

Pos logit contributions
ivering+0.020
 lately+0.017
ening+0.016
ishly+0.016
 unatt+0.016
Neg logit contributions
J-0.017
ves-0.016
 Jen-0.016
ia-0.016
Jen-0.016
Token went
Token ID1816
Feature activation-2.01e-03

Pos logit contributions
J+0.028
ves+0.027
ia+0.027
 Jen+0.027
 Lia+0.025
Neg logit contributions
ivering-0.046
 lately-0.039
ishly-0.039
ening-0.039
 unatt-0.038
Token for
Token ID329
Feature activation-2.22e-02

Pos logit contributions
ivering+0.004
 lately+0.003
istent+0.003
ening+0.003
ishly+0.003
Neg logit contributions
J-0.003
ves-0.003
 Jen-0.003
ia-0.003
 Lia-0.003
Token one
Token ID530
Feature activation+3.27e-02

Pos logit contributions
ivering+0.045
 lately+0.041
 asleep+0.041
 unatt+0.040
ishly+0.040
Neg logit contributions
J-0.029
ves-0.027
ia-0.026
Jen-0.026
 Jen-0.025
Token more
Token ID517
Feature activation+4.72e-02

Pos logit contributions
J+0.048
ves+0.046
Jen+0.044
ia+0.044
 Lia+0.043
Neg logit contributions
ivering-0.062
 lately-0.056
 asleep-0.054
 unatt-0.054
ening-0.053
Token dip
Token ID19550
Feature activation+1.21e-02

Pos logit contributions
J+0.067
ves+0.062
ia+0.061
Jen+0.061
 Jen+0.060
Neg logit contributions
ivering-0.093
 lately-0.082
 asleep-0.080
ening-0.080
ishly-0.080
Token in
Token ID287
Feature activation+7.17e-03

Pos logit contributions
J+0.017
ia+0.016
 Jen+0.016
ves+0.016
Jen+0.015
Neg logit contributions
ivering-0.024
ishly-0.020
 lately-0.020
ening-0.020
 unatt-0.020
Token the
Token ID262
Feature activation-8.53e-04

Pos logit contributions
 Jen+0.007
J+0.007
ia+0.007
 two+0.006
Jen+0.006
Neg logit contributions
ivering-0.017
ishly-0.015
istent-0.015
 lately-0.014
pping-0.014
Token pond
Token ID16723
Feature activation+1.38e-02

Pos logit contributions
ivering+0.002
 lately+0.002
ishly+0.002
ening+0.002
 asleep+0.002
Neg logit contributions
J-0.001
ves-0.001
ia-0.001
Jen-0.001
 Jen-0.001
Token.
Token ID13
Feature activation-1.02e-03

Pos logit contributions
J+0.015
ves+0.015
ia+0.015
 Jen+0.014
 Lia+0.013
Neg logit contributions
ivering-0.030
 lately-0.026
ening-0.026
ishly-0.026
pping-0.025
Token.
Token ID13
Feature activation+6.35e-03

Pos logit contributions
J+0.046
ves+0.044
 Lia+0.042
Jen+0.042
ia+0.041
Neg logit contributions
ivering-0.044
 lately-0.040
 anymore-0.039
ening-0.037
 unatt-0.037
Token They
Token ID1119
Feature activation+2.05e-02

Pos logit contributions
ves+0.012
J+0.012
kins+0.011
ia+0.011
 clues+0.010
Neg logit contributions
 Playing-0.007
ivering-0.007
 about-0.007
 Eating-0.007
 asleep-0.007
Token want
Token ID765
Feature activation+5.06e-02

Pos logit contributions
J+0.023
 Jen+0.022
ia+0.022
 Lia+0.022
ves+0.021
Neg logit contributions
ivering-0.047
 lately-0.042
 unatt-0.041
ening-0.040
ishly-0.039
Token to
Token ID284
Feature activation-1.75e-03

Pos logit contributions
J+0.110
ves+0.107
Jen+0.106
ia+0.101
ila+0.099
Neg logit contributions
 about-0.051
 anymore-0.050
 asleep-0.049
 lately-0.045
 such-0.043
Token say
Token ID910
Feature activation+4.27e-02

Pos logit contributions
ivering+0.003
 anymore+0.003
 asleep+0.003
ishly+0.003
pping+0.003
Neg logit contributions
J-0.003
ves-0.003
ia-0.002
kins-0.002
Jen-0.002
Token hello
Token ID23748
Feature activation+6.07e-02

Pos logit contributions
J+0.076
Jen+0.072
ves+0.067
ia+0.067
ila+0.063
Neg logit contributions
ivering-0.061
 asleep-0.060
ishly-0.060
 lately-0.058
 anymore-0.058
Token to
Token ID284
Feature activation+2.73e-03

Pos logit contributions
J+0.101
ves+0.098
Jen+0.093
ia+0.091
 Lia+0.088
Neg logit contributions
ivering-0.102
 lately-0.091
 asleep-0.091
ishly-0.089
 anymore-0.087
Token the
Token ID262
Feature activation-2.90e-03

Pos logit contributions
J+0.005
ves+0.005
Jen+0.005
Ar+0.005
ia+0.005
Neg logit contributions
 anymore-0.004
ishly-0.003
 about-0.003
 such-0.003
ening-0.003
Token frog
Token ID21264
Feature activation+5.16e-03

Pos logit contributions
ivering+0.006
 asleep+0.005
 lately+0.005
ishly+0.005
 anymore+0.005
Neg logit contributions
J-0.004
ves-0.004
ia-0.003
Jen-0.003
 Jen-0.003
Token.
Token ID13
Feature activation+3.87e-03

Pos logit contributions
J+0.008
ves+0.008
Jen+0.008
ia+0.007
 Jen+0.007
Neg logit contributions
ivering-0.009
 lately-0.008
 asleep-0.008
ishly-0.008
 anymore-0.008
Token They
Token ID1119
Feature activation+1.48e-02

Pos logit contributions
ves+0.008
J+0.007
ia+0.007
kins+0.007
 clues+0.006
Neg logit contributions
 Playing-0.004
 lately-0.004
 about-0.004
ivering-0.004
ishly-0.004
Token and
Token ID290
Feature activation-2.69e-02

Pos logit contributions
J+0.018
ves+0.017
Jen+0.017
ia+0.017
 Jen+0.016
Neg logit contributions
ivering-0.023
ishly-0.020
 lately-0.020
ening-0.020
 asleep-0.020
Token Tess
Token ID39412
Feature activation-8.39e-04

Pos logit contributions
ivering+0.039
 lately+0.035
ishly+0.035
ening+0.033
 asleep+0.033
Neg logit contributions
ves-0.049
J-0.049
ia-0.049
Jen-0.047
 Lia-0.046
Token ran
Token ID4966
Feature activation+1.10e-02

Pos logit contributions
ivering+0.002
ishly+0.001
pping+0.001
 lately+0.001
 asleep+0.001
Neg logit contributions
J-0.001
ves-0.001
ia-0.001
 Lia-0.001
Jen-0.001
Token around
Token ID1088
Feature activation-2.21e-02

Pos logit contributions
J+0.022
ves+0.022
ia+0.021
Jen+0.021
 Lia+0.020
Neg logit contributions
ivering-0.014
 lately-0.012
 asleep-0.012
ishly-0.012
ening-0.012
Token the
Token ID262
Feature activation+3.98e-03

Pos logit contributions
ivering+0.045
 lately+0.040
ishly+0.038
ening+0.038
 unatt+0.038
Neg logit contributions
J-0.030
 Jen-0.028
ves-0.028
ia-0.028
Jen-0.027
Token park
Token ID3952
Feature activation+5.51e-02

Pos logit contributions
J+0.004
Jen+0.004
 other+0.004
 two+0.004
 Jen+0.003
Neg logit contributions
 lately-0.009
ivering-0.009
ishly-0.009
ening-0.009
istent-0.009
Token,
Token ID11
Feature activation-1.40e-02

Pos logit contributions
J+0.093
ves+0.087
ia+0.087
Jen+0.086
 Jen+0.084
Neg logit contributions
ivering-0.092
 lately-0.080
ishly-0.080
 asleep-0.078
ening-0.078
Token quickly
Token ID2952
Feature activation+2.11e-02

Pos logit contributions
ivering+0.024
 lately+0.020
ening+0.019
ishly+0.019
 unatt+0.019
Neg logit contributions
J-0.024
 Jen-0.023
ves-0.022
Jen-0.022
ia-0.022
Token gathering
Token ID11228
Feature activation-1.10e-02

Pos logit contributions
J+0.030
 Jen+0.029
ves+0.029
ia+0.028
Jen+0.027
Neg logit contributions
ivering-0.041
 lately-0.035
ishly-0.034
ening-0.033
 unatt-0.033
Token the
Token ID262
Feature activation-4.04e-03

Pos logit contributions
ivering+0.021
 lately+0.019
 asleep+0.019
ening+0.019
ishly+0.019
Neg logit contributions
J-0.015
ves-0.015
ia-0.014
Jen-0.014
 Jen-0.013
Token dolls
Token ID36062
Feature activation+1.69e-02

Pos logit contributions
ivering+0.010
 lately+0.009
ishly+0.008
ening+0.008
pping+0.008
Neg logit contributions
J-0.004
ves-0.004
ia-0.004
 Jen-0.004
 Lia-0.003
Token happy
Token ID3772
Feature activation-1.65e-03

Pos logit contributions
ivering+0.003
ishly+0.002
ening+0.002
istent+0.002
 unatt+0.002
Neg logit contributions
 Jen-0.002
J-0.002
 Lia-0.002
ia-0.002
 two-0.002
Token and
Token ID290
Feature activation-3.10e-03

Pos logit contributions
ivering+0.004
opl+0.004
ishly+0.004
istent+0.004
ening+0.003
Neg logit contributions
 Jen-0.002
 they-0.002
J-0.002
 Mia-0.002
ia-0.002
Token l
Token ID300
Feature activation-4.61e-02

Pos logit contributions
ivering+0.006
 lately+0.006
ishly+0.006
ening+0.006
 asleep+0.006
Neg logit contributions
J-0.004
ves-0.004
ia-0.004
Jen-0.004
 Jen-0.004
Tokenicked
Token ID9484
Feature activation-1.09e-02

Pos logit contributions
ivering+0.078
ishly+0.067
 lately+0.066
 unatt+0.062
 asleep+0.062
Neg logit contributions
J-0.077
ves-0.074
Jen-0.072
ia-0.071
 Jen-0.070
Token the
Token ID262
Feature activation+2.69e-03

Pos logit contributions
ivering+0.016
 lately+0.014
ishly+0.014
 anymore+0.014
ening+0.014
Neg logit contributions
J-0.019
ves-0.019
Jen-0.018
ia-0.018
Ar-0.018
Token little
Token ID1310
Feature activation+5.02e-02

Pos logit contributions
J+0.005
Jud+0.004
ves+0.004
lan+0.004
 Mir+0.004
Neg logit contributions
ivering-0.005
ishly-0.004
 weeping-0.004
 asleep-0.003
ening-0.003
Token girl
Token ID2576
Feature activation+1.67e-02

Pos logit contributions
ves+0.071
J+0.070
ia+0.063
Dan+0.060
Jen+0.060
Neg logit contributions
ivering-0.101
ishly-0.088
ening-0.088
 lately-0.088
 asleep-0.085
Token's
Token ID338
Feature activation+1.80e-03

Pos logit contributions
J+0.028
ves+0.026
Jen+0.026
ia+0.026
 Jen+0.025
Neg logit contributions
ivering-0.029
 lately-0.025
ishly-0.025
ening-0.024
 asleep-0.024
Token face
Token ID1986
Feature activation-2.03e-02

Pos logit contributions
J+0.004
ila+0.003
ves+0.003
Dan+0.003
Jud+0.003
Neg logit contributions
ivering-0.003
ishly-0.002
 weeping-0.002
 streaming-0.002
ening-0.002
Token.
Token ID13
Feature activation-5.86e-03

Pos logit contributions
ivering+0.038
 lately+0.034
ishly+0.033
 asleep+0.033
ening+0.033
Neg logit contributions
J-0.030
ves-0.028
Jen-0.028
ia-0.028
 Jen-0.027
Token The
Token ID383
Feature activation+1.15e-02

Pos logit contributions
ivering+0.011
 lately+0.010
ishly+0.010
 asleep+0.010
ening+0.010
Neg logit contributions
J-0.008
ves-0.008
ia-0.008
Jen-0.008
 Jen-0.008
Token hesitant
Token ID32848
Feature activation+3.86e-04

Pos logit contributions
ivering+0.060
ening+0.055
 lately+0.055
opl+0.052
 unatt+0.052
Neg logit contributions
J-0.046
 two-0.045
ves-0.043
 Jen-0.043
 second-0.042
Token at
Token ID379
Feature activation-1.90e-02

Pos logit contributions
J+0.001
ia+0.001
 Jen+0.001
 Lia+0.001
 they+0.001
Neg logit contributions
ivering-0.001
opl-0.001
 unatt-0.001
 asleep-0.001
pping-0.001
Token first
Token ID717
Feature activation+2.15e-02

Pos logit contributions
ivering+0.041
 lately+0.039
ishly+0.038
 asleep+0.038
ening+0.037
Neg logit contributions
J-0.022
ves-0.021
Jen-0.020
ia-0.020
 Jen-0.019
Token.
Token ID13
Feature activation-1.57e-02

Pos logit contributions
J+0.035
ves+0.033
ia+0.033
 Jen+0.033
Jen+0.032
Neg logit contributions
ivering-0.038
 lately-0.031
 unatt-0.031
 asleep-0.031
ening-0.031
Token They
Token ID1119
Feature activation-3.80e-03

Pos logit contributions
ivering+0.029
 lately+0.026
ishly+0.026
 asleep+0.025
ening+0.025
Neg logit contributions
J-0.023
ves-0.023
ia-0.021
Jen-0.021
 Jen-0.020
Token did
Token ID750
Feature activation+3.20e-02

Pos logit contributions
ivering+0.009
 lately+0.007
ening+0.007
 asleep+0.007
 unatt+0.007
Neg logit contributions
J-0.005
ves-0.004
 Jen-0.004
ia-0.004
Jen-0.004
Token not
Token ID407
Feature activation-1.91e-02

Pos logit contributions
J+0.038
ves+0.035
ia+0.035
Jen+0.034
 Jen+0.034
Neg logit contributions
ivering-0.070
 lately-0.063
ishly-0.061
ening-0.061
 asleep-0.061
Token know
Token ID760
Feature activation+1.56e-02

Pos logit contributions
ivering+0.037
 lately+0.032
ishly+0.032
ening+0.032
 asleep+0.031
Neg logit contributions
J-0.028
ves-0.026
ia-0.026
Jen-0.025
 Jen-0.025
Token if
Token ID611
Feature activation+1.27e-02

Pos logit contributions
J+0.030
ves+0.029
ia+0.029
Jen+0.028
 Jen+0.028
Neg logit contributions
ivering-0.022
 lately-0.019
ishly-0.018
ening-0.018
 asleep-0.018
Token it
Token ID340
Feature activation-2.32e-02

Pos logit contributions
J+0.014
Jen+0.014
ves+0.013
ia+0.013
Ar+0.013
Neg logit contributions
 lately-0.026
 asleep-0.023
ishly-0.023
 anymore-0.023
 about-0.023
Token was
Token ID373
Feature activation-1.01e-03

Pos logit contributions
ivering+0.049
 lately+0.043
ishly+0.042
 asleep+0.042
ening+0.042
Neg logit contributions
J-0.030
ves-0.028
ia-0.028
 Jen-0.027
Jen-0.027
Token was
Token ID373
Feature activation+8.35e-03

Pos logit contributions
ivering+0.079
 lately+0.070
 unatt+0.069
 asleep+0.068
ening+0.066
Neg logit contributions
ves-0.029
J-0.028
ia-0.027
 third-0.024
 Lia-0.024
Token better
Token ID1365
Feature activation+7.01e-03

Pos logit contributions
 Jen+0.008
ia+0.008
J+0.008
 Lia+0.007
 two+0.007
Neg logit contributions
ivering-0.020
ishly-0.018
istent-0.017
 lately-0.017
ening-0.017
Token to
Token ID284
Feature activation-9.22e-03

Pos logit contributions
J+0.012
ves+0.012
Jen+0.011
ia+0.011
 Lia+0.011
Neg logit contributions
ivering-0.011
 lately-0.010
 asleep-0.009
ening-0.009
ishly-0.009
Token live
Token ID2107
Feature activation-1.24e-04

Pos logit contributions
ivering+0.020
 lately+0.018
ening+0.017
ishly+0.017
 asleep+0.017
Neg logit contributions
J-0.011
ves-0.011
ia-0.011
 Jen-0.010
Jen-0.010
Token in
Token ID287
Feature activation-3.47e-03

Pos logit contributions
ivering+0.000
 lately+0.000
 asleep+0.000
 unatt+0.000
ening+0.000
Neg logit contributions
J-0.000
ves-0.000
Jen-0.000
ia-0.000
 Jen-0.000
Token a
Token ID257
Feature activation+2.21e-02

Pos logit contributions
ivering+0.008
 lately+0.007
ishly+0.007
ening+0.007
 asleep+0.007
Neg logit contributions
J-0.004
ves-0.004
ia-0.004
 Jen-0.004
Jen-0.004
Token small
Token ID1402
Feature activation+1.35e-02

Pos logit contributions
J+0.031
ves+0.030
ia+0.030
Jen+0.029
 Jen+0.029
Neg logit contributions
ivering-0.043
 asleep-0.037
 unatt-0.037
 lately-0.037
ening-0.036
Token and
Token ID290
Feature activation+2.69e-02

Pos logit contributions
J+0.018
ia+0.017
 Jen+0.017
Jen+0.016
 Lia+0.016
Neg logit contributions
ivering-0.027
ishly-0.024
pping-0.024
 lately-0.023
 streaming-0.023
Token cozy
Token ID37438
Feature activation-1.11e-02

Pos logit contributions
J+0.039
ves+0.038
ia+0.037
Jen+0.036
 Jen+0.034
Neg logit contributions
ivering-0.050
 lately-0.046
 asleep-0.045
 unatt-0.044
ishly-0.043
Token house
Token ID2156
Feature activation+2.10e-02

Pos logit contributions
ivering+0.021
 lately+0.018
ishly+0.018
pping+0.018
ening+0.018
Neg logit contributions
J-0.016
ia-0.015
 Jen-0.015
ves-0.015
Jen-0.015
Token than
Token ID621
Feature activation+5.39e-03

Pos logit contributions
J+0.027
ves+0.025
 Jen+0.024
ia+0.024
 Lia+0.023
Neg logit contributions
ivering-0.044
 lately-0.038
ishly-0.038
ening-0.038
pping-0.037
Token not
Token ID407
Feature activation+8.86e-03

Pos logit contributions
J+0.013
 Jen+0.012
 two+0.012
ves+0.012
ia+0.012
Neg logit contributions
ivering-0.018
ishly-0.016
 lately-0.015
istent-0.015
opl-0.015
Token so
Token ID523
Feature activation-2.35e-03

Pos logit contributions
J+0.013
 Jen+0.012
ves+0.012
ia+0.012
Jen+0.012
Neg logit contributions
ivering-0.017
ishly-0.015
 lately-0.014
 unatt-0.014
ening-0.014
Token scary
Token ID14343
Feature activation-1.04e-02

Pos logit contributions
ivering+0.005
 lately+0.004
ishly+0.004
 asleep+0.004
ening+0.004
Neg logit contributions
J-0.003
ves-0.003
ia-0.003
 Jen-0.003
Jen-0.003
Token.
Token ID13
Feature activation-8.05e-03

Pos logit contributions
ivering+0.020
ishly+0.016
 unatt+0.016
 lately+0.016
pping+0.016
Neg logit contributions
J-0.015
 Jen-0.015
ves-0.014
ia-0.014
 they-0.014
Token Soon
Token ID15894
Feature activation+4.19e-02

Pos logit contributions
ivering+0.013
 lately+0.011
ishly+0.011
 asleep+0.011
ening+0.011
Neg logit contributions
J-0.014
ves-0.013
ia-0.013
Jen-0.013
 Jen-0.013
Token,
Token ID11
Feature activation-1.02e-03

Pos logit contributions
J+0.074
ves+0.070
Jen+0.069
ia+0.069
 Lia+0.066
Neg logit contributions
ivering-0.065
 lately-0.059
ishly-0.056
 asleep-0.056
ening-0.055
Token the
Token ID262
Feature activation+1.16e-02

Pos logit contributions
 lately+0.002
ivering+0.002
ishly+0.002
 asleep+0.002
 anymore+0.002
Neg logit contributions
J-0.001
ves-0.001
ia-0.001
Jen-0.001
Ar-0.001
Token picture
Token ID4286
Feature activation+5.56e-03

Pos logit contributions
J+0.016
ves+0.016
 Lia+0.014
Jen+0.014
ia+0.014
Neg logit contributions
ivering-0.023
 lately-0.020
 unatt-0.020
 asleep-0.020
ening-0.020
Token was
Token ID373
Feature activation+1.41e-02

Pos logit contributions
J+0.006
ves+0.006
ia+0.006
 Jen+0.006
Jen+0.006
Neg logit contributions
ivering-0.012
 lately-0.011
ishly-0.011
ening-0.011
 unatt-0.011
Token done
Token ID1760
Feature activation-2.24e-02

Pos logit contributions
J+0.021
 Jen+0.020
 two+0.020
 second+0.019
ves+0.019
Neg logit contributions
ivering-0.026
ishly-0.023
 lately-0.023
Charl-0.022
istent-0.022
Token.
Token ID13
Feature activation-5.86e-03

Pos logit contributions
ivering+0.046
ishly+0.040
 lately+0.039
 unatt+0.038
ening+0.038
Neg logit contributions
J-0.031
ves-0.029
ia-0.028
 Jen-0.027
Jen-0.027
Token normal
Token ID3487
Feature activation-3.05e-02

Pos logit contributions
ivering+0.019
 lately+0.017
ening+0.017
ishly+0.017
 unatt+0.016
Neg logit contributions
J-0.013
 Jen-0.012
ia-0.012
ves-0.012
 Lia-0.012
Token brother
Token ID3956
Feature activation-3.68e-03

Pos logit contributions
ivering+0.061
ening+0.052
ishly+0.052
 lately+0.052
pping+0.052
Neg logit contributions
J-0.041
ia-0.040
 Jen-0.039
 Lia-0.038
ves-0.038
Token and
Token ID290
Feature activation+5.53e-04

Pos logit contributions
ivering+0.007
 lately+0.007
ening+0.006
ishly+0.006
 unatt+0.006
Neg logit contributions
J-0.005
ia-0.005
 Jen-0.005
ves-0.005
 Lia-0.005
Token sister
Token ID6621
Feature activation-6.66e-03

Pos logit contributions
J+0.001
ves+0.001
ia+0.001
Jen+0.001
 Jen+0.001
Neg logit contributions
ivering-0.001
 lately-0.001
ishly-0.001
ening-0.001
 asleep-0.001
Token again
Token ID757
Feature activation+1.26e-02

Pos logit contributions
ivering+0.016
 lately+0.014
ening+0.014
istent+0.014
ishly+0.013
Neg logit contributions
J-0.007
ia-0.006
ves-0.006
 Jen-0.006
 other-0.006
Token.
Token ID13
Feature activation-1.82e-03

Pos logit contributions
J+0.017
ves+0.016
ia+0.016
 Jen+0.015
Jen+0.015
Neg logit contributions
ivering-0.026
 lately-0.023
ishly-0.022
ening-0.022
 asleep-0.022
Token<|endoftext|>
Token ID50256
Feature activation-3.30e-02

Pos logit contributions
ivering+0.004
 lately+0.004
ishly+0.004
ening+0.004
 asleep+0.004
Neg logit contributions
J-0.002
ves-0.002
ia-0.002
Jen-0.002
 Jen-0.002
TokenTim
Token ID14967
Feature activation+1.60e-02

Pos logit contributions
ivering+0.060
 asleep+0.054
 lately+0.053
 unatt+0.051
ening+0.050
Neg logit contributions
J-0.047
ves-0.046
ia-0.045
 Jen-0.044
Jen-0.044
Token had
Token ID550
Feature activation-1.89e-02

Pos logit contributions
ia+0.025
J+0.025
 Jen+0.024
Jen+0.023
ila+0.023
Neg logit contributions
ivering-0.029
ishly-0.026
 unatt-0.025
 lately-0.025
istent-0.024
Token a
Token ID257
Feature activation-8.00e-03

Pos logit contributions
ivering+0.041
 lately+0.038
 asleep+0.038
 unatt+0.036
ening+0.036
Neg logit contributions
J-0.020
ves-0.020
Jen-0.019
ia-0.019
 Lia-0.019
Token small
Token ID1402
Feature activation-2.26e-02

Pos logit contributions
ivering+0.016
 asleep+0.015
 lately+0.015
ishly+0.014
 unatt+0.014
Neg logit contributions
J-0.010
ves-0.010
Jen-0.009
ia-0.009
 Jen-0.009
Token of
Token ID286
Feature activation+1.45e-02

Pos logit contributions
ivering+0.009
 lately+0.008
ishly+0.008
 asleep+0.008
ening+0.008
Neg logit contributions
J-0.006
ves-0.006
ia-0.006
 Jen-0.006
Jen-0.006
Token things
Token ID1243
Feature activation-4.91e-03

Pos logit contributions
J+0.016
ves+0.015
ia+0.015
Jen+0.014
 Lia+0.014
Neg logit contributions
ivering-0.033
 lately-0.030
ening-0.029
 asleep-0.029
 unatt-0.028
Token in
Token ID287
Feature activation+2.03e-03

Pos logit contributions
ivering+0.014
ishly+0.012
istent+0.012
ening+0.011
opl+0.011
Neg logit contributions
 they-0.004
 Jen-0.003
J-0.003
ves-0.003
 two-0.003
Token his
Token ID465
Feature activation+1.34e-02

Pos logit contributions
J+0.003
ves+0.003
ia+0.003
Jen+0.003
 Lia+0.003
Neg logit contributions
ivering-0.004
 lately-0.003
 asleep-0.003
ening-0.003
 unatt-0.003
Token garden
Token ID11376
Feature activation-1.71e-02

Pos logit contributions
J+0.021
ves+0.020
ia+0.019
Jen+0.019
 Jen+0.019
Neg logit contributions
ivering-0.025
 lately-0.021
 asleep-0.021
ishly-0.021
 unatt-0.021
Token.
Token ID13
Feature activation-2.03e-03

Pos logit contributions
ivering+0.039
ening+0.035
ishly+0.035
 lately+0.034
 streaming+0.034
Neg logit contributions
J-0.018
ves-0.017
ia-0.016
 Jen-0.016
Jen-0.015
Token So
Token ID1406
Feature activation+3.08e-02

Pos logit contributions
ivering+0.003
 lately+0.003
 asleep+0.002
ishly+0.002
ening+0.002
Neg logit contributions
J-0.004
ves-0.004
ia-0.004
Jen-0.004
 Jen-0.003
Token,
Token ID11
Feature activation-1.25e-02

Pos logit contributions
J+0.064
ves+0.062
ia+0.060
Jen+0.059
 Lia+0.057
Neg logit contributions
 lately-0.037
ivering-0.036
ishly-0.032
ening-0.031
 asleep-0.030
Token he
Token ID339
Feature activation+1.55e-03

Pos logit contributions
 lately+0.018
ivering+0.017
 asleep+0.016
ishly+0.016
 unatt+0.015
Neg logit contributions
J-0.023
ia-0.023
ves-0.022
Jen-0.021
ila-0.020
Token went
Token ID1816
Feature activation-3.09e-03

Pos logit contributions
J+0.003
 Jen+0.002
Jen+0.002
ia+0.002
 Lia+0.002
Neg logit contributions
ivering-0.002
 lately-0.002
 asleep-0.002
 streaming-0.002
 about-0.002
Token to
Token ID284
Feature activation+6.52e-03

Pos logit contributions
ivering+0.006
 lately+0.005
ishly+0.005
ening+0.005
 asleep+0.005
Neg logit contributions
J-0.005
ves-0.005
ia-0.004
Jen-0.004
 Jen-0.004
Token.
Token ID13
Feature activation-2.33e-02

Pos logit contributions
ivering+0.107
opl+0.099
Charl+0.097
ishly+0.095
 unatt+0.094
Neg logit contributions
 they-0.044
 Jen-0.038
J-0.037
 two-0.036
ia-0.034
Token He
Token ID679
Feature activation-2.22e-03

Pos logit contributions
ivering+0.046
ening+0.039
ishly+0.038
 unatt+0.038
 lately+0.038
Neg logit contributions
J-0.035
 Jen-0.033
Jen-0.033
ia-0.032
 Lia-0.031
Token ran
Token ID4966
Feature activation+6.36e-03

Pos logit contributions
ivering+0.005
 lately+0.004
 unatt+0.004
 asleep+0.004
ening+0.004
Neg logit contributions
J-0.003
ves-0.003
ia-0.002
 Jen-0.002
Jen-0.002
Token and
Token ID290
Feature activation-1.83e-02

Pos logit contributions
J+0.010
 Jen+0.010
 Lia+0.009
Jen+0.009
ia+0.009
Neg logit contributions
ivering-0.012
 lately-0.010
istent-0.010
ening-0.010
opl-0.010
Token ran
Token ID4966
Feature activation+1.81e-02

Pos logit contributions
ivering+0.042
 lately+0.038
ishly+0.037
ening+0.037
 asleep+0.037
Neg logit contributions
J-0.020
ves-0.018
ia-0.018
 Jen-0.018
Jen-0.018
Token,
Token ID11
Feature activation-8.65e-03

Pos logit contributions
J+0.027
 Jen+0.026
ves+0.025
 Lia+0.025
ia+0.025
Neg logit contributions
ivering-0.035
 lately-0.029
ening-0.029
ishly-0.028
istent-0.028
Token trying
Token ID2111
Feature activation+2.31e-02

Pos logit contributions
ivering+0.016
 lately+0.014
ening+0.013
 unatt+0.013
 asleep+0.013
Neg logit contributions
J-0.013
 Jen-0.012
ves-0.012
Jen-0.012
 Lia-0.012
Token to
Token ID284
Feature activation-1.27e-02

Pos logit contributions
J+0.027
ves+0.026
 Jen+0.025
ia+0.024
 Lia+0.023
Neg logit contributions
ivering-0.054
ishly-0.045
 lately-0.045
 unatt-0.044
ening-0.044
Token get
Token ID651
Feature activation+6.34e-05

Pos logit contributions
ivering+0.024
ishly+0.021
pping+0.021
 unatt+0.021
 asleep+0.021
Neg logit contributions
J-0.018
ves-0.018
ia-0.017
Jen-0.016
 Jen-0.016
Token it
Token ID340
Feature activation-1.45e-02

Pos logit contributions
J+0.000
 Jen+0.000
ves+0.000
Jen+0.000
ia+0.000
Neg logit contributions
ivering-0.000
 lately-0.000
ishly-0.000
ening-0.000
 asleep-0.000
Token back
Token ID736
Feature activation-4.07e-04

Pos logit contributions
ivering+0.024
 lately+0.021
ishly+0.020
ening+0.020
 asleep+0.020
Neg logit contributions
J-0.024
ves-0.023
ia-0.023
 Jen-0.023
Jen-0.023
TokenHer
Token ID9360
Feature activation-1.29e-03

Pos logit contributions
 Jen+0.004
 Lia+0.004
ia+0.004
ves+0.004
 tad+0.004
Neg logit contributions
ivering-0.005
Charl-0.005
ishly-0.005
 lately-0.004
pping-0.004
Token brother
Token ID3956
Feature activation-1.74e-02

Pos logit contributions
ivering+0.002
 asleep+0.002
 lately+0.002
 weeping+0.002
ening+0.002
Neg logit contributions
Jen-0.002
ves-0.002
J-0.002
Dan-0.002
 Lia-0.002
Token agreed
Token ID4987
Feature activation+1.04e-02

Pos logit contributions
ivering+0.037
 lately+0.032
 unatt+0.032
 asleep+0.032
ening+0.031
Neg logit contributions
J-0.023
ia-0.021
 Jen-0.021
ves-0.021
Jen-0.020
Token and
Token ID290
Feature activation-1.33e-02

Pos logit contributions
J+0.016
ves+0.015
ia+0.015
 Jen+0.015
Jen+0.015
Neg logit contributions
ivering-0.019
 lately-0.016
 asleep-0.016
ening-0.016
ishly-0.016
Token they
Token ID484
Feature activation-1.07e-02

Pos logit contributions
ivering+0.030
ishly+0.030
 lately+0.028
 asleep+0.028
 streaming+0.027
Neg logit contributions
J-0.013
ves-0.012
ia-0.012
Jen-0.012
Land-0.010
Token had
Token ID550
Feature activation-9.63e-03

Pos logit contributions
ivering+0.019
 lately+0.016
ishly+0.016
ening+0.016
 asleep+0.016
Neg logit contributions
J-0.017
ves-0.016
ia-0.016
Jen-0.016
 Jen-0.016
Token lots
Token ID6041
Feature activation-1.26e-02

Pos logit contributions
ivering+0.018
 lately+0.017
 asleep+0.017
 about+0.016
pping+0.016
Neg logit contributions
Jen-0.012
J-0.012
ves-0.012
ia-0.012
 Lia-0.012
Token of
Token ID286
Feature activation+1.87e-02

Pos logit contributions
ivering+0.025
 lately+0.022
ishly+0.022
ening+0.022
 asleep+0.022
Neg logit contributions
J-0.017
ves-0.016
ia-0.016
 Jen-0.016
Jen-0.016
Token fun
Token ID1257
Feature activation+1.29e-02

Pos logit contributions
J+0.023
ves+0.021
ia+0.021
Jen+0.021
 Jen+0.020
Neg logit contributions
ivering-0.040
 lately-0.035
 asleep-0.035
ening-0.035
ishly-0.035
Token playing
Token ID2712
Feature activation+1.48e-02

Pos logit contributions
J+0.023
ves+0.022
ia+0.021
Jen+0.021
 Jen+0.021
Neg logit contributions
ivering-0.021
 lately-0.018
ening-0.017
ishly-0.017
 asleep-0.017
Token together
Token ID1978
Feature activation+3.96e-02

Pos logit contributions
J+0.023
ia+0.022
Jen+0.022
ves+0.021
 Jen+0.021
Neg logit contributions
ivering-0.026
 lately-0.023
 asleep-0.023
ishly-0.023
ening-0.022
Token could
Token ID714
Feature activation+2.28e-02

Pos logit contributions
J+0.001
ves+0.001
 rods+0.001
Dan+0.001
 tad+0.001
Neg logit contributions
ivering-0.001
 asleep-0.001
 unatt-0.001
opl-0.001
 anymore-0.001
Token.
Token ID13
Feature activation+1.38e-04

Pos logit contributions
J+0.035
ves+0.032
Jen+0.031
ia+0.030
 Lia+0.030
Neg logit contributions
ivering-0.040
 asleep-0.036
 lately-0.036
 anymore-0.035
 unatt-0.034
Token One
Token ID1881
Feature activation+3.51e-02

Pos logit contributions
J+0.000
ves+0.000
ia+0.000
Jen+0.000
 Jen+0.000
Neg logit contributions
ivering-0.000
 lately-0.000
 asleep-0.000
ishly-0.000
ening-0.000
Token day
Token ID1110
Feature activation+1.12e-03

Pos logit contributions
J+0.057
ves+0.054
 Lia+0.050
Ar+0.049
Jen+0.048
Neg logit contributions
ivering-0.060
 lately-0.056
 about-0.051
 asleep-0.051
ening-0.050
Token,
Token ID11
Feature activation-1.18e-02

Pos logit contributions
J+0.002
ves+0.002
ia+0.002
Jen+0.002
 Jen+0.002
Neg logit contributions
ivering-0.002
 lately-0.001
 asleep-0.001
ishly-0.001
ening-0.001
Token she
Token ID673
Feature activation-1.50e-02

Pos logit contributions
 lately+0.018
 asleep+0.017
ivering+0.017
 anymore+0.016
 unatt+0.016
Neg logit contributions
ves-0.020
ia-0.020
Jen-0.019
Ar-0.019
J-0.019
Token saw
Token ID2497
Feature activation+2.26e-02

Pos logit contributions
ivering+0.024
 lately+0.021
 asleep+0.021
 unatt+0.021
ening+0.020
Neg logit contributions
ves-0.024
J-0.023
 Lia-0.022
ia-0.022
Jen-0.022
Token a
Token ID257
Feature activation+1.40e-02

Pos logit contributions
ves+0.027
J+0.026
ia+0.026
Jen+0.024
Ar+0.023
Neg logit contributions
ivering-0.045
 lately-0.043
 asleep-0.042
 unatt-0.041
ishly-0.040
Token big
Token ID1263
Feature activation-9.47e-03

Pos logit contributions
J+0.014
ves+0.013
ia+0.013
Jen+0.012
 Jen+0.012
Neg logit contributions
ivering-0.033
 lately-0.029
 asleep-0.029
ening-0.029
ishly-0.029
Token hill
Token ID12788
Feature activation-9.24e-03

Pos logit contributions
ivering+0.023
pping+0.021
 lately+0.021
ishly+0.021
istent+0.021
Neg logit contributions
 Jen-0.009
 flag-0.009
ia-0.008
J-0.008
Jen-0.008
Token with
Token ID351
Feature activation+2.74e-02

Pos logit contributions
ivering+0.018
ishly+0.016
 asleep+0.016
 lately+0.016
ening+0.016
Neg logit contributions
J-0.013
ia-0.012
ves-0.012
Jen-0.012
 Jen-0.012
Token slipped
Token ID18859
Feature activation-2.63e-02

Pos logit contributions
ivering+0.035
 lately+0.031
ishly+0.031
ening+0.030
 asleep+0.030
Neg logit contributions
J-0.025
ves-0.024
ia-0.023
Jen-0.023
 Jen-0.023
Token out
Token ID503
Feature activation-5.40e-03

Pos logit contributions
ivering+0.054
 lately+0.047
ishly+0.045
 unatt+0.045
opl+0.044
Neg logit contributions
J-0.034
 Jen-0.032
Jen-0.032
ves-0.031
 second-0.031
Token of
Token ID286
Feature activation-1.76e-02

Pos logit contributions
ivering+0.008
 asleep+0.007
ening+0.007
 streaming+0.007
 lately+0.007
Neg logit contributions
ves-0.010
J-0.010
ia-0.009
 Lia-0.009
Jen-0.009
Token Jane
Token ID12091
Feature activation+1.28e-02

Pos logit contributions
ivering+0.035
 lately+0.031
ishly+0.031
ening+0.031
 asleep+0.031
Neg logit contributions
J-0.024
ves-0.023
ia-0.022
Jen-0.022
 Jen-0.022
Token's
Token ID338
Feature activation-1.49e-02

Pos logit contributions
J+0.016
ves+0.015
ia+0.015
 Jen+0.015
Jen+0.014
Neg logit contributions
ivering-0.026
 lately-0.024
ishly-0.023
 unatt-0.022
 asleep-0.022
Token hands
Token ID2832
Feature activation-5.33e-02

Pos logit contributions
ivering+0.034
 lately+0.031
ishly+0.030
ening+0.030
 asleep+0.030
Neg logit contributions
J-0.016
ves-0.015
ia-0.015
 Jen-0.014
Jen-0.014
Token and
Token ID290
Feature activation-1.60e-02

Pos logit contributions
ivering+0.105
 lately+0.093
ishly+0.089
 unatt+0.088
ening+0.087
Neg logit contributions
J-0.072
ves-0.068
 Jen-0.066
ia-0.065
Jen-0.064
Token fell
Token ID3214
Feature activation-1.94e-02

Pos logit contributions
ivering+0.034
 lately+0.030
ishly+0.030
ening+0.029
 asleep+0.029
Neg logit contributions
J-0.020
ves-0.019
 Jen-0.018
ia-0.018
Jen-0.018
Token to
Token ID284
Feature activation+3.05e-03

Pos logit contributions
ivering+0.035
 lately+0.032
ishly+0.031
opl+0.030
 impact+0.030
Neg logit contributions
J-0.028
 Jen-0.028
 two-0.027
Jen-0.026
 second-0.026
Token the
Token ID262
Feature activation-1.24e-02

Pos logit contributions
J+0.005
ves+0.005
ia+0.005
Jen+0.005
Ar+0.004
Neg logit contributions
ivering-0.005
 asleep-0.004
ishly-0.004
ening-0.004
 unatt-0.004
Token ground
Token ID2323
Feature activation-3.27e-03

Pos logit contributions
ivering+0.023
 lately+0.020
ishly+0.020
ening+0.020
 asleep+0.020
Neg logit contributions
J-0.018
ves-0.018
ia-0.017
Jen-0.017
 Jen-0.017
Token.
Token ID13
Feature activation-2.43e-03

Pos logit contributions
ivering+0.032
 lately+0.028
ishly+0.028
 asleep+0.027
ening+0.026
Neg logit contributions
J-0.028
ves-0.026
ia-0.026
 Lia-0.025
Jen-0.025
Token
Token ID220
Feature activation-1.68e-02

Pos logit contributions
ivering+0.004
 lately+0.004
 asleep+0.003
ishly+0.003
ening+0.003
Neg logit contributions
ves-0.004
J-0.004
ia-0.004
Jen-0.004
 Lia-0.003
Token
Token ID198
Feature activation+8.29e-04

Pos logit contributions
ivering+0.030
 asleep+0.027
 lately+0.026
ishly+0.026
pping+0.025
Neg logit contributions
J-0.025
ves-0.024
ia-0.023
Jen-0.022
 flag-0.021
Token
Token ID198
Feature activation-2.88e-03

Pos logit contributions
ves+0.001
ia+0.001
 flag+0.001
J+0.001
 Jen+0.001
Neg logit contributions
ivering-0.001
 asleep-0.001
 lately-0.001
Charl-0.001
ishly-0.001
TokenM
Token ID44
Feature activation-1.59e-02

Pos logit contributions
ivering+0.006
 lately+0.005
Charl+0.005
pping+0.005
 asleep+0.005
Neg logit contributions
ia-0.003
ves-0.003
 Jen-0.003
 Lia-0.003
J-0.003
Tokenummy
Token ID13513
Feature activation-4.41e-02

Pos logit contributions
ivering+0.026
 lately+0.022
 asleep+0.021
ening+0.020
ishly+0.020
Neg logit contributions
J-0.028
ves-0.027
Jen-0.025
 Lia-0.025
 Jen-0.025
Token agreed
Token ID4987
Feature activation+1.40e-02

Pos logit contributions
ivering+0.084
 lately+0.074
ishly+0.073
 asleep+0.072
ening+0.072
Neg logit contributions
J-0.063
ves-0.060
Jen-0.058
ia-0.057
 Jen-0.057
Token it
Token ID340
Feature activation-1.18e-02

Pos logit contributions
J+0.023
ves+0.022
ia+0.022
Jen+0.021
 Jen+0.021
Neg logit contributions
ivering-0.024
 lately-0.021
ishly-0.020
ening-0.020
 asleep-0.020
Token was
Token ID373
Feature activation+9.51e-03

Pos logit contributions
ivering+0.024
 lately+0.022
 asleep+0.021
ishly+0.021
ening+0.021
Neg logit contributions
J-0.015
ves-0.015
ia-0.014
 Jen-0.014
Jen-0.014
Token a
Token ID257
Feature activation+1.54e-02

Pos logit contributions
J+0.013
ves+0.013
ia+0.012
 Jen+0.012
Jen+0.012
Neg logit contributions
ivering-0.019
 lately-0.016
ishly-0.016
ening-0.016
 unatt-0.016
Token very
Token ID845
Feature activation-1.76e-02

Pos logit contributions
J+0.022
ves+0.021
Jen+0.021
ia+0.021
 Jen+0.020
Neg logit contributions
ivering-0.029
 lately-0.026
 asleep-0.025
ishly-0.025
ening-0.025
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
ivering+0.012
 lately+0.011
ishly+0.011
ening+0.011
 asleep+0.011
Neg logit contributions
J-0.007
ia-0.007
ves-0.007
 Jen-0.007
Jen-0.007
Token Benny
Token ID44275
Feature activation-6.11e-03

Pos logit contributions
ivering+0.033
 unatt+0.030
ishly+0.028
ening+0.028
pping+0.028
Neg logit contributions
J-0.020
 Lia-0.020
 two-0.019
 Jen-0.019
 Mia-0.019
Token loved
Token ID6151
Feature activation+6.35e-03

Pos logit contributions
ivering+0.012
 unatt+0.011
ishly+0.011
 asleep+0.010
 lately+0.010
Neg logit contributions
ia-0.009
J-0.009
ves-0.009
Jen-0.008
 Jen-0.008
Token to
Token ID284
Feature activation-6.32e-04

Pos logit contributions
 Jen+0.007
J+0.007
ves+0.006
 other+0.006
ia+0.006
Neg logit contributions
ivering-0.015
ishly-0.013
istent-0.013
 lately-0.013
ening-0.013
Token eat
Token ID4483
Feature activation-1.12e-02

Pos logit contributions
ivering+0.001
 lately+0.001
 asleep+0.001
ishly+0.001
ening+0.001
Neg logit contributions
J-0.001
ves-0.001
ia-0.001
Jen-0.001
 Jen-0.001
Token broccoli
Token ID44653
Feature activation-5.99e-02

Pos logit contributions
ivering+0.026
ishly+0.024
istent+0.023
 lately+0.023
 unatt+0.023
Neg logit contributions
J-0.012
ves-0.012
ia-0.011
 Jen-0.011
 other-0.011
Token,
Token ID11
Feature activation+8.83e-03

Pos logit contributions
ivering+0.125
ening+0.107
istent+0.104
ishly+0.104
 streaming+0.103
Neg logit contributions
ves-0.080
J-0.078
ia-0.078
 they-0.077
 Lia-0.073
Token but
Token ID475
Feature activation-1.18e-02

Pos logit contributions
J+0.014
 Jen+0.014
ves+0.013
 they+0.013
 Lia+0.013
Neg logit contributions
ivering-0.016
ishly-0.014
ening-0.014
 lately-0.013
 unatt-0.013
Token he
Token ID339
Feature activation-1.36e-02

Pos logit contributions
ivering+0.029
ishly+0.025
istent+0.025
ening+0.024
 streaming+0.024
Neg logit contributions
J-0.012
 Lia-0.011
 Jen-0.011
ves-0.011
ia-0.011
Token was
Token ID373
Feature activation-7.14e-03

Pos logit contributions
ivering+0.032
ening+0.029
 asleep+0.029
ishly+0.029
 streaming+0.028
Neg logit contributions
ia-0.015
ves-0.015
J-0.014
 Jen-0.013
Jen-0.013
Token always
Token ID1464
Feature activation+3.23e-03

Pos logit contributions
ivering+0.017
ishly+0.016
ening+0.015
istent+0.015
 unatt+0.015
Neg logit contributions
 two-0.008
 Jen-0.007
 other-0.007
 Mia-0.007
 second-0.007
Token put
Token ID1234
Feature activation-3.28e-02

Pos logit contributions
ivering+0.018
 lately+0.016
ishly+0.016
pping+0.016
ening+0.016
Neg logit contributions
J-0.016
ves-0.015
Jen-0.014
ia-0.014
 Lia-0.014
Token the
Token ID262
Feature activation-1.13e-02

Pos logit contributions
ivering+0.067
 lately+0.058
ishly+0.057
ening+0.056
 unatt+0.056
Neg logit contributions
J-0.045
ves-0.042
 Jen-0.041
ia-0.041
Jen-0.040
Token goodies
Token ID39863
Feature activation-1.14e-02

Pos logit contributions
ivering+0.026
ening+0.023
ishly+0.022
 lately+0.022
pping+0.022
Neg logit contributions
J-0.012
ia-0.011
 second-0.011
 other-0.011
 third-0.011
Token in
Token ID287
Feature activation-8.74e-03

Pos logit contributions
ivering+0.019
 lately+0.016
ening+0.016
ishly+0.016
 asleep+0.015
Neg logit contributions
J-0.019
ves-0.018
 Jen-0.018
ia-0.018
Jen-0.018
Token her
Token ID607
Feature activation-3.27e-03

Pos logit contributions
ivering+0.016
 lately+0.015
 asleep+0.014
ishly+0.014
ening+0.014
Neg logit contributions
J-0.013
ves-0.012
ia-0.012
Jen-0.012
 Jen-0.011
Token basket
Token ID7988
Feature activation-5.66e-02

Pos logit contributions
ivering+0.007
 lately+0.006
ening+0.006
ishly+0.006
pping+0.006
Neg logit contributions
J-0.004
ia-0.004
ves-0.004
 Jen-0.004
 Lia-0.004
Token-
Token ID12
Feature activation+2.55e-02

Pos logit contributions
ivering+0.116
ening+0.101
 lately+0.099
ishly+0.098
 asleep+0.097
Neg logit contributions
J-0.075
ia-0.069
 Jen-0.069
ves-0.068
Jen-0.066
Tokenst
Token ID301
Feature activation+4.76e-03

Pos logit contributions
ia+0.041
J+0.040
 Lia+0.040
ves+0.038
 Jen+0.037
Neg logit contributions
ivering-0.040
 lately-0.037
ening-0.035
ishly-0.034
 unatt-0.034
Tokenomach
Token ID10806
Feature activation-1.10e-02

Pos logit contributions
J+0.007
ves+0.007
ia+0.007
Jen+0.007
 Jen+0.006
Neg logit contributions
ivering-0.009
 lately-0.008
ishly-0.008
ening-0.008
 asleep-0.008
Token.
Token ID13
Feature activation-4.14e-03

Pos logit contributions
ivering+0.017
 lately+0.015
 asleep+0.015
ishly+0.015
 unatt+0.014
Neg logit contributions
J-0.019
ves-0.018
Jen-0.018
ia-0.018
 Lia-0.018
Token But
Token ID887
Feature activation+2.44e-03

Pos logit contributions
ivering+0.005
 lately+0.004
ishly+0.004
 asleep+0.004
ening+0.004
Neg logit contributions
J-0.009
ves-0.009
Jen-0.008
ia-0.008
 Jen-0.008
Token,
Token ID11
Feature activation-1.98e-02

Pos logit contributions
J+0.006
 Jen+0.006
ia+0.006
ves+0.005
Jen+0.005
Neg logit contributions
ivering-0.010
ening-0.008
opl-0.008
 unatt-0.008
ishly-0.008
Token she
Token ID673
Feature activation-2.47e-02

Pos logit contributions
ivering+0.041
 lately+0.036
ishly+0.035
ening+0.035
 asleep+0.035
Neg logit contributions
J-0.027
ves-0.025
ia-0.024
 Jen-0.024
Jen-0.024
Token still
Token ID991
Feature activation-5.66e-03

Pos logit contributions
ivering+0.050
 lately+0.045
ening+0.044
 asleep+0.044
ishly+0.043
Neg logit contributions
J-0.034
ia-0.032
ves-0.031
 Jen-0.030
Jen-0.030
Token missed
Token ID6825
Feature activation-5.45e-03

Pos logit contributions
ivering+0.014
opl+0.012
Charl+0.012
 unatt+0.012
ishly+0.012
Neg logit contributions
 Jen-0.005
ia-0.005
 they-0.004
J-0.004
 Mia-0.004
Token her
Token ID607
Feature activation-2.14e-02

Pos logit contributions
ivering+0.011
 lately+0.009
ishly+0.009
ening+0.009
 unatt+0.009
Neg logit contributions
J-0.007
 Jen-0.007
ves-0.007
ia-0.007
 Lia-0.007
Token rad
Token ID2511
Feature activation-6.58e-02

Pos logit contributions
ivering+0.046
 lately+0.040
ishly+0.039
pping+0.039
ening+0.039
Neg logit contributions
J-0.026
ia-0.025
 Jen-0.024
ves-0.024
Jen-0.023
Tokenish
Token ID680
Feature activation-6.46e-02

Pos logit contributions
ivering+0.098
 lately+0.092
 unatt+0.086
 asleep+0.086
pping+0.083
Neg logit contributions
J-0.108
 Jen-0.108
ia-0.107
Jen-0.106
 two-0.103
Token.
Token ID13
Feature activation-6.92e-03

Pos logit contributions
ivering+0.126
 lately+0.107
ening+0.107
 asleep+0.105
ishly+0.105
Neg logit contributions
ia-0.085
J-0.085
ves-0.083
 Jen-0.082
 other-0.077
Token<|endoftext|>
Token ID50256
Feature activation-4.00e-02

Pos logit contributions
ivering+0.012
 lately+0.010
ening+0.010
 unatt+0.010
ishly+0.010
Neg logit contributions
J-0.012
 Jen-0.011
ia-0.011
Jen-0.011
 Lia-0.011
TokenOnce
Token ID7454
Feature activation-8.46e-03

Pos logit contributions
ivering+0.073
 lately+0.063
ishly+0.062
 asleep+0.062
ening+0.061
Neg logit contributions
J-0.062
ves-0.059
ia-0.058
Jen-0.057
 Jen-0.056
Token upon
Token ID2402
Feature activation-4.09e-03

Pos logit contributions
ivering+0.016
ishly+0.014
 lately+0.014
ening+0.013
 unatt+0.013
Neg logit contributions
J-0.013
ia-0.012
 Jen-0.012
ves-0.012
Jen-0.012
Token
Token ID198
Feature activation+4.64e-03

Pos logit contributions
ves+0.014
 flag+0.014
 tad+0.013
J+0.013
ia+0.013
Neg logit contributions
ivering-0.011
 Playing-0.009
 about-0.009
 lately-0.009
 anymore-0.008
TokenBen
Token ID11696
Feature activation+4.11e-03

Pos logit contributions
ves+0.005
 Jen+0.005
ia+0.005
 flag+0.005
ull+0.005
Neg logit contributions
ivering-0.009
pping-0.008
 lately-0.008
Charl-0.008
 Playing-0.008
Token cried
Token ID16896
Feature activation-1.70e-02

Pos logit contributions
J+0.005
ves+0.005
ia+0.005
Jen+0.004
 Lia+0.004
Neg logit contributions
ivering-0.009
 lately-0.008
ening-0.008
ishly-0.008
 asleep-0.008
Token out
Token ID503
Feature activation-2.38e-02

Pos logit contributions
ivering+0.034
 lately+0.030
ishly+0.029
ening+0.029
 unatt+0.028
Neg logit contributions
J-0.024
ves-0.022
ia-0.022
 Jen-0.022
Jen-0.022
Token in
Token ID287
Feature activation-2.14e-02

Pos logit contributions
ivering+0.041
 asleep+0.035
ening+0.035
 lately+0.035
ishly+0.034
Neg logit contributions
J-0.038
ves-0.037
Jen-0.036
ia-0.035
 Jen-0.034
Token pain
Token ID2356
Feature activation-5.75e-02

Pos logit contributions
ivering+0.036
 lately+0.031
ening+0.030
 asleep+0.030
ishly+0.030
Neg logit contributions
J-0.036
ves-0.035
ia-0.034
Jen-0.033
 Jen-0.033
Token.
Token ID13
Feature activation-1.95e-02

Pos logit contributions
ivering+0.136
ishly+0.123
Charl+0.122
 lately+0.122
 unatt+0.121
Neg logit contributions
J-0.055
ves-0.052
ia-0.052
 Jen-0.049
 two-0.045
Token He
Token ID679
Feature activation+2.89e-03

Pos logit contributions
ivering+0.028
 lately+0.024
 asleep+0.023
ishly+0.023
ening+0.022
Neg logit contributions
J-0.037
ves-0.036
ia-0.034
Jen-0.034
 Jen-0.033
Token let
Token ID1309
Feature activation+1.89e-03

Pos logit contributions
J+0.004
ves+0.004
ia+0.003
Jen+0.003
 Jen+0.003
Neg logit contributions
ivering-0.006
 lately-0.005
ishly-0.005
 asleep-0.005
ening-0.005
Token go
Token ID467
Feature activation+5.50e-03

Pos logit contributions
J+0.003
lan+0.003
ves+0.003
 flags+0.003
 tad+0.003
Neg logit contributions
 anymore-0.003
 about-0.003
ivering-0.003
pping-0.003
 asleep-0.003
Token of
Token ID286
Feature activation-1.11e-02

Pos logit contributions
ves+0.010
J+0.010
ia+0.009
 Lia+0.009
Land+0.009
Neg logit contributions
ivering-0.008
 anymore-0.007
 asleep-0.007
 lately-0.007
 unatt-0.007
Token mom
Token ID1995
Feature activation-2.32e-02

Pos logit contributions
J+0.004
ves+0.004
Jen+0.003
 Lia+0.003
ia+0.003
Neg logit contributions
ivering-0.010
 asleep-0.009
ishly-0.009
 lately-0.009
 unatt-0.009
Tokenmy
Token ID1820
Feature activation-1.09e-02

Pos logit contributions
ivering+0.033
 lately+0.028
ening+0.027
 unatt+0.027
ishly+0.026
Neg logit contributions
J-0.045
 Jen-0.043
Jen-0.043
ia-0.042
ves-0.041
Token put
Token ID1234
Feature activation-3.46e-02

Pos logit contributions
ivering+0.025
 lately+0.022
ening+0.022
ishly+0.022
 asleep+0.022
Neg logit contributions
J-0.012
ves-0.011
ia-0.011
Jen-0.010
 Jen-0.010
Token on
Token ID319
Feature activation-2.38e-02

Pos logit contributions
ivering+0.067
 lately+0.059
ishly+0.058
 asleep+0.058
ening+0.058
Neg logit contributions
J-0.049
ves-0.047
ia-0.046
Jen-0.045
 Jen-0.044
Token their
Token ID511
Feature activation-9.70e-03

Pos logit contributions
ivering+0.051
 lately+0.047
ishly+0.046
 asleep+0.046
ening+0.046
Neg logit contributions
J-0.027
ia-0.026
ves-0.026
Jen-0.025
 Lia-0.024
Token apr
Token ID46593
Feature activation-5.74e-02

Pos logit contributions
ivering+0.016
 unatt+0.014
 asleep+0.014
 lately+0.014
ishly+0.014
Neg logit contributions
J-0.016
Jen-0.016
 Lia-0.015
ia-0.015
ves-0.015
Tokenons
Token ID684
Feature activation-2.48e-02

Pos logit contributions
ivering+0.101
 lately+0.087
ishly+0.084
ening+0.084
 asleep+0.083
Neg logit contributions
J-0.091
ia-0.087
 Lia-0.087
 Jen-0.086
ves-0.085
Token and
Token ID290
Feature activation+1.17e-02

Pos logit contributions
ivering+0.051
 lately+0.044
ening+0.043
ishly+0.043
 unatt+0.042
Neg logit contributions
J-0.033
ves-0.031
ia-0.030
 Jen-0.030
Jen-0.029
Token started
Token ID2067
Feature activation+1.79e-02

Pos logit contributions
ia+0.018
J+0.018
 Lia+0.017
ves+0.016
Jen+0.016
Neg logit contributions
 lately-0.018
 asleep-0.018
ishly-0.017
 streaming-0.017
ivering-0.017
Token cooking
Token ID10801
Feature activation-3.31e-02

Pos logit contributions
J+0.031
ia+0.030
ves+0.029
Jen+0.029
 Lia+0.029
Neg logit contributions
ivering-0.029
 asleep-0.026
 lately-0.025
ening-0.025
ishly-0.024
Token.
Token ID13
Feature activation-2.56e-03

Pos logit contributions
ivering+0.067
 lately+0.059
ishly+0.058
ening+0.057
 asleep+0.057
Neg logit contributions
J-0.045
ves-0.043
ia-0.042
Jen-0.041
 Jen-0.041