TOP ACTIVATIONS
MAX = 0.104

is it , Tom ?" she asked . He
pray for something fun ," they say . Mom
little hedge hog named Harry . Harry loved to explore the
was a bee named Simon . He was a very special
" What is famous ?" she asks . Ben
a little boy named Jason . Every day he would make
was a baby named Gary . He was three years old
a little girl named Alexa . She liked to pretend and
a small dog named Tiny . Tiny loved to play with
c actus , Tom ?" she asks . "
was a turkey named Toby . He was very friendly ,
" What ?" Lily and Max ask . "
" What is that ?" he asks . "
dent ists next time ?" they ask . Mom
lived a boy named Toby . Toby was three years old
a brown dog named Toby . Toby loved to run ,
, Mom ?" Sara and Ben say . "
a meeting . His mum told him ,
a little boy named Simon . He was very lonely because
a small mouse named Tiny . Tiny had a very small

MIN ACTIVATIONS
MIN = -0.105

Lily . She loved ice - cream more than anything in
". They share their ice - cream with Mom and Dad
nodded . He liked ice - cream too , but he
Anna and Ben wanted ice - cream s . They ran
Lily . She loved ice - cream more than anything in
and a merry - go - round . Lily wanted to
. Tim my loved ice - cream and he always asked
The man gives them ice - cream . Tim and Mia
asked . She loved ice - cream , especially chocolate and
she could share her ice - cream with the boy .
. They share their ice - cream . They talk and
." Tim took the ice - cream and started to eat
the rest of the ice - cream and played together .
, " I want ice - cream !" Suddenly , two
, can we have ice - cream , please ?" Tim
all kinds of delicious ice - cream flavors . " Can
ride the merry - go - round . She liked the
to the merry - go - round . They
, Tyler chose the best - looking ice cream , with
Tim . Tim loved ice - cream so much . One

INTERVAL 0.052 - 0.104
CONTAINS 0.251%

a little monkey named Max . Max liked to play in
." said Mom . James took a few small
in named P udd les . P udd les loved to
it . The hunter was sad he didn
But Tom didn 't laugh . He pushed her away

INTERVAL -0.000 - 0.052
CONTAINS 50.351%

to draw with chalk . One day , M andy was
smiled and told him it was okay . She said he
Max said he would listen sometimes and not be mean .
Little boy , the harbor is full of
my heard Lily 's scream and ran to the table .

INTERVAL -0.053 - -0.000
CONTAINS 49.073%

many new things to eat . From that day on ,
. As she walked , she saw a
Once upon a time , there was a big , rough
an orange flower , sweet ie ," Mom my said .
was very sad . Bob 's friend , a

INTERVAL -0.105 - -0.053
CONTAINS 0.324%

named Mia went to the gym with her mom . The
, Be careful when touching the
was playing hide - and - seek with her best friend
wanted to step in the p uddle . S
an idea ! Let â s spin together and
Token is
Token ID318
Feature activation-4.73e-03

Pos logit contributions
 Jason+0.044
 Gary+0.042
oby+0.041
Jason+0.040
 Simon+0.040
Neg logit contributions
mons-0.034
opard-0.030
 badly-0.029
iw-0.026
 bars-0.026
Token it
Token ID340
Feature activation+2.78e-02

Pos logit contributions
mons+0.008
opard+0.007
aro+0.007
iw+0.007
 badly+0.007
Neg logit contributions
 Jason-0.010
 Gary-0.009
 Martin-0.009
oby-0.009
 Simon-0.009
Token,
Token ID11
Feature activation+6.47e-03

Pos logit contributions
 Jason+0.057
 Gary+0.054
oby+0.053
Jason+0.053
 Martin+0.051
Neg logit contributions
mons-0.045
opard-0.040
 badly-0.038
aro-0.036
iw-0.036
Token Tom
Token ID4186
Feature activation+5.45e-02

Pos logit contributions
 Jason+0.012
 Gary+0.012
oby+0.011
Jason+0.011
 Simon+0.011
Neg logit contributions
mons-0.012
opard-0.011
 badly-0.010
aro-0.010
iw-0.010
Token?"
Token ID1701
Feature activation+3.13e-02

Pos logit contributions
 Gary+0.120
 Jason+0.119
oby+0.117
 Martin+0.114
 Justin+0.114
Neg logit contributions
mons-0.067
opard-0.062
 badly-0.057
iw-0.052
round-0.051
Token she
Token ID673
Feature activation+1.04e-01

Pos logit contributions
 Gary+0.066
oby+0.066
 Jason+0.065
Jason+0.060
 Justin+0.060
Neg logit contributions
mons-0.040
 badly-0.035
iw-0.035
opard-0.034
 cherry-0.034
Token asked
Token ID1965
Feature activation+1.49e-02

Pos logit contributions
oby+0.219
 Gary+0.218
 journals+0.206
ye+0.203
 Jason+0.201
Neg logit contributions
 badly-0.094
mons-0.081
 le-0.077
 pigeon-0.075
 pige-0.075
Token.
Token ID13
Feature activation+9.29e-03

Pos logit contributions
 Jason+0.034
 Gary+0.034
oby+0.032
Jason+0.031
 Simon+0.031
Neg logit contributions
mons-0.020
opard-0.017
 badly-0.017
aro-0.016
iw-0.016
Token
Token ID198
Feature activation+3.87e-03

Pos logit contributions
 Jason+0.020
 Gary+0.019
oby+0.019
Jason+0.018
 Simon+0.018
Neg logit contributions
mons-0.014
opard-0.013
 badly-0.011
aro-0.011
iw-0.011
Token
Token ID198
Feature activation+1.49e-02

Pos logit contributions
 Jason+0.008
 Gary+0.008
oby+0.007
Jason+0.007
 Simon+0.007
Neg logit contributions
mons-0.006
opard-0.006
aro-0.005
 badly-0.005
iw-0.005
TokenHe
Token ID1544
Feature activation+1.12e-02

Pos logit contributions
 Jason+0.026
 Gary+0.026
oby+0.024
 Simon+0.023
 Martin+0.023
Neg logit contributions
mons-0.029
opard-0.027
 badly-0.025
aro-0.024
iw-0.024
Token pray
Token ID12472
Feature activation-7.32e-03

Pos logit contributions
 Jason+0.024
 Gary+0.023
oby+0.022
Jason+0.022
 Simon+0.021
Neg logit contributions
mons-0.020
opard-0.018
 badly-0.017
aro-0.017
iw-0.016
Token for
Token ID329
Feature activation+2.10e-02

Pos logit contributions
mons+0.012
opard+0.011
aro+0.010
iw+0.010
 badly+0.009
Neg logit contributions
 Jason-0.016
 Gary-0.015
oby-0.014
 Simon-0.014
 Martin-0.014
Token something
Token ID1223
Feature activation+1.70e-03

Pos logit contributions
 Jason+0.033
 Gary+0.032
oby+0.031
Jason+0.029
 Simon+0.028
Neg logit contributions
mons-0.042
opard-0.039
 badly-0.038
aro-0.037
iw-0.036
Token fun
Token ID1257
Feature activation+1.04e-02

Pos logit contributions
 Jason+0.003
 Gary+0.003
oby+0.003
Jason+0.003
 Simon+0.003
Neg logit contributions
mons-0.003
opard-0.003
aro-0.002
 badly-0.002
iw-0.002
Token,"
Token ID553
Feature activation+3.35e-02

Pos logit contributions
 Jason+0.024
 Gary+0.024
oby+0.023
Jason+0.022
 Simon+0.022
Neg logit contributions
mons-0.014
opard-0.013
 badly-0.011
aro-0.011
iw-0.011
Token they
Token ID484
Feature activation+1.03e-01

Pos logit contributions
oby+0.073
 Gary+0.071
 Jason+0.070
Jason+0.067
umper+0.066
Neg logit contributions
mons-0.044
 cherry-0.039
 fountain-0.039
 muff-0.038
iw-0.038
Token say
Token ID910
Feature activation+2.45e-02

Pos logit contributions
oby+0.233
Gary+0.212
 avail+0.212
 Gary+0.208
umper+0.205
Neg logit contributions
 bars-0.091
 bench-0.076
 pet-0.074
 Sara-0.072
 muff-0.070
Token.
Token ID13
Feature activation+1.72e-02

Pos logit contributions
 Jason+0.058
 Gary+0.057
oby+0.056
Jason+0.054
 Simon+0.053
Neg logit contributions
mons-0.031
opard-0.026
 badly-0.026
aro-0.023
pre-0.022
Token
Token ID198
Feature activation+1.08e-02

Pos logit contributions
 Jason+0.039
 Gary+0.038
oby+0.037
Jason+0.036
 Simon+0.035
Neg logit contributions
mons-0.023
opard-0.021
 badly-0.018
aro-0.018
iw-0.018
Token
Token ID198
Feature activation+2.32e-02

Pos logit contributions
 Jason+0.024
 Gary+0.023
oby+0.022
 Simon+0.022
Jason+0.022
Neg logit contributions
mons-0.016
opard-0.014
 badly-0.013
aro-0.013
iw-0.013
TokenMom
Token ID29252
Feature activation+3.45e-02

Pos logit contributions
 Jason+0.046
 Gary+0.046
oby+0.043
 Simon+0.042
 Martin+0.041
Neg logit contributions
mons-0.038
opard-0.036
 badly-0.033
iw-0.031
 fountain-0.031
Token little
Token ID1310
Feature activation-5.70e-03

Pos logit contributions
mons+0.017
opard+0.015
aro+0.015
 badly+0.014
iw+0.014
Neg logit contributions
 Jason-0.014
 Gary-0.013
oby-0.013
Jason-0.012
 Simon-0.012
Token hedge
Token ID19859
Feature activation-5.11e-02

Pos logit contributions
mons+0.012
opard+0.011
aro+0.010
 badly+0.010
iw+0.010
Neg logit contributions
 Jason-0.010
 Gary-0.009
oby-0.008
 Simon-0.008
 Martin-0.008
Tokenhog
Token ID31897
Feature activation-5.44e-02

Pos logit contributions
mons+0.092
iw+0.072
opard+0.071
har+0.071
drops+0.070
Neg logit contributions
 Gary-0.090
 Jason-0.086
oby-0.085
 Peter-0.082
 Simon-0.081
Token named
Token ID3706
Feature activation+1.30e-02

Pos logit contributions
mons+0.105
drops+0.086
opard+0.079
iw+0.077
ears+0.077
Neg logit contributions
 Gary-0.097
 Jason-0.094
oby-0.089
 Simon-0.087
 Harry-0.087
Token Harry
Token ID5850
Feature activation+2.19e-02

Pos logit contributions
 Jason+0.024
 Gary+0.022
Jason+0.022
oby+0.022
 Simon+0.021
Neg logit contributions
mons-0.024
opard-0.022
aro-0.021
 badly-0.020
iw-0.020
Token.
Token ID13
Feature activation+1.01e-01

Pos logit contributions
 Jason+0.053
 Gary+0.050
Jason+0.049
oby+0.048
 Martin+0.047
Neg logit contributions
mons-0.027
opard-0.025
 badly-0.022
aro-0.022
iw-0.021
Token Harry
Token ID5850
Feature activation-4.93e-03

Pos logit contributions
 lull+0.105
Jason+0.094
 Jason+0.091
 Deal+0.090
ilo+0.089
Neg logit contributions
mons-0.197
opard-0.190
app-0.167
 But-0.166
 Sy-0.165
Token loved
Token ID6151
Feature activation+1.81e-02

Pos logit contributions
mons+0.008
opard+0.007
aro+0.007
iw+0.007
 badly+0.006
Neg logit contributions
 Jason-0.010
 Gary-0.010
oby-0.009
 Martin-0.009
 Simon-0.009
Token to
Token ID284
Feature activation+1.22e-02

Pos logit contributions
 Jason+0.050
Jason+0.047
 Gary+0.047
oby+0.046
 Martin+0.045
Neg logit contributions
mons-0.019
opard-0.015
aro-0.013
iw-0.013
 badly-0.013
Token explore
Token ID7301
Feature activation+2.27e-02

Pos logit contributions
 Jason+0.023
 Gary+0.022
oby+0.021
Jason+0.021
 Martin+0.020
Neg logit contributions
mons-0.022
opard-0.020
aro-0.019
 badly-0.019
iw-0.018
Token the
Token ID262
Feature activation+3.01e-02

Pos logit contributions
 Jason+0.052
 Gary+0.048
Jason+0.048
oby+0.047
 Justin+0.046
Neg logit contributions
mons-0.031
opard-0.027
 badly-0.027
aro-0.026
 bars-0.025
Token was
Token ID373
Feature activation+1.01e-02

Pos logit contributions
mons+0.011
opard+0.009
aro+0.008
iw+0.008
 badly+0.008
Neg logit contributions
 Jason-0.014
 Gary-0.014
oby-0.013
 Simon-0.013
Jason-0.013
Token a
Token ID257
Feature activation-8.76e-03

Pos logit contributions
 Jason+0.022
 Gary+0.021
oby+0.020
Jason+0.020
 Simon+0.020
Neg logit contributions
mons-0.016
opard-0.014
 badly-0.012
iw-0.012
aro-0.012
Token bee
Token ID20697
Feature activation-2.47e-02

Pos logit contributions
mons+0.018
opard+0.016
aro+0.016
 badly+0.015
iw+0.015
Neg logit contributions
 Jason-0.015
 Gary-0.014
oby-0.013
Jason-0.013
 Simon-0.013
Token named
Token ID3706
Feature activation-1.40e-02

Pos logit contributions
mons+0.040
opard+0.032
iw+0.030
aro+0.030
drops+0.030
Neg logit contributions
 Jason-0.051
 Gary-0.051
oby-0.048
 Simon-0.047
 Martin-0.046
Token Simon
Token ID11288
Feature activation+1.30e-02

Pos logit contributions
mons+0.029
opard+0.027
 badly+0.025
aro+0.025
pre+0.024
Neg logit contributions
 Jason-0.024
 Gary-0.023
 Simon-0.021
 Justin-0.021
 Martin-0.021
Token.
Token ID13
Feature activation+1.00e-01

Pos logit contributions
 Jason+0.030
 Gary+0.029
oby+0.027
Jason+0.027
 Martin+0.027
Neg logit contributions
mons-0.018
opard-0.017
 badly-0.015
aro-0.015
iw-0.014
Token He
Token ID679
Feature activation-1.66e-02

Pos logit contributions
 Deal+0.085
 obstacle+0.083
 forth+0.082
reci+0.081
 respond+0.081
Neg logit contributions
mons-0.167
opard-0.166
 But-0.164
 Whe-0.156
t-0.156
Token was
Token ID373
Feature activation+2.97e-04

Pos logit contributions
mons+0.030
opard+0.026
aro+0.025
iw+0.025
 badly+0.024
Neg logit contributions
 Jason-0.031
 Gary-0.031
oby-0.029
 Martin-0.028
 Simon-0.028
Token a
Token ID257
Feature activation-2.48e-02

Pos logit contributions
 Jason+0.001
 Gary+0.001
oby+0.001
 Simon+0.001
 Martin+0.001
Neg logit contributions
mons-0.000
opard-0.000
aro-0.000
 badly-0.000
iw-0.000
Token very
Token ID845
Feature activation-1.32e-02

Pos logit contributions
mons+0.052
aro+0.045
 bars+0.043
opard+0.043
drops+0.042
Neg logit contributions
 Jason-0.042
 Gary-0.041
 Simon-0.038
 Martin-0.038
 Justin-0.037
Token special
Token ID2041
Feature activation-2.63e-02

Pos logit contributions
mons+0.027
opard+0.023
aro+0.022
 badly+0.022
 bars+0.022
Neg logit contributions
 Jason-0.022
 Gary-0.022
 Simon-0.020
oby-0.020
 Martin-0.020
Token"
Token ID1
Feature activation+1.09e-03

Pos logit contributions
 Jason+0.043
 Gary+0.041
oby+0.038
 Martin+0.038
 Simon+0.038
Neg logit contributions
mons-0.039
opard-0.037
 badly-0.033
iw-0.032
aro-0.032
TokenWhat
Token ID2061
Feature activation+1.99e-02

Pos logit contributions
 Jason+0.002
 Gary+0.002
oby+0.002
Jason+0.002
 Simon+0.002
Neg logit contributions
mons-0.002
opard-0.002
aro-0.002
 badly-0.002
iw-0.002
Token is
Token ID318
Feature activation-7.87e-03

Pos logit contributions
 Jason+0.041
 Gary+0.040
oby+0.038
Jason+0.037
 Martin+0.037
Neg logit contributions
mons-0.032
opard-0.028
 badly-0.026
iw-0.025
 bars-0.025
Token famous
Token ID5863
Feature activation+2.84e-02

Pos logit contributions
mons+0.012
opard+0.011
iw+0.010
 badly+0.009
aro+0.009
Neg logit contributions
 Jason-0.018
 Gary-0.017
 Simon-0.016
oby-0.016
 Martin-0.016
Token?"
Token ID1701
Feature activation+1.60e-02

Pos logit contributions
 Jason+0.057
 Gary+0.054
Jason+0.053
oby+0.052
 Martin+0.051
Neg logit contributions
mons-0.048
opard-0.042
 badly-0.039
aro-0.038
 fountain-0.037
Token she
Token ID673
Feature activation+1.00e-01

Pos logit contributions
 Jason+0.033
 Gary+0.031
oby+0.031
Jason+0.030
 Martin+0.029
Neg logit contributions
mons-0.026
opard-0.023
 badly-0.022
aro-0.021
iw-0.021
Token asks
Token ID7893
Feature activation+1.89e-02

Pos logit contributions
oby+0.193
 Gary+0.183
 Jason+0.181
 journals+0.171
ye+0.171
Neg logit contributions
 bars-0.101
 not-0.097
 bumped-0.096
 swings-0.094
 pe-0.092
Token.
Token ID13
Feature activation+1.65e-03

Pos logit contributions
 Jason+0.043
 Gary+0.042
oby+0.041
Jason+0.040
 Martin+0.039
Neg logit contributions
mons-0.027
opard-0.023
 badly-0.022
aro-0.021
iw-0.020
Token
Token ID198
Feature activation+8.55e-03

Pos logit contributions
 Jason+0.003
 Gary+0.003
oby+0.003
Jason+0.003
 Simon+0.003
Neg logit contributions
mons-0.003
opard-0.003
aro-0.002
 badly-0.002
iw-0.002
Token
Token ID198
Feature activation+1.41e-02

Pos logit contributions
 Jason+0.019
 Gary+0.018
oby+0.017
Jason+0.017
 Simon+0.017
Neg logit contributions
mons-0.013
opard-0.012
aro-0.011
 badly-0.011
iw-0.011
TokenBen
Token ID11696
Feature activation+3.65e-02

Pos logit contributions
 Jason+0.024
 Gary+0.023
oby+0.021
 Simon+0.021
 Martin+0.021
Neg logit contributions
mons-0.029
opard-0.027
 badly-0.025
aro-0.024
iw-0.024
Token a
Token ID257
Feature activation-1.37e-02

Pos logit contributions
 Jason+0.007
 Gary+0.006
oby+0.006
Jason+0.006
 Simon+0.006
Neg logit contributions
mons-0.005
opard-0.005
aro-0.004
 badly-0.004
iw-0.004
Token little
Token ID1310
Feature activation-9.51e-03

Pos logit contributions
mons+0.029
opard+0.026
aro+0.025
 badly+0.024
iw+0.024
Neg logit contributions
 Jason-0.023
 Gary-0.021
Jason-0.020
oby-0.020
 Martin-0.020
Token boy
Token ID2933
Feature activation-3.21e-02

Pos logit contributions
mons+0.020
opard+0.018
aro+0.017
 badly+0.017
iw+0.016
Neg logit contributions
 Jason-0.016
 Gary-0.015
oby-0.014
 Simon-0.013
 Martin-0.013
Token named
Token ID3706
Feature activation+2.22e-02

Pos logit contributions
mons+0.054
drops+0.045
opard+0.045
aro+0.041
round+0.039
Neg logit contributions
 Jason-0.066
 Gary-0.063
oby-0.060
 Simon-0.059
 Harry-0.058
Token Jason
Token ID8982
Feature activation+3.08e-03

Pos logit contributions
 Jason+0.053
 Gary+0.052
oby+0.051
Jason+0.051
 Simon+0.049
Neg logit contributions
mons-0.026
opard-0.022
 badly-0.020
iw-0.019
round-0.019
Token.
Token ID13
Feature activation+9.96e-02

Pos logit contributions
 Jason+0.007
 Gary+0.006
oby+0.006
Jason+0.006
 Simon+0.006
Neg logit contributions
mons-0.005
opard-0.004
aro-0.004
 badly-0.004
iw-0.004
Token Every
Token ID3887
Feature activation+2.42e-02

Pos logit contributions
py+0.137
inda+0.123
iot+0.117
 obstacle+0.111
 respond+0.109
Neg logit contributions
 Whe-0.156
 But-0.150
mons-0.149
-0.146
 favorite-0.145
Token day
Token ID1110
Feature activation+4.40e-02

Pos logit contributions
 Jason+0.042
 Gary+0.039
Jason+0.037
 Martin+0.036
 Simon+0.036
Neg logit contributions
mons-0.048
opard-0.046
 badly-0.042
round-0.040
 cherry-0.040
Token he
Token ID339
Feature activation+4.44e-03

Pos logit contributions
 Gary+0.106
oby+0.103
 Jason+0.101
Jason+0.099
Gary+0.099
Neg logit contributions
mons-0.042
 badly-0.037
opard-0.035
t-0.033
op-0.029
Token would
Token ID561
Feature activation+1.14e-02

Pos logit contributions
 Jason+0.009
 Gary+0.008
oby+0.008
Jason+0.008
 Simon+0.008
Neg logit contributions
mons-0.008
opard-0.007
aro-0.006
 badly-0.006
iw-0.006
Token make
Token ID787
Feature activation+1.95e-02

Pos logit contributions
 Jason+0.021
 Gary+0.020
oby+0.019
Jason+0.019
 Simon+0.019
Neg logit contributions
mons-0.021
opard-0.019
 badly-0.018
aro-0.017
iw-0.017
Token was
Token ID373
Feature activation-1.09e-02

Pos logit contributions
mons+0.074
opard+0.067
drops+0.060
round+0.060
aro+0.060
Neg logit contributions
 Jason-0.065
 Gary-0.060
oby-0.059
 Simon-0.058
 Peter-0.057
Token a
Token ID257
Feature activation-2.96e-02

Pos logit contributions
mons+0.020
opard+0.018
aro+0.017
iw+0.016
drops+0.016
Neg logit contributions
 Jason-0.021
 Gary-0.020
oby-0.019
Jason-0.019
 Martin-0.019
Token baby
Token ID5156
Feature activation-4.18e-02

Pos logit contributions
mons+0.070
aro+0.062
opard+0.058
drops+0.057
 bars+0.057
Neg logit contributions
 Jason-0.044
 Gary-0.041
Jason-0.038
oby-0.037
 Martin-0.037
Token named
Token ID3706
Feature activation-2.05e-02

Pos logit contributions
mons+0.074
opard+0.056
aro+0.056
drops+0.055
har+0.054
Neg logit contributions
 Jason-0.084
 Gary-0.080
 Simon-0.076
oby-0.075
 Harry-0.074
Token Gary
Token ID10936
Feature activation-2.23e-03

Pos logit contributions
mons+0.040
opard+0.036
pre+0.033
aro+0.033
iw+0.033
Neg logit contributions
 Jason-0.039
 Gary-0.037
 Simon-0.034
oby-0.034
 Martin-0.034
Token.
Token ID13
Feature activation+9.83e-02

Pos logit contributions
mons+0.004
opard+0.003
aro+0.003
iw+0.003
 badly+0.003
Neg logit contributions
 Jason-0.005
 Gary-0.004
oby-0.004
 Simon-0.004
 Martin-0.004
Token He
Token ID679
Feature activation-1.19e-02

Pos logit contributions
Jason+0.137
 Jason+0.135
ye+0.129
iful+0.129
iot+0.128
Neg logit contributions
opard-0.145
mons-0.144
 But-0.141
 Whe-0.129
-0.128
Token was
Token ID373
Feature activation-1.37e-02

Pos logit contributions
mons+0.021
opard+0.018
aro+0.017
iw+0.017
 badly+0.016
Neg logit contributions
 Jason-0.024
 Gary-0.023
oby-0.022
 Martin-0.022
Jason-0.022
Token three
Token ID1115
Feature activation-3.31e-02

Pos logit contributions
mons+0.024
opard+0.021
aro+0.019
round+0.018
iw+0.018
Neg logit contributions
 Jason-0.029
 Gary-0.028
 Martin-0.026
 Simon-0.026
oby-0.025
Token years
Token ID812
Feature activation+2.11e-02

Pos logit contributions
mons+0.071
opard+0.063
iw+0.058
pre+0.058
aro+0.057
Neg logit contributions
 Jason-0.052
 Gary-0.048
oby-0.046
Jason-0.044
 Simon-0.044
Token old
Token ID1468
Feature activation-3.33e-02

Pos logit contributions
 Jason+0.042
 Gary+0.041
oby+0.039
Jason+0.038
 Simon+0.037
Neg logit contributions
mons-0.036
opard-0.033
 badly-0.031
aro-0.030
iw-0.030
Token a
Token ID257
Feature activation-1.65e-02

Pos logit contributions
mons+0.009
opard+0.008
aro+0.007
iw+0.007
 badly+0.007
Neg logit contributions
 Jason-0.010
 Gary-0.009
oby-0.009
Jason-0.009
 Martin-0.009
Token little
Token ID1310
Feature activation-1.14e-02

Pos logit contributions
mons+0.036
opard+0.031
aro+0.031
iw+0.029
 badly+0.029
Neg logit contributions
 Jason-0.027
 Gary-0.025
Jason-0.023
oby-0.023
 Martin-0.023
Token girl
Token ID2576
Feature activation-3.52e-02

Pos logit contributions
mons+0.024
opard+0.021
aro+0.021
 badly+0.020
iw+0.020
Neg logit contributions
 Jason-0.019
 Gary-0.018
oby-0.016
 Simon-0.016
 Martin-0.016
Token named
Token ID3706
Feature activation-1.91e-02

Pos logit contributions
mons+0.061
opard+0.051
drops+0.048
aro+0.047
round+0.046
Neg logit contributions
 Jason-0.072
 Gary-0.067
 Emily-0.065
 Simon-0.064
oby-0.063
Token Alexa
Token ID34630
Feature activation-8.94e-03

Pos logit contributions
mons+0.041
opard+0.039
aro+0.037
pre+0.035
 badly+0.035
Neg logit contributions
 Jason-0.031
 Gary-0.029
 Emily-0.028
 Martin-0.026
 Simon-0.026
Token.
Token ID13
Feature activation+9.82e-02

Pos logit contributions
mons+0.016
opard+0.014
aro+0.013
iw+0.013
 badly+0.012
Neg logit contributions
 Jason-0.018
 Gary-0.017
oby-0.017
 Simon-0.016
Jason-0.016
Token She
Token ID1375
Feature activation-2.76e-03

Pos logit contributions
ye+0.197
Jason+0.195
 Jason+0.194
umper+0.194
 avail+0.192
Neg logit contributions
mons-0.085
 Whe-0.070
Because-0.069
iffs-0.068
iw-0.067
Token liked
Token ID8288
Feature activation+4.53e-04

Pos logit contributions
mons+0.004
opard+0.004
aro+0.004
iw+0.004
 badly+0.003
Neg logit contributions
 Jason-0.006
 Gary-0.006
oby-0.006
Jason-0.005
 Martin-0.005
Token to
Token ID284
Feature activation+2.19e-02

Pos logit contributions
 Jason+0.001
 Gary+0.001
oby+0.001
Jason+0.001
 Simon+0.001
Neg logit contributions
mons-0.001
opard-0.001
aro-0.000
 badly-0.000
iw-0.000
Token pretend
Token ID16614
Feature activation-7.43e-03

Pos logit contributions
 Jason+0.044
 Gary+0.042
oby+0.041
Jason+0.040
 Martin+0.039
Neg logit contributions
mons-0.037
opard-0.032
 cherry-0.030
 badly-0.030
 bars-0.029
Token and
Token ID290
Feature activation+1.64e-02

Pos logit contributions
mons+0.012
opard+0.011
iw+0.010
aro+0.010
 badly+0.010
Neg logit contributions
 Jason-0.016
 Gary-0.015
oby-0.014
 Simon-0.014
 Martin-0.014
Token a
Token ID257
Feature activation-2.91e-02

Pos logit contributions
 Jason+0.013
 Gary+0.012
oby+0.012
Jason+0.012
 Simon+0.012
Neg logit contributions
mons-0.009
opard-0.008
 badly-0.008
aro-0.008
iw-0.007
Token small
Token ID1402
Feature activation-3.25e-02

Pos logit contributions
mons+0.066
aro+0.058
opard+0.056
 bars+0.054
drops+0.054
Neg logit contributions
 Jason-0.045
 Gary-0.042
 Martin-0.040
Jason-0.039
 Simon-0.039
Token dog
Token ID3290
Feature activation-3.51e-02

Pos logit contributions
mons+0.070
aro+0.060
opard+0.059
 badly+0.056
drops+0.055
Neg logit contributions
 Jason-0.053
 Gary-0.049
 Martin-0.047
oby-0.046
 Simon-0.046
Token named
Token ID3706
Feature activation+1.25e-02

Pos logit contributions
mons+0.060
opard+0.049
drops+0.048
pre+0.045
iw+0.044
Neg logit contributions
 Jason-0.073
 Gary-0.072
 Martin-0.067
 Emily-0.065
 Simon-0.065
Token Tiny
Token ID20443
Feature activation+1.38e-02

Pos logit contributions
 Jason+0.023
 Gary+0.022
oby+0.021
Jason+0.021
 Simon+0.020
Neg logit contributions
mons-0.023
opard-0.021
 badly-0.019
aro-0.019
iw-0.019
Token.
Token ID13
Feature activation+9.79e-02

Pos logit contributions
 Jason+0.031
 Gary+0.030
oby+0.029
Jason+0.029
 Simon+0.028
Neg logit contributions
mons-0.019
opard-0.018
 badly-0.016
aro-0.016
iw-0.015
Token Tiny
Token ID20443
Feature activation-6.29e-03

Pos logit contributions
lling+0.152
Jason+0.143
 Jason+0.139
oby+0.135
iot+0.132
Neg logit contributions
opard-0.141
mons-0.141
 bars-0.130
 Wh-0.130
gy-0.128
Token loved
Token ID6151
Feature activation+2.19e-02

Pos logit contributions
mons+0.010
opard+0.009
aro+0.008
iw+0.008
 badly+0.008
Neg logit contributions
 Jason-0.013
 Gary-0.013
oby-0.012
 Martin-0.012
 Simon-0.012
Token to
Token ID284
Feature activation+2.45e-02

Pos logit contributions
 Jason+0.061
 Gary+0.057
oby+0.057
Jason+0.057
 Simon+0.056
Neg logit contributions
mons-0.022
opard-0.017
aro-0.014
iw-0.014
 badly-0.014
Token play
Token ID711
Feature activation+1.51e-02

Pos logit contributions
 Jason+0.050
oby+0.047
 Gary+0.046
Jason+0.046
 Simon+0.044
Neg logit contributions
mons-0.040
opard-0.035
aro-0.033
 cherry-0.033
 badly-0.033
Token with
Token ID351
Feature activation+2.73e-02

Pos logit contributions
 Jason+0.039
 Gary+0.037
oby+0.036
Jason+0.036
 Simon+0.036
Neg logit contributions
mons-0.017
opard-0.015
 badly-0.014
aro-0.013
 bars-0.012
Token c
Token ID269
Feature activation-3.42e-02

Pos logit contributions
mons+0.059
opard+0.053
aro+0.049
round+0.049
drops+0.048
Neg logit contributions
 Jason-0.046
 Gary-0.045
 Simon-0.044
oby-0.043
 Martin-0.042
Tokenactus
Token ID34144
Feature activation+1.38e-02

Pos logit contributions
mons+0.053
aro+0.049
opard+0.048
 badly+0.044
 bars+0.043
Neg logit contributions
oby-0.066
 Jason-0.065
 Gary-0.062
ilo-0.059
 Simon-0.059
Token,
Token ID11
Feature activation+3.93e-02

Pos logit contributions
 Jason+0.027
 Gary+0.026
oby+0.025
Jason+0.025
 Simon+0.024
Neg logit contributions
mons-0.024
opard-0.022
 badly-0.021
iw-0.020
aro-0.020
Token Tom
Token ID4186
Feature activation+6.11e-02

Pos logit contributions
 Jason+0.077
oby+0.076
 Gary+0.075
Jason+0.074
 Martin+0.070
Neg logit contributions
mons-0.055
opard-0.050
 badly-0.049
 muff-0.047
 cherry-0.046
Token?"
Token ID1701
Feature activation+2.26e-02

Pos logit contributions
 Jason+0.147
 Gary+0.146
oby+0.145
 Martin+0.144
 Simon+0.144
Neg logit contributions
 badly-0.055
mons-0.050
opard-0.046
iw-0.042
 cherry-0.041
Token she
Token ID673
Feature activation+9.76e-02

Pos logit contributions
 Jason+0.048
 Gary+0.047
oby+0.046
Jason+0.044
 Simon+0.044
Neg logit contributions
mons-0.033
opard-0.029
 badly-0.028
iw-0.027
aro-0.027
Token asks
Token ID7893
Feature activation+2.64e-02

Pos logit contributions
oby+0.202
Harry+0.182
 journals+0.182
 Jason+0.182
 Gary+0.181
Neg logit contributions
 Sara-0.102
 le-0.100
 bars-0.092
 bumped-0.088
mons-0.086
Token.
Token ID13
Feature activation+4.74e-03

Pos logit contributions
 Gary+0.057
 Jason+0.056
oby+0.055
Jason+0.053
 Simon+0.052
Neg logit contributions
mons-0.037
 badly-0.032
opard-0.031
aro-0.028
iw-0.028
Token
Token ID198
Feature activation+1.20e-02

Pos logit contributions
 Jason+0.010
 Gary+0.009
oby+0.009
Jason+0.009
 Simon+0.009
Neg logit contributions
mons-0.008
opard-0.007
aro-0.007
 badly-0.006
iw-0.006
Token
Token ID198
Feature activation+2.49e-02

Pos logit contributions
 Jason+0.026
 Gary+0.025
oby+0.024
 Simon+0.024
Jason+0.024
Neg logit contributions
mons-0.018
opard-0.016
aro-0.014
 badly-0.014
iw-0.014
Token"
Token ID1
Feature activation-8.87e-03

Pos logit contributions
 Jason+0.051
 Gary+0.050
oby+0.048
 Simon+0.047
 Martin+0.046
Neg logit contributions
mons-0.040
opard-0.037
 badly-0.033
round-0.032
iw-0.031
Token was
Token ID373
Feature activation+6.42e-03

Pos logit contributions
mons+0.015
opard+0.013
aro+0.012
iw+0.012
drops+0.012
Neg logit contributions
 Jason-0.019
 Gary-0.018
oby-0.018
 Simon-0.017
 Martin-0.017
Token a
Token ID257
Feature activation-1.12e-02

Pos logit contributions
 Jason+0.014
 Gary+0.013
oby+0.013
Jason+0.013
 Simon+0.012
Neg logit contributions
mons-0.010
opard-0.009
 badly-0.008
aro-0.008
iw-0.008
Token turkey
Token ID26876
Feature activation-1.91e-02

Pos logit contributions
mons+0.024
opard+0.021
aro+0.020
 badly+0.019
iw+0.019
Neg logit contributions
 Jason-0.019
 Gary-0.018
oby-0.016
Jason-0.016
 Simon-0.016
Token named
Token ID3706
Feature activation+1.25e-02

Pos logit contributions
mons+0.027
opard+0.022
drops+0.021
aro+0.020
iw+0.020
Neg logit contributions
 Jason-0.044
 Gary-0.043
oby-0.041
 Simon-0.040
 Martin-0.040
Token Toby
Token ID37578
Feature activation+1.59e-03

Pos logit contributions
 Jason+0.022
 Gary+0.021
oby+0.020
Jason+0.020
 Simon+0.019
Neg logit contributions
mons-0.024
opard-0.022
aro-0.020
iw-0.020
 badly-0.020
Token.
Token ID13
Feature activation+9.76e-02

Pos logit contributions
 Jason+0.003
 Gary+0.003
oby+0.003
Jason+0.003
 Simon+0.003
Neg logit contributions
mons-0.003
opard-0.002
aro-0.002
iw-0.002
 badly-0.002
Token He
Token ID679
Feature activation-1.45e-02

Pos logit contributions
father+0.106
py+0.104
iot+0.104
Beck+0.103
Jason+0.101
Neg logit contributions
 Whe-0.166
mons-0.159
 But-0.152
t-0.149
-0.148
Token was
Token ID373
Feature activation+1.67e-03

Pos logit contributions
mons+0.027
opard+0.024
aro+0.023
iw+0.023
drops+0.022
Neg logit contributions
 Jason-0.027
 Gary-0.026
oby-0.024
 Martin-0.024
 Simon-0.024
Token very
Token ID845
Feature activation-4.31e-04

Pos logit contributions
 Jason+0.004
 Gary+0.004
oby+0.004
 Simon+0.004
Jason+0.004
Neg logit contributions
mons-0.002
opard-0.002
aro-0.002
 badly-0.002
iw-0.002
Token friendly
Token ID8030
Feature activation-7.04e-03

Pos logit contributions
mons+0.001
opard+0.001
aro+0.001
 badly+0.001
iw+0.001
Neg logit contributions
 Jason-0.001
 Gary-0.001
oby-0.001
 Simon-0.001
Jason-0.001
Token,
Token ID11
Feature activation-2.55e-02

Pos logit contributions
mons+0.012
opard+0.011
aro+0.010
iw+0.009
 badly+0.009
Neg logit contributions
 Jason-0.015
 Gary-0.014
oby-0.014
 Simon-0.013
 Martin-0.013
Token"
Token ID1
Feature activation-1.07e-02

Pos logit contributions
 Jason+0.044
 Gary+0.042
oby+0.040
 Simon+0.040
 Martin+0.039
Neg logit contributions
mons-0.037
opard-0.034
 badly-0.031
iw-0.030
aro-0.030
TokenWhat
Token ID2061
Feature activation+1.91e-02

Pos logit contributions
mons+0.018
opard+0.016
 badly+0.015
aro+0.015
iw+0.015
Neg logit contributions
 Jason-0.021
 Gary-0.021
oby-0.020
Jason-0.020
 Simon-0.019
Token?"
Token ID1701
Feature activation+2.25e-02

Pos logit contributions
 Jason+0.040
 Gary+0.039
oby+0.038
Jason+0.037
 Simon+0.037
Neg logit contributions
mons-0.030
opard-0.027
 badly-0.025
iw-0.023
aro-0.023
Token Lily
Token ID20037
Feature activation+8.10e-02

Pos logit contributions
 Jason+0.043
oby+0.042
 Gary+0.041
Jason+0.040
 Simon+0.039
Neg logit contributions
mons-0.037
opard-0.033
 badly-0.032
aro-0.031
iw-0.031
Token and
Token ID290
Feature activation+4.77e-02

Pos logit contributions
 Jason+0.142
oby+0.140
 Gary+0.139
ye+0.138
Jason+0.132
Neg logit contributions
mons-0.110
 bars-0.104
 badly-0.095
 pige-0.095
opard-0.094
Token Max
Token ID5436
Feature activation+9.75e-02

Pos logit contributions
oby+0.084
 Jason+0.075
ye+0.075
Jason+0.075
 Simon+0.074
Neg logit contributions
mons-0.082
 bars-0.075
opard-0.072
 Sy-0.070
 badly-0.070
Token ask
Token ID1265
Feature activation+1.96e-02

Pos logit contributions
oby+0.193
 Jason+0.182
 Gary+0.179
ye+0.175
Jason+0.174
Neg logit contributions
 bars-0.103
 fountain-0.097
mons-0.096
 slide-0.095
drops-0.094
Token.
Token ID13
Feature activation+7.14e-03

Pos logit contributions
 Jason+0.046
 Gary+0.045
oby+0.044
Jason+0.043
 Martin+0.042
Neg logit contributions
mons-0.026
opard-0.022
 badly-0.021
aro-0.020
 bars-0.019
Token
Token ID198
Feature activation+1.74e-02

Pos logit contributions
 Jason+0.015
 Gary+0.015
oby+0.014
Jason+0.014
 Simon+0.014
Neg logit contributions
mons-0.011
opard-0.010
 badly-0.009
aro-0.009
iw-0.009
Token
Token ID198
Feature activation+3.37e-02

Pos logit contributions
 Jason+0.040
 Gary+0.038
oby+0.037
 Simon+0.036
 Martin+0.036
Neg logit contributions
mons-0.024
opard-0.021
 badly-0.019
aro-0.019
iw-0.019
Token"
Token ID1
Feature activation-1.08e-02

Pos logit contributions
 Jason+0.072
 Gary+0.068
 Simon+0.066
oby+0.066
 Justin+0.065
Neg logit contributions
mons-0.051
opard-0.047
 badly-0.044
aro-0.041
 bars-0.040
Token"
Token ID1
Feature activation+2.28e-02

Pos logit contributions
 Jason+0.077
 Gary+0.077
 Simon+0.072
 Martin+0.071
oby+0.071
Neg logit contributions
mons-0.050
opard-0.049
 badly-0.041
iw-0.041
round-0.040
TokenWhat
Token ID2061
Feature activation+2.65e-02

Pos logit contributions
 Jason+0.048
 Gary+0.046
 Simon+0.043
 Martin+0.042
oby+0.042
Neg logit contributions
mons-0.039
opard-0.035
iw-0.031
pre-0.031
aro-0.030
Token is
Token ID318
Feature activation-3.54e-03

Pos logit contributions
 Jason+0.057
 Gary+0.056
oby+0.054
 Simon+0.052
 Martin+0.052
Neg logit contributions
mons-0.039
opard-0.034
 badly-0.033
 bars-0.030
 cherry-0.030
Token that
Token ID326
Feature activation+2.54e-02

Pos logit contributions
mons+0.005
opard+0.005
iw+0.004
 badly+0.004
aro+0.004
Neg logit contributions
 Jason-0.008
 Gary-0.007
oby-0.007
 Simon-0.007
 Martin-0.007
Token?"
Token ID1701
Feature activation+3.13e-02

Pos logit contributions
 Jason+0.051
 Gary+0.049
oby+0.047
Jason+0.046
 Martin+0.046
Neg logit contributions
mons-0.042
opard-0.039
 badly-0.035
aro-0.033
 fountain-0.033
Token he
Token ID339
Feature activation+9.74e-02

Pos logit contributions
oby+0.066
 Gary+0.064
 Jason+0.064
Jason+0.061
 Martin+0.059
Neg logit contributions
mons-0.041
 badly-0.036
opard-0.036
 cherry-0.035
iw-0.035
Token asks
Token ID7893
Feature activation+2.66e-02

Pos logit contributions
oby+0.190
 Jason+0.178
 Gary+0.175
father+0.174
umper+0.174
Neg logit contributions
 bars-0.099
 le-0.098
 not-0.096
 swings-0.095
mons-0.092
Token.
Token ID13
Feature activation+1.56e-02

Pos logit contributions
 Jason+0.064
 Gary+0.063
oby+0.061
Jason+0.061
 Martin+0.059
Neg logit contributions
mons-0.031
 badly-0.026
opard-0.025
aro-0.024
iw-0.022
Token
Token ID198
Feature activation+9.73e-03

Pos logit contributions
 Jason+0.034
 Gary+0.033
oby+0.032
Jason+0.031
 Simon+0.031
Neg logit contributions
mons-0.023
opard-0.021
 badly-0.018
aro-0.018
iw-0.018
Token
Token ID198
Feature activation+2.72e-02

Pos logit contributions
 Jason+0.021
 Gary+0.021
oby+0.020
Jason+0.019
 Simon+0.019
Neg logit contributions
mons-0.015
opard-0.013
aro-0.012
 badly-0.012
iw-0.012
Token"
Token ID1
Feature activation-1.13e-02

Pos logit contributions
 Jason+0.054
 Gary+0.053
oby+0.051
 Simon+0.049
 Martin+0.049
Neg logit contributions
mons-0.044
opard-0.042
 badly-0.038
iw-0.036
aro-0.036
Token dent
Token ID18794
Feature activation-8.09e-03

Pos logit contributions
 Jason+0.005
 Gary+0.005
oby+0.005
Jason+0.005
 Simon+0.005
Neg logit contributions
mons-0.005
opard-0.004
aro-0.004
 badly-0.004
iw-0.004
Tokenists
Token ID1023
Feature activation+1.15e-02

Pos logit contributions
mons+0.015
opard+0.014
iw+0.013
aro+0.013
 badly+0.012
Neg logit contributions
 Jason-0.015
 Gary-0.014
oby-0.014
Jason-0.013
 Simon-0.013
Token next
Token ID1306
Feature activation+2.63e-02

Pos logit contributions
 Jason+0.025
 Gary+0.024
oby+0.023
Jason+0.022
 Simon+0.022
Neg logit contributions
mons-0.018
opard-0.016
 badly-0.015
aro-0.014
iw-0.014
Token time
Token ID640
Feature activation+1.61e-02

Pos logit contributions
 Jason+0.048
 Gary+0.047
oby+0.043
Jason+0.043
 Simon+0.042
Neg logit contributions
mons-0.048
opard-0.044
 badly-0.042
iw-0.040
 bars-0.040
Token?"
Token ID1701
Feature activation+1.67e-02

Pos logit contributions
 Jason+0.032
 Gary+0.031
oby+0.030
Jason+0.029
 Martin+0.029
Neg logit contributions
mons-0.027
opard-0.024
 badly-0.022
aro-0.022
iw-0.022
Token they
Token ID484
Feature activation+9.69e-02

Pos logit contributions
 Jason+0.037
 Gary+0.036
oby+0.036
Jason+0.034
 Simon+0.033
Neg logit contributions
mons-0.024
opard-0.021
aro-0.020
 badly-0.019
iw-0.019
Token ask
Token ID1265
Feature activation+1.95e-02

Pos logit contributions
oby+0.210
 Gary+0.183
 journals+0.180
ross+0.180
ye+0.179
Neg logit contributions
 Sara-0.098
 bench-0.092
 bars-0.090
 Ell-0.088
 slide-0.087
Token.
Token ID13
Feature activation-1.63e-03

Pos logit contributions
 Jason+0.045
 Gary+0.043
oby+0.042
Jason+0.041
 Simon+0.040
Neg logit contributions
mons-0.027
opard-0.023
 badly-0.022
aro-0.021
iw-0.019
Token
Token ID198
Feature activation+5.63e-03

Pos logit contributions
mons+0.003
opard+0.003
aro+0.002
 badly+0.002
iw+0.002
Neg logit contributions
 Jason-0.003
 Gary-0.003
oby-0.003
Jason-0.003
 Simon-0.003
Token
Token ID198
Feature activation+1.48e-02

Pos logit contributions
 Jason+0.012
 Gary+0.012
oby+0.011
Jason+0.011
 Simon+0.011
Neg logit contributions
mons-0.009
opard-0.008
aro-0.007
 badly-0.007
iw-0.007
TokenMom
Token ID29252
Feature activation+3.05e-02

Pos logit contributions
 Jason+0.027
 Gary+0.026
oby+0.025
 Simon+0.024
 Martin+0.024
Neg logit contributions
mons-0.028
opard-0.026
 badly-0.024
aro-0.024
iw-0.023
Token lived
Token ID5615
Feature activation+1.87e-02

Pos logit contributions
mons+0.013
opard+0.011
aro+0.010
iw+0.010
 badly+0.010
Neg logit contributions
 Jason-0.017
 Gary-0.016
oby-0.016
 Simon-0.015
 Martin-0.015
Token a
Token ID257
Feature activation-1.52e-02

Pos logit contributions
 Jason+0.044
 Gary+0.042
oby+0.041
Jason+0.040
 Simon+0.040
Neg logit contributions
mons-0.026
opard-0.023
 badly-0.020
iw-0.020
aro-0.019
Token boy
Token ID2933
Feature activation-3.61e-02

Pos logit contributions
mons+0.033
opard+0.028
aro+0.028
 badly+0.027
iw+0.027
Neg logit contributions
 Jason-0.025
 Gary-0.024
Jason-0.022
oby-0.022
 Martin-0.022
Token named
Token ID3706
Feature activation+2.11e-02

Pos logit contributions
mons+0.063
drops+0.055
opard+0.053
aro+0.050
har+0.048
Neg logit contributions
 Jason-0.070
 Gary-0.066
oby-0.063
 Emily-0.062
 Harry-0.062
Token Toby
Token ID37578
Feature activation-8.06e-03

Pos logit contributions
 Jason+0.048
 Gary+0.047
Jason+0.046
oby+0.046
 Simon+0.044
Neg logit contributions
mons-0.027
opard-0.024
aro-0.021
iw-0.021
 badly-0.021
Token.
Token ID13
Feature activation+9.67e-02

Pos logit contributions
mons+0.015
opard+0.013
aro+0.012
iw+0.012
drops+0.012
Neg logit contributions
 Jason-0.016
 Gary-0.015
oby-0.015
 Simon-0.014
 Martin-0.014
Token Toby
Token ID37578
Feature activation-3.32e-02

Pos logit contributions
father+0.122
 respond+0.119
Beck+0.119
 Gary+0.118
iot+0.118
Neg logit contributions
 Whe-0.147
mons-0.144
t-0.134
 But-0.133
 favorite-0.132
Token was
Token ID373
Feature activation-2.45e-02

Pos logit contributions
mons+0.063
aro+0.057
opard+0.056
iw+0.055
drops+0.052
Neg logit contributions
 Jason-0.063
 Gary-0.057
oby-0.056
 Martin-0.055
 Simon-0.055
Token three
Token ID1115
Feature activation-3.67e-02

Pos logit contributions
mons+0.048
opard+0.043
aro+0.042
round+0.041
iw+0.039
Neg logit contributions
 Jason-0.046
 Gary-0.044
 Martin-0.040
 Simon-0.040
 Justin-0.039
Token years
Token ID812
Feature activation+2.05e-02

Pos logit contributions
mons+0.080
opard+0.073
aro+0.066
pre+0.066
iw+0.065
Neg logit contributions
 Jason-0.055
 Gary-0.051
oby-0.049
 brothers-0.047
Jason-0.046
Token old
Token ID1468
Feature activation-3.11e-02

Pos logit contributions
 Jason+0.040
 Gary+0.039
oby+0.037
Jason+0.037
 Simon+0.036
Neg logit contributions
mons-0.035
opard-0.033
 badly-0.030
aro-0.030
iw-0.029
Token a
Token ID257
Feature activation-1.87e-02

Pos logit contributions
mons+0.027
opard+0.025
aro+0.024
iw+0.023
drops+0.023
Neg logit contributions
 Jason-0.024
 Gary-0.023
oby-0.021
 Martin-0.021
Jason-0.021
Token brown
Token ID7586
Feature activation-4.59e-02

Pos logit contributions
mons+0.041
aro+0.036
opard+0.036
iw+0.034
drops+0.034
Neg logit contributions
 Jason-0.030
 Gary-0.028
Jason-0.026
 Martin-0.026
 Simon-0.026
Token dog
Token ID3290
Feature activation-4.13e-02

Pos logit contributions
mons+0.090
aro+0.080
iw+0.074
drops+0.073
har+0.072
Neg logit contributions
 Jason-0.079
 Gary-0.075
oby-0.074
 Martin-0.071
 Simon-0.070
Token named
Token ID3706
Feature activation+1.09e-02

Pos logit contributions
mons+0.076
drops+0.062
opard+0.060
iw+0.057
pre+0.057
Neg logit contributions
 Jason-0.079
 Gary-0.079
 Emily-0.072
 Martin-0.072
oby-0.071
Token Toby
Token ID37578
Feature activation-1.29e-02

Pos logit contributions
 Jason+0.019
 Gary+0.018
oby+0.017
Jason+0.017
 Simon+0.016
Neg logit contributions
mons-0.022
opard-0.020
 badly-0.018
aro-0.018
iw-0.018
Token.
Token ID13
Feature activation+9.66e-02

Pos logit contributions
mons+0.025
opard+0.022
iw+0.021
aro+0.020
drops+0.020
Neg logit contributions
 Jason-0.024
 Gary-0.023
oby-0.022
 Simon-0.022
 Martin-0.022
Token Toby
Token ID37578
Feature activation-3.29e-02

Pos logit contributions
iot+0.119
father+0.119
lling+0.116
Beck+0.111
Jason+0.111
Neg logit contributions
 Whe-0.154
mons-0.145
-0.142
t-0.140
 But-0.137
Token loved
Token ID6151
Feature activation+1.82e-02

Pos logit contributions
mons+0.063
aro+0.055
iw+0.054
opard+0.054
drops+0.051
Neg logit contributions
 Jason-0.062
 Gary-0.058
oby-0.056
 Martin-0.056
 Simon-0.055
Token to
Token ID284
Feature activation+1.13e-02

Pos logit contributions
 Jason+0.049
 Gary+0.047
oby+0.046
Jason+0.046
 Simon+0.045
Neg logit contributions
mons-0.019
opard-0.015
aro-0.013
 badly-0.013
iw-0.013
Token run
Token ID1057
Feature activation-2.39e-02

Pos logit contributions
 Jason+0.022
 Gary+0.020
oby+0.020
Jason+0.019
 Simon+0.019
Neg logit contributions
mons-0.021
opard-0.019
aro-0.017
 badly-0.017
iw-0.017
Token,
Token ID11
Feature activation-2.50e-03

Pos logit contributions
mons+0.049
opard+0.044
iw+0.042
pre+0.041
aro+0.040
Neg logit contributions
 Gary-0.041
 Jason-0.041
oby-0.038
 Martin-0.038
 Simon-0.036
Token,
Token ID11
Feature activation+8.90e-03

Pos logit contributions
 Jason+0.036
 Gary+0.035
oby+0.033
 Martin+0.033
 Simon+0.033
Neg logit contributions
mons-0.030
opard-0.026
 badly-0.025
iw-0.023
aro-0.023
Token Mom
Token ID11254
Feature activation+3.72e-02

Pos logit contributions
 Jason+0.017
 Gary+0.016
oby+0.016
Jason+0.015
 Martin+0.015
Neg logit contributions
mons-0.016
opard-0.014
 badly-0.013
aro-0.013
iw-0.013
Token?"
Token ID1701
Feature activation-4.88e-03

Pos logit contributions
 Gary+0.078
 Jason+0.077
oby+0.074
 Martin+0.074
Jason+0.072
Neg logit contributions
mons-0.058
opard-0.049
iw-0.046
 badly-0.045
 fountain-0.043
Token Sara
Token ID24799
Feature activation+5.83e-02

Pos logit contributions
mons+0.005
opard+0.005
aro+0.004
 badly+0.004
iw+0.004
Neg logit contributions
 Jason-0.013
 Gary-0.012
 Simon-0.012
oby-0.012
Jason-0.012
Token and
Token ID290
Feature activation+3.78e-02

Pos logit contributions
 Jason+0.105
 Gary+0.105
oby+0.102
 Martin+0.095
 Simon+0.095
Neg logit contributions
mons-0.089
opard-0.078
 bars-0.077
 badly-0.076
iw-0.075
Token Ben
Token ID3932
Feature activation+9.54e-02

Pos logit contributions
oby+0.063
 Jason+0.058
 Gary+0.057
Jason+0.056
 Martin+0.056
Neg logit contributions
mons-0.073
opard-0.063
iw-0.061
 cherry-0.060
 bars-0.058
Token say
Token ID910
Feature activation+9.78e-03

Pos logit contributions
oby+0.194
 Gary+0.176
 Jason+0.169
ilo+0.166
die+0.165
Neg logit contributions
 fountain-0.106
 bars-0.104
 bench-0.104
mons-0.101
 slide-0.100
Token.
Token ID13
Feature activation+4.47e-03

Pos logit contributions
 Jason+0.022
 Gary+0.021
oby+0.020
Jason+0.020
 Simon+0.020
Neg logit contributions
mons-0.015
opard-0.013
 badly-0.012
aro-0.012
iw-0.011
Token
Token ID198
Feature activation+1.23e-02

Pos logit contributions
 Jason+0.009
 Gary+0.009
oby+0.008
Jason+0.008
 Simon+0.008
Neg logit contributions
mons-0.008
opard-0.007
aro-0.006
 badly-0.006
iw-0.006
Token
Token ID198
Feature activation+1.78e-02

Pos logit contributions
 Jason+0.027
 Gary+0.026
oby+0.025
Jason+0.025
 Simon+0.025
Neg logit contributions
mons-0.018
opard-0.016
 badly-0.015
aro-0.015
iw-0.014
Token"
Token ID1
Feature activation-1.79e-02

Pos logit contributions
 Jason+0.034
 Gary+0.033
oby+0.031
 Simon+0.030
 Martin+0.030
Neg logit contributions
mons-0.033
opard-0.030
 badly-0.028
iw-0.027
aro-0.027
Token a
Token ID257
Feature activation+3.16e-03

Pos logit contributions
 Jason+0.062
 Gary+0.061
oby+0.061
Jason+0.058
 Justin+0.056
Neg logit contributions
mons-0.042
 bars-0.038
 badly-0.037
 cherry-0.037
opard-0.037
Token meeting
Token ID3249
Feature activation-6.80e-03

Pos logit contributions
 Jason+0.006
 Gary+0.005
oby+0.005
Jason+0.005
 Simon+0.005
Neg logit contributions
mons-0.006
opard-0.006
aro-0.005
 badly-0.005
iw-0.005
Token.
Token ID13
Feature activation+6.59e-02

Pos logit contributions
mons+0.011
opard+0.011
iw+0.009
aro+0.009
 badly+0.009
Neg logit contributions
 Jason-0.014
 Gary-0.013
oby-0.013
 Simon-0.012
 Martin-0.012
Token His
Token ID2399
Feature activation-8.08e-03

Pos logit contributions
inda+0.106
ilo+0.105
umper+0.104
Jason+0.103
 Jason+0.102
Neg logit contributions
 But-0.079
round-0.078
mons-0.076
 favorite-0.074
ocular-0.074
Token mum
Token ID25682
Feature activation+5.60e-03

Pos logit contributions
mons+0.015
opard+0.013
aro+0.013
iw+0.013
 badly+0.013
Neg logit contributions
 Jason-0.015
 Gary-0.015
oby-0.014
 Simon-0.014
 Martin-0.013
Token told
Token ID1297
Feature activation+9.54e-02

Pos logit contributions
 Jason+0.010
 Gary+0.009
oby+0.009
Jason+0.009
 Simon+0.009
Neg logit contributions
mons-0.011
opard-0.010
aro-0.009
 badly-0.009
iw-0.009
Token him
Token ID683
Feature activation-2.22e-02

Pos logit contributions
die+0.201
ye+0.193
Gary+0.190
 Deal+0.188
Jason+0.187
Neg logit contributions
 that-0.075
 it-0.074
 badly-0.069
t-0.064
--0.064
Token,
Token ID11
Feature activation+3.07e-03

Pos logit contributions
mons+0.035
opard+0.031
iw+0.030
pre+0.027
drops+0.027
Neg logit contributions
 Jason-0.050
 Gary-0.048
 Simon-0.045
 Martin-0.045
oby-0.045
Token
Token ID6184
Feature activation-8.44e-03

Pos logit contributions
 Jason+0.006
 Gary+0.006
oby+0.006
Jason+0.006
 Simon+0.005
Neg logit contributions
mons-0.005
opard-0.005
aro-0.004
 badly-0.004
iw-0.004
Token
Token ID95
Feature activation+3.64e-03

Pos logit contributions
mons+0.016
opard+0.015
aro+0.014
 badly+0.014
iw+0.013
Neg logit contributions
 Jason-0.016
 Gary-0.015
oby-0.014
Jason-0.014
 Simon-0.014
Token
Token ID26391
Feature activation-2.51e-02

Pos logit contributions
 Jason+0.007
 Gary+0.007
oby+0.006
Jason+0.006
 Simon+0.006
Neg logit contributions
mons-0.007
opard-0.006
aro-0.005
 badly-0.005
iw-0.005
Token a
Token ID257
Feature activation-1.18e-02

Pos logit contributions
 Jason+0.013
 Gary+0.012
oby+0.012
Jason+0.011
 Simon+0.011
Neg logit contributions
mons-0.009
opard-0.008
 badly-0.007
aro-0.007
iw-0.007
Token little
Token ID1310
Feature activation-1.13e-02

Pos logit contributions
mons+0.025
opard+0.022
aro+0.022
 badly+0.021
iw+0.021
Neg logit contributions
 Jason-0.020
 Gary-0.019
oby-0.017
Jason-0.017
 Martin-0.017
Token boy
Token ID2933
Feature activation-3.02e-02

Pos logit contributions
mons+0.024
opard+0.021
aro+0.021
 badly+0.020
iw+0.020
Neg logit contributions
 Jason-0.018
 Gary-0.017
oby-0.016
 Simon-0.016
 Martin-0.016
Token named
Token ID3706
Feature activation+2.49e-02

Pos logit contributions
mons+0.050
opard+0.042
drops+0.041
aro+0.038
round+0.036
Neg logit contributions
 Jason-0.064
 Gary-0.061
oby-0.058
 Simon-0.057
 Harry-0.056
Token Simon
Token ID11288
Feature activation+2.64e-03

Pos logit contributions
 Jason+0.059
 Gary+0.058
Jason+0.058
oby+0.057
 Martin+0.055
Neg logit contributions
mons-0.029
opard-0.024
iw-0.021
round-0.021
 badly-0.021
Token.
Token ID13
Feature activation+9.54e-02

Pos logit contributions
 Jason+0.006
 Gary+0.005
oby+0.005
Jason+0.005
 Simon+0.005
Neg logit contributions
mons-0.004
opard-0.004
aro-0.003
 badly-0.003
iw-0.003
Token He
Token ID679
Feature activation-5.34e-04

Pos logit contributions
py+0.105
 obstacle+0.103
 forth+0.103
reci+0.102
 respond+0.100
Neg logit contributions
mons-0.139
 But-0.137
 Whe-0.137
 favorite-0.135
 Mike-0.133
Token was
Token ID373
Feature activation-1.55e-02

Pos logit contributions
mons+0.001
opard+0.001
aro+0.001
iw+0.001
 badly+0.001
Neg logit contributions
 Jason-0.001
 Gary-0.001
oby-0.001
Jason-0.001
 Simon-0.001
Token very
Token ID845
Feature activation-3.50e-03

Pos logit contributions
mons+0.027
opard+0.024
aro+0.023
round+0.022
iw+0.022
Neg logit contributions
 Jason-0.032
 Gary-0.031
 Martin-0.029
 Simon-0.029
 Justin-0.028
Token lonely
Token ID21757
Feature activation-3.02e-02

Pos logit contributions
mons+0.007
opard+0.006
aro+0.006
 badly+0.006
iw+0.006
Neg logit contributions
 Jason-0.006
 Gary-0.006
oby-0.006
 Simon-0.006
Jason-0.006
Token because
Token ID780
Feature activation+1.69e-02

Pos logit contributions
mons+0.062
opard+0.055
aro+0.054
iw+0.051
pre+0.048
Neg logit contributions
 Jason-0.055
 Gary-0.050
oby-0.049
 Martin-0.047
 Simon-0.047
Token a
Token ID257
Feature activation-1.34e-02

Pos logit contributions
 Jason+0.000
 Gary+0.000
oby+0.000
Jason+0.000
 Simon+0.000
Neg logit contributions
mons-0.000
opard-0.000
aro-0.000
iw-0.000
 badly-0.000
Token small
Token ID1402
Feature activation-1.64e-02

Pos logit contributions
mons+0.029
opard+0.025
aro+0.025
 badly+0.024
iw+0.024
Neg logit contributions
 Jason-0.022
 Gary-0.021
Jason-0.019
oby-0.019
 Martin-0.019
Token mouse
Token ID10211
Feature activation-2.98e-02

Pos logit contributions
mons+0.033
opard+0.029
aro+0.028
 badly+0.027
iw+0.026
Neg logit contributions
 Jason-0.029
 Gary-0.027
oby-0.026
 Simon-0.025
 Martin-0.025
Token named
Token ID3706
Feature activation+2.25e-02

Pos logit contributions
mons+0.046
opard+0.036
drops+0.036
iw+0.033
aro+0.033
Neg logit contributions
 Jason-0.065
 Gary-0.064
oby-0.061
 Simon-0.060
 Martin-0.059
Token Tiny
Token ID20443
Feature activation+2.12e-02

Pos logit contributions
 Jason+0.042
oby+0.041
Jason+0.040
 Gary+0.040
 Simon+0.038
Neg logit contributions
mons-0.038
opard-0.034
iw-0.032
 badly-0.032
 cherry-0.031
Token.
Token ID13
Feature activation+9.53e-02

Pos logit contributions
 Jason+0.050
 Gary+0.048
Jason+0.047
oby+0.046
 Simon+0.045
Neg logit contributions
mons-0.027
opard-0.025
 badly-0.022
aro-0.021
iw-0.020
Token Tiny
Token ID20443
Feature activation+3.45e-03

Pos logit contributions
lling+0.137
Jason+0.133
 Jason+0.128
oby+0.124
 Justin+0.123
Neg logit contributions
mons-0.145
opard-0.143
gy-0.143
 Wh-0.137
 bars-0.133
Token had
Token ID550
Feature activation-6.29e-03

Pos logit contributions
 Jason+0.008
 Gary+0.007
oby+0.007
Jason+0.007
 Simon+0.007
Neg logit contributions
mons-0.005
opard-0.005
aro-0.004
 badly-0.004
iw-0.004
Token a
Token ID257
Feature activation+4.45e-04

Pos logit contributions
mons+0.011
opard+0.010
aro+0.010
iw+0.010
round+0.009
Neg logit contributions
 Jason-0.012
 Gary-0.012
oby-0.011
 Martin-0.011
Jason-0.011
Token very
Token ID845
Feature activation-8.52e-03

Pos logit contributions
 Jason+0.001
 Gary+0.001
oby+0.001
Jason+0.001
 Martin+0.001
Neg logit contributions
mons-0.001
opard-0.001
aro-0.001
 badly-0.001
iw-0.001
Token small
Token ID1402
Feature activation+2.98e-03

Pos logit contributions
mons+0.017
opard+0.015
aro+0.015
iw+0.014
 badly+0.014
Neg logit contributions
 Jason-0.014
 Gary-0.014
oby-0.013
 Martin-0.012
Jason-0.012
Token Lily
Token ID20037
Feature activation-7.37e-03

Pos logit contributions
mons+0.022
opard+0.021
aro+0.020
 badly+0.019
pre+0.019
Neg logit contributions
 Jason-0.018
 Gary-0.017
 Emily-0.016
oby-0.016
 Martin-0.016
Token.
Token ID13
Feature activation+2.16e-02

Pos logit contributions
mons+0.013
opard+0.012
aro+0.011
iw+0.011
drops+0.010
Neg logit contributions
 Jason-0.015
 Gary-0.014
oby-0.013
Jason-0.013
 Simon-0.013
Token She
Token ID1375
Feature activation-6.06e-03

Pos logit contributions
 Jason+0.043
 Gary+0.041
Jason+0.040
oby+0.039
 Simon+0.038
Neg logit contributions
mons-0.038
opard-0.033
iw-0.031
 badly-0.031
 cherry-0.030
Token loved
Token ID6151
Feature activation+3.38e-03

Pos logit contributions
mons+0.010
opard+0.009
aro+0.008
iw+0.008
 badly+0.008
Neg logit contributions
 Jason-0.013
 Gary-0.012
oby-0.012
Jason-0.011
 Martin-0.011
Token ice
Token ID4771
Feature activation-7.42e-02

Pos logit contributions
 Jason+0.008
 Gary+0.008
oby+0.008
Jason+0.008
 Simon+0.007
Neg logit contributions
mons-0.004
opard-0.004
aro-0.003
 badly-0.003
iw-0.003
Token-
Token ID12
Feature activation-1.05e-01

Pos logit contributions
aro+0.112
sed+0.112
rils+0.108
mons+0.107
opard+0.106
Neg logit contributions
 brothers-0.103
ie-0.101
oby-0.100
iny-0.097
 forth-0.097
Tokencream
Token ID36277
Feature activation-4.58e-02

Pos logit contributions
sed+0.164
ses+0.155
opard+0.137
mons+0.133
 badly+0.130
Neg logit contributions
umper-0.143
 Jason-0.142
ye-0.142
 him-0.140
iny-0.139
Token more
Token ID517
Feature activation-2.72e-02

Pos logit contributions
mons+0.079
opard+0.074
aro+0.073
har+0.069
ork+0.067
Neg logit contributions
 Jason-0.078
 Gary-0.072
oby-0.071
 Simon-0.069
 Martin-0.068
Token than
Token ID621
Feature activation-4.90e-02

Pos logit contributions
mons+0.043
opard+0.038
aro+0.035
iw+0.032
 bars+0.032
Neg logit contributions
 Jason-0.057
 Gary-0.054
oby-0.053
 Martin-0.052
 Simon-0.052
Token anything
Token ID1997
Feature activation-2.56e-02

Pos logit contributions
opard+0.116
mons+0.113
har+0.102
pre+0.101
round+0.099
Neg logit contributions
 Jason-0.067
 Gary-0.059
 Justin-0.055
 Martin-0.055
 dragons-0.054
Token in
Token ID287
Feature activation-3.37e-03

Pos logit contributions
mons+0.046
opard+0.044
round+0.038
aro+0.037
iw+0.037
Neg logit contributions
 Jason-0.047
 Gary-0.046
 Simon-0.043
 Martin-0.042
oby-0.042
Token".
Token ID1911
Feature activation-2.06e-02

Pos logit contributions
 Jason+0.006
 Gary+0.006
oby+0.005
Jason+0.005
 Simon+0.005
Neg logit contributions
mons-0.005
opard-0.004
aro-0.004
 badly-0.004
iw-0.004
Token They
Token ID1119
Feature activation+1.04e-02

Pos logit contributions
mons+0.045
opard+0.044
aro+0.042
 badly+0.041
iw+0.040
Neg logit contributions
 Jason-0.032
 Gary-0.029
 Simon-0.027
 Martin-0.027
oby-0.026
Token share
Token ID2648
Feature activation-5.00e-02

Pos logit contributions
 Jason+0.020
 Gary+0.019
oby+0.019
Jason+0.018
 Simon+0.018
Neg logit contributions
mons-0.018
opard-0.016
 badly-0.015
iw-0.015
aro-0.015
Token their
Token ID511
Feature activation-3.16e-02

Pos logit contributions
opard+0.148
mons+0.141
drops+0.135
aro+0.134
har+0.131
Neg logit contributions
 Jason-0.042
 his-0.032
 Justin-0.026
Jason-0.025
 Gary-0.025
Token ice
Token ID4771
Feature activation-7.59e-02

Pos logit contributions
mons+0.048
opard+0.045
aro+0.041
 badly+0.041
drops+0.040
Neg logit contributions
 Jason-0.063
 Gary-0.058
oby-0.058
Jason-0.057
 Martin-0.055
Token-
Token ID12
Feature activation-1.03e-01

Pos logit contributions
mons+0.117
 badly+0.111
opard+0.109
aro+0.109
sed+0.106
Neg logit contributions
oby-0.119
 Jason-0.115
iny-0.115
pa-0.107
father-0.104
Tokencream
Token ID36277
Feature activation-5.98e-02

Pos logit contributions
sed+0.161
ses+0.147
 badly+0.139
+0.136
mons+0.130
Neg logit contributions
 Jason-0.160
oby-0.160
iny-0.156
ye-0.152
ock-0.149
Token with
Token ID351
Feature activation-2.91e-02

Pos logit contributions
mons+0.107
opard+0.100
aro+0.097
ork+0.091
 badly+0.091
Neg logit contributions
 Jason-0.090
oby-0.080
 Simon-0.077
 Gary-0.077
 Martin-0.077
Token Mom
Token ID11254
Feature activation-8.64e-03

Pos logit contributions
mons+0.069
opard+0.066
iw+0.062
pre+0.061
round+0.060
Neg logit contributions
 Jason-0.042
 Gary-0.038
 Simon-0.036
 Luke-0.036
 Justin-0.035
Token and
Token ID290
Feature activation+7.90e-03

Pos logit contributions
mons+0.015
opard+0.013
aro+0.012
 badly+0.012
iw+0.012
Neg logit contributions
 Jason-0.018
 Gary-0.017
oby-0.016
 Simon-0.016
Jason-0.016
Token Dad
Token ID17415
Feature activation-6.96e-03

Pos logit contributions
 Jason+0.014
 Gary+0.013
oby+0.013
Jason+0.012
 Martin+0.012
Neg logit contributions
mons-0.016
opard-0.014
aro-0.013
iw-0.013
 badly-0.013
Token nodded
Token ID14464
Feature activation+1.07e-02

Pos logit contributions
mons+0.028
opard+0.026
aro+0.024
 badly+0.023
iw+0.023
Neg logit contributions
 Jason-0.034
 Gary-0.032
oby-0.030
Jason-0.030
 Simon-0.030
Token.
Token ID13
Feature activation+2.03e-02

Pos logit contributions
 Jason+0.019
 Gary+0.018
oby+0.017
Jason+0.016
 Martin+0.016
Neg logit contributions
mons-0.021
opard-0.019
 badly-0.018
aro-0.018
iw-0.017
Token He
Token ID679
Feature activation-4.24e-02

Pos logit contributions
 Jason+0.037
 Gary+0.035
oby+0.034
Jason+0.033
 Simon+0.032
Neg logit contributions
mons-0.037
opard-0.034
 badly-0.031
iw-0.031
aro-0.031
Token liked
Token ID8288
Feature activation-3.97e-02

Pos logit contributions
mons+0.086
opard+0.078
aro+0.076
 badly+0.071
iw+0.069
Neg logit contributions
 Jason-0.075
 Gary-0.067
Jason-0.064
 Justin-0.064
oby-0.063
Token ice
Token ID4771
Feature activation-6.11e-02

Pos logit contributions
mons+0.071
opard+0.070
pre+0.060
har+0.059
 badly+0.056
Neg logit contributions
 Jason-0.075
 Gary-0.068
 Simon-0.065
 Justin-0.064
oby-0.063
Token-
Token ID12
Feature activation-1.03e-01

Pos logit contributions
mons+0.087
opard+0.084
aro+0.083
har+0.075
sed+0.074
Neg logit contributions
 Jason-0.112
oby-0.109
iny-0.100
Jason-0.096
 Gary-0.096
Tokencream
Token ID36277
Feature activation-3.77e-02

Pos logit contributions
sed+0.144
ses+0.132
 badly+0.129
opard+0.126
 fountain+0.126
Neg logit contributions
 Jason-0.157
aus-0.147
oby-0.146
iny-0.145
umper-0.143
Token too
Token ID1165
Feature activation-2.42e-02

Pos logit contributions
mons+0.069
opard+0.063
aro+0.060
har+0.057
iw+0.056
Neg logit contributions
 Jason-0.065
 Gary-0.061
oby-0.059
 Simon-0.057
 Justin-0.056
Token,
Token ID11
Feature activation-3.53e-02

Pos logit contributions
mons+0.051
opard+0.047
aro+0.044
iw+0.043
pre+0.042
Neg logit contributions
 Jason-0.042
 Gary-0.038
 Simon-0.036
oby-0.036
 Martin-0.036
Token but
Token ID475
Feature activation+7.40e-03

Pos logit contributions
mons+0.064
opard+0.062
aro+0.054
iw+0.053
pre+0.053
Neg logit contributions
 Jason-0.069
 Gary-0.066
 Simon-0.061
 Justin-0.060
 Harry-0.059
Token he
Token ID339
Feature activation-3.37e-02

Pos logit contributions
 Jason+0.013
 Gary+0.012
oby+0.012
Jason+0.012
 Simon+0.011
Neg logit contributions
mons-0.014
opard-0.013
 badly-0.012
aro-0.012
iw-0.012
Token Anna
Token ID11735
Feature activation-1.51e-02

Pos logit contributions
 Jason+0.028
 Gary+0.027
oby+0.027
Jason+0.026
 Simon+0.026
Neg logit contributions
mons-0.022
opard-0.019
 badly-0.017
iw-0.017
aro-0.017
Token and
Token ID290
Feature activation+3.58e-02

Pos logit contributions
mons+0.026
opard+0.023
aro+0.023
iw+0.021
 badly+0.021
Neg logit contributions
 Jason-0.030
 Gary-0.029
oby-0.028
 Simon-0.027
Jason-0.027
Token Ben
Token ID3932
Feature activation-2.28e-02

Pos logit contributions
oby+0.054
 Jason+0.051
 Gary+0.051
Jason+0.050
die+0.048
Neg logit contributions
mons-0.074
opard-0.063
 fountain-0.059
iw-0.058
 cherry-0.057
Token wanted
Token ID2227
Feature activation-5.89e-02

Pos logit contributions
mons+0.045
opard+0.042
aro+0.040
iw+0.039
pre+0.037
Neg logit contributions
 Jason-0.040
 Gary-0.037
 Simon-0.035
 Martin-0.035
Jason-0.035
Token ice
Token ID4771
Feature activation-7.31e-02

Pos logit contributions
opard+0.139
mons+0.129
drops+0.126
pre+0.122
har+0.120
Neg logit contributions
 Jason-0.079
 Harry-0.067
 Gary-0.067
 his-0.066
 Simon-0.065
Token-
Token ID12
Feature activation-1.01e-01

Pos logit contributions
opard+0.116
mons+0.109
aro+0.108
sed+0.105
ses+0.100
Neg logit contributions
 Jason-0.111
oby-0.108
 his-0.097
iny-0.096
pa-0.095
Tokencream
Token ID36277
Feature activation-3.80e-02

Pos logit contributions
sed+0.162
ses+0.153
opard+0.141
mons+0.131
sing+0.130
Neg logit contributions
 Jason-0.156
umper-0.146
oby-0.142
 him-0.140
aus-0.140
Tokens
Token ID82
Feature activation-4.37e-02

Pos logit contributions
mons+0.073
opard+0.069
aro+0.065
har+0.063
iw+0.061
Neg logit contributions
 Jason-0.061
 Gary-0.056
oby-0.054
 Simon-0.053
 Martin-0.051
Token.
Token ID13
Feature activation+6.99e-03

Pos logit contributions
mons+0.096
opard+0.093
aro+0.089
pre+0.085
iw+0.083
Neg logit contributions
 Jason-0.059
 Gary-0.053
oby-0.052
 Simon-0.049
 Peter-0.048
Token They
Token ID1119
Feature activation+9.19e-03

Pos logit contributions
 Jason+0.015
 Gary+0.014
oby+0.014
Jason+0.013
 Simon+0.013
Neg logit contributions
mons-0.011
opard-0.010
aro-0.009
iw-0.009
 badly-0.009
Token ran
Token ID4966
Feature activation-5.29e-02

Pos logit contributions
 Jason+0.018
 Gary+0.017
oby+0.016
Jason+0.016
 Simon+0.016
Neg logit contributions
mons-0.016
opard-0.015
 badly-0.014
aro-0.014
iw-0.013
Token Lily
Token ID20037
Feature activation+5.15e-03

Pos logit contributions
mons+0.010
opard+0.010
aro+0.009
 badly+0.009
iw+0.009
Neg logit contributions
 Jason-0.009
 Gary-0.009
oby-0.008
 Simon-0.008
 Martin-0.008
Token.
Token ID13
Feature activation+2.56e-02

Pos logit contributions
 Jason+0.011
 Gary+0.011
oby+0.010
Jason+0.010
 Simon+0.010
Neg logit contributions
mons-0.008
opard-0.007
 badly-0.006
aro-0.006
iw-0.006
Token She
Token ID1375
Feature activation-1.53e-03

Pos logit contributions
 Jason+0.052
 Gary+0.050
Jason+0.049
oby+0.048
 Simon+0.047
Neg logit contributions
mons-0.043
opard-0.036
iw-0.035
 badly-0.035
 cherry-0.034
Token loved
Token ID6151
Feature activation+4.03e-03

Pos logit contributions
mons+0.002
opard+0.002
aro+0.002
iw+0.002
 badly+0.002
Neg logit contributions
 Jason-0.003
 Gary-0.003
oby-0.003
Jason-0.003
 Martin-0.003
Token ice
Token ID4771
Feature activation-6.84e-02

Pos logit contributions
 Jason+0.010
 Gary+0.010
oby+0.009
Jason+0.009
 Simon+0.009
Neg logit contributions
mons-0.005
opard-0.004
aro-0.004
 badly-0.004
iw-0.004
Token-
Token ID12
Feature activation-9.91e-02

Pos logit contributions
aro+0.097
sed+0.096
rils+0.094
opard+0.094
mons+0.094
Neg logit contributions
oby-0.101
 brothers-0.099
ie-0.098
 Jason-0.095
iny-0.094
Tokencream
Token ID36277
Feature activation-4.21e-02

Pos logit contributions
sed+0.153
ses+0.144
opard+0.128
mons+0.120
sing+0.120
Neg logit contributions
 Jason-0.143
umper-0.141
 him-0.136
oby-0.135
iny-0.134
Token more
Token ID517
Feature activation-2.16e-02

Pos logit contributions
mons+0.072
opard+0.067
aro+0.066
har+0.062
ork+0.059
Neg logit contributions
 Jason-0.074
 Gary-0.069
oby-0.067
 Simon-0.066
 Martin-0.064
Token than
Token ID621
Feature activation-4.75e-02

Pos logit contributions
mons+0.033
opard+0.028
aro+0.027
iw+0.024
 bars+0.024
Neg logit contributions
 Jason-0.047
 Gary-0.045
oby-0.044
 Simon-0.043
 Martin-0.043
Token anything
Token ID1997
Feature activation-2.36e-02

Pos logit contributions
opard+0.113
mons+0.109
har+0.100
pre+0.099
round+0.097
Neg logit contributions
 Jason-0.065
 Gary-0.055
 Justin-0.052
 Martin-0.051
 Simon-0.050
Token in
Token ID287
Feature activation-2.66e-03

Pos logit contributions
mons+0.042
opard+0.040
round+0.035
aro+0.034
iw+0.034
Neg logit contributions
 Jason-0.044
 Gary-0.043
 Simon-0.040
oby-0.039
 Martin-0.039
Token and
Token ID290
Feature activation-2.06e-02

Pos logit contributions
mons+0.096
opard+0.096
aro+0.091
ork+0.086
iw+0.085
Neg logit contributions
 Jason-0.064
 Gary-0.057
 Luke-0.052
 Harry-0.052
 Martin-0.052
Token a
Token ID257
Feature activation-3.51e-02

Pos logit contributions
mons+0.039
opard+0.038
iw+0.034
aro+0.033
pre+0.033
Neg logit contributions
 Jason-0.039
 Gary-0.036
 Simon-0.034
 Martin-0.034
Jason-0.033
Token merry
Token ID44570
Feature activation-5.26e-02

Pos logit contributions
mons+0.065
aro+0.057
opard+0.055
iw+0.051
 badly+0.051
Neg logit contributions
 Jason-0.065
 Gary-0.061
Jason-0.059
oby-0.057
 Simon-0.057
Token-
Token ID12
Feature activation-9.17e-02

Pos logit contributions
mons+0.089
iw+0.074
aro+0.072
ometers+0.070
opard+0.068
Neg logit contributions
 Jason-0.100
oby-0.096
 Gary-0.095
 shield-0.090
 Martin-0.090
Tokengo
Token ID2188
Feature activation-6.70e-02

Pos logit contributions
mons+0.180
 badly+0.173
+0.172
ric+0.170
 fault+0.166
Neg logit contributions
ye-0.088
rr-0.083
iny-0.075
ock-0.074
oby-0.073
Token-
Token ID12
Feature activation-9.87e-02

Pos logit contributions
mons+0.122
sed+0.102
+0.102
iw+0.100
opard+0.099
Neg logit contributions
 forth-0.090
ye-0.087
rr-0.086
oby-0.084
ie-0.081
Tokenround
Token ID744
Feature activation-5.53e-02

Pos logit contributions
sed+0.133
mons+0.127
 badly+0.124
+0.122
ses+0.120
Neg logit contributions
oby-0.155
iny-0.155
ock-0.154
rr-0.151
ye-0.146
Token.
Token ID13
Feature activation-5.50e-03

Pos logit contributions
mons+0.118
iw+0.114
opard+0.114
har+0.108
aro+0.107
Neg logit contributions
 Jason-0.064
 Gary-0.057
oby-0.056
 Simon-0.054
 Chris-0.054
Token Lily
Token ID20037
Feature activation-2.96e-02

Pos logit contributions
mons+0.010
opard+0.010
aro+0.009
 badly+0.009
iw+0.009
Neg logit contributions
 Jason-0.010
 Gary-0.010
oby-0.009
 Simon-0.009
 Martin-0.009
Token wanted
Token ID2227
Feature activation-4.52e-02

Pos logit contributions
mons+0.062
opard+0.057
aro+0.055
pre+0.052
iw+0.052
Neg logit contributions
 Jason-0.051
 Gary-0.046
Jason-0.043
oby-0.043
 Simon-0.043
Token to
Token ID284
Feature activation-3.40e-02

Pos logit contributions
opard+0.100
mons+0.094
pre+0.092
har+0.090
drops+0.085
Neg logit contributions
 Jason-0.067
 Gary-0.062
 Harry-0.058
 Simon-0.056
 Toby-0.056
Token.
Token ID13
Feature activation+2.35e-02

Pos logit contributions
mons+0.019
opard+0.017
aro+0.016
iw+0.015
drops+0.015
Neg logit contributions
 Jason-0.020
 Gary-0.019
oby-0.018
Jason-0.018
 Simon-0.018
Token Tim
Token ID5045
Feature activation+1.17e-02

Pos logit contributions
 Jason+0.056
 Gary+0.053
Jason+0.053
oby+0.052
 Simon+0.051
Neg logit contributions
mons-0.031
opard-0.027
iw-0.025
 badly-0.024
 cherry-0.023
Tokenmy
Token ID1820
Feature activation-1.64e-02

Pos logit contributions
 Jason+0.014
 Gary+0.013
oby+0.012
 Simon+0.012
 Martin+0.012
Neg logit contributions
mons-0.029
opard-0.027
 badly-0.026
iw-0.026
aro-0.025
Token loved
Token ID6151
Feature activation+1.27e-02

Pos logit contributions
mons+0.029
aro+0.026
opard+0.025
iw+0.024
drops+0.023
Neg logit contributions
 Jason-0.033
 Gary-0.031
oby-0.030
Jason-0.029
 Martin-0.029
Token ice
Token ID4771
Feature activation-7.31e-02

Pos logit contributions
 Jason+0.032
 Gary+0.031
oby+0.030
Jason+0.030
 Simon+0.029
Neg logit contributions
mons-0.016
opard-0.013
aro-0.011
iw-0.011
 badly-0.011
Token-
Token ID12
Feature activation-9.86e-02

Pos logit contributions
sed+0.111
aro+0.107
opard+0.103
mons+0.103
overed+0.102
Neg logit contributions
 brothers-0.103
oby-0.101
 forth-0.099
ie-0.098
iny-0.096
Tokencream
Token ID36277
Feature activation-4.18e-02

Pos logit contributions
sed+0.153
ses+0.145
opard+0.127
mons+0.122
 badly+0.121
Neg logit contributions
 Jason-0.139
umper-0.139
oby-0.133
aus-0.133
ye-0.133
Token and
Token ID290
Feature activation-1.67e-02

Pos logit contributions
mons+0.070
opard+0.065
aro+0.064
har+0.059
ork+0.057
Neg logit contributions
 Jason-0.075
 Gary-0.069
oby-0.068
 Simon-0.066
 Martin-0.064
Token he
Token ID339
Feature activation-2.73e-02

Pos logit contributions
mons+0.033
opard+0.031
aro+0.028
 badly+0.027
iw+0.027
Neg logit contributions
 Jason-0.031
 Gary-0.028
 Simon-0.026
 Martin-0.026
Jason-0.026
Token always
Token ID1464
Feature activation-1.09e-03

Pos logit contributions
mons+0.054
opard+0.047
aro+0.046
drops+0.044
 badly+0.043
Neg logit contributions
 Jason-0.049
 Gary-0.045
Jason-0.043
oby-0.042
 Justin-0.042
Token asked
Token ID1965
Feature activation+2.16e-02

Pos logit contributions
mons+0.002
opard+0.002
aro+0.002
 badly+0.002
iw+0.002
Neg logit contributions
 Jason-0.002
 Gary-0.002
oby-0.002
Jason-0.002
 Simon-0.002
TokenThe
Token ID464
Feature activation+1.40e-04

Pos logit contributions
 Jason+0.026
 Gary+0.025
oby+0.024
 Simon+0.024
 Martin+0.023
Neg logit contributions
mons-0.023
opard-0.021
aro-0.019
iw-0.018
 badly-0.018
Token man
Token ID582
Feature activation-2.20e-03

Pos logit contributions
 Jason+0.000
 Gary+0.000
oby+0.000
Jason+0.000
 Martin+0.000
Neg logit contributions
mons-0.000
opard-0.000
aro-0.000
 badly-0.000
iw-0.000
Token gives
Token ID3607
Feature activation-1.21e-02

Pos logit contributions
mons+0.004
opard+0.004
 badly+0.004
aro+0.004
iw+0.004
Neg logit contributions
 Jason-0.004
 Gary-0.004
oby-0.003
Jason-0.003
 Simon-0.003
Token them
Token ID606
Feature activation-5.54e-02

Pos logit contributions
mons+0.025
opard+0.023
 badly+0.022
aro+0.021
drops+0.021
Neg logit contributions
 Jason-0.020
 Gary-0.019
oby-0.018
 Simon-0.018
 Justin-0.017
Token ice
Token ID4771
Feature activation-7.52e-02

Pos logit contributions
opard+0.115
mons+0.114
drops+0.105
 badly+0.102
aro+0.102
Neg logit contributions
 Jason-0.081
 Gary-0.071
 Justin-0.070
 Simon-0.069
oby-0.067
Token-
Token ID12
Feature activation-9.80e-02

Pos logit contributions
opard+0.102
aro+0.100
mons+0.099
 badly+0.095
lves+0.095
Neg logit contributions
oby-0.125
 Jason-0.125
iny-0.113
ilo-0.109
Jason-0.107
Tokencream
Token ID36277
Feature activation-4.28e-02

Pos logit contributions
sed+0.137
ses+0.123
 badly+0.121
opard+0.121
ich+0.120
Neg logit contributions
 Jason-0.158
oby-0.153
umper-0.144
 Justin-0.143
iny-0.143
Token.
Token ID13
Feature activation-1.03e-02

Pos logit contributions
mons+0.080
opard+0.076
aro+0.073
har+0.070
iw+0.066
Neg logit contributions
 Jason-0.068
 Gary-0.061
oby-0.058
 Simon-0.058
 Martin-0.057
Token Tim
Token ID5045
Feature activation-7.66e-03

Pos logit contributions
mons+0.021
opard+0.020
 badly+0.019
aro+0.018
iw+0.018
Neg logit contributions
 Jason-0.017
 Gary-0.017
oby-0.015
 Simon-0.015
 Martin-0.015
Token and
Token ID290
Feature activation+4.37e-03

Pos logit contributions
mons+0.013
opard+0.012
aro+0.011
 badly+0.011
iw+0.010
Neg logit contributions
 Jason-0.016
 Gary-0.015
oby-0.014
Jason-0.014
 Martin-0.014
Token Mia
Token ID32189
Feature activation-4.29e-03

Pos logit contributions
 Jason+0.009
 Gary+0.009
oby+0.008
Jason+0.008
 Simon+0.008
Neg logit contributions
mons-0.007
opard-0.007
aro-0.006
 badly-0.006
iw-0.006
Token asked
Token ID1965
Feature activation+1.12e-02

Pos logit contributions
 Jason+0.052
 Gary+0.052
oby+0.049
Jason+0.047
 Martin+0.046
Neg logit contributions
mons-0.061
opard-0.055
 badly-0.054
iw-0.051
 bars-0.050
Token.
Token ID13
Feature activation+5.70e-03

Pos logit contributions
 Jason+0.025
 Gary+0.024
oby+0.023
Jason+0.022
 Martin+0.022
Neg logit contributions
mons-0.017
opard-0.015
 badly-0.014
aro-0.013
iw-0.013
Token She
Token ID1375
Feature activation-1.15e-02

Pos logit contributions
 Jason+0.011
 Gary+0.011
oby+0.010
Jason+0.010
 Simon+0.010
Neg logit contributions
mons-0.010
opard-0.009
aro-0.008
 badly-0.008
iw-0.008
Token loved
Token ID6151
Feature activation-3.28e-02

Pos logit contributions
mons+0.022
opard+0.020
aro+0.019
iw+0.018
 badly+0.018
Neg logit contributions
 Jason-0.022
 Gary-0.020
oby-0.020
Jason-0.019
 Simon-0.019
Token ice
Token ID4771
Feature activation-6.31e-02

Pos logit contributions
mons+0.056
opard+0.055
pre+0.047
har+0.047
 badly+0.047
Neg logit contributions
 Jason-0.064
 Gary-0.059
 Simon-0.056
 Justin-0.055
 Martin-0.055
Token-
Token ID12
Feature activation-9.77e-02

Pos logit contributions
mons+0.092
aro+0.089
opard+0.089
lves+0.082
har+0.080
Neg logit contributions
 Jason-0.113
oby-0.108
iny-0.099
pa-0.096
 Gary-0.096
Tokencream
Token ID36277
Feature activation-3.80e-02

Pos logit contributions
sed+0.142
ses+0.131
 badly+0.129
 fountain+0.123
 purse+0.120
Neg logit contributions
 Jason-0.150
aus-0.136
oby-0.135
iny-0.134
 Gary-0.134
Token,
Token ID11
Feature activation-6.06e-02

Pos logit contributions
mons+0.071
opard+0.065
aro+0.062
har+0.059
iw+0.058
Neg logit contributions
 Jason-0.065
 Gary-0.060
oby-0.058
 Simon-0.057
 Martin-0.055
Token especially
Token ID2592
Feature activation-3.49e-02

Pos logit contributions
opard+0.121
mons+0.117
aro+0.104
pre+0.102
har+0.102
Neg logit contributions
 Jason-0.105
 Gary-0.098
 Justin-0.089
 Harry-0.088
 Emily-0.088
Token chocolate
Token ID11311
Feature activation-5.27e-02

Pos logit contributions
mons+0.064
opard+0.061
har+0.058
aro+0.056
iw+0.056
Neg logit contributions
 Jason-0.061
 Gary-0.057
oby-0.053
 Simon-0.052
 Justin-0.052
Token and
Token ID290
Feature activation-3.35e-02

Pos logit contributions
mons+0.098
opard+0.095
aro+0.092
har+0.090
iw+0.086
Neg logit contributions
 Jason-0.082
 Gary-0.072
oby-0.071
 Simon-0.068
 Martin-0.067
Token she
Token ID673
Feature activation-8.07e-03

Pos logit contributions
 Jason+0.029
 Gary+0.028
oby+0.028
Jason+0.027
 Simon+0.026
Neg logit contributions
mons-0.023
opard-0.020
aro-0.019
 badly-0.018
iw-0.018
Token could
Token ID714
Feature activation-2.51e-02

Pos logit contributions
mons+0.016
opard+0.014
aro+0.014
iw+0.013
 badly+0.013
Neg logit contributions
 Jason-0.015
 Gary-0.014
oby-0.013
 Simon-0.013
Jason-0.013
Token share
Token ID2648
Feature activation-4.38e-02

Pos logit contributions
mons+0.057
opard+0.053
aro+0.049
iw+0.047
 pige+0.046
Neg logit contributions
 Jason-0.038
 Gary-0.035
 Martin-0.032
 Simon-0.032
oby-0.031
Token her
Token ID607
Feature activation-7.02e-02

Pos logit contributions
opard+0.131
mons+0.130
pre+0.117
drops+0.117
aro+0.116
Neg logit contributions
 Jason-0.039
 Gary-0.029
 Martin-0.025
 Justin-0.025
 Simon-0.025
Token ice
Token ID4771
Feature activation-7.38e-02

Pos logit contributions
mons+0.141
opard+0.141
aro+0.135
drops+0.132
overed+0.118
Neg logit contributions
 his-0.084
 Jason-0.081
 me-0.078
 brothers-0.077
 agreement-0.073
Token-
Token ID12
Feature activation-9.76e-02

Pos logit contributions
sed+0.112
mons+0.112
opard+0.110
aro+0.108
ses+0.104
Neg logit contributions
oby-0.123
 Jason-0.117
iny-0.112
father-0.106
ie-0.103
Tokencream
Token ID36277
Feature activation-5.49e-02

Pos logit contributions
sed+0.162
ses+0.148
opard+0.126
sing+0.124
mons+0.119
Neg logit contributions
 Jason-0.161
oby-0.157
umper-0.153
iny-0.150
Jason-0.147
Token with
Token ID351
Feature activation-2.25e-02

Pos logit contributions
mons+0.104
opard+0.098
aro+0.096
drops+0.084
 pel+0.084
Neg logit contributions
 Jason-0.086
oby-0.077
 Gary-0.074
 Simon-0.073
 Justin-0.071
Token the
Token ID262
Feature activation-2.93e-02

Pos logit contributions
mons+0.062
opard+0.061
round+0.055
aro+0.055
drops+0.055
Neg logit contributions
 Jason-0.025
 Gary-0.022
 Simon-0.019
 Martin-0.019
 Justin-0.018
Token boy
Token ID2933
Feature activation-2.27e-02

Pos logit contributions
mons+0.071
aro+0.068
opard+0.064
drops+0.060
har+0.059
Neg logit contributions
 Jason-0.037
Jason-0.031
oby-0.031
 Gary-0.030
 Justin-0.028
Token.
Token ID13
Feature activation-2.54e-03

Pos logit contributions
mons+0.044
opard+0.041
aro+0.037
pre+0.035
drops+0.035
Neg logit contributions
 Jason-0.042
 Gary-0.039
 Simon-0.036
 Martin-0.036
 Justin-0.036
Token.
Token ID13
Feature activation-5.27e-03

Pos logit contributions
mons+0.077
opard+0.069
aro+0.068
 Sy+0.062
iw+0.061
Neg logit contributions
 Jason-0.060
 Gary-0.055
 Martin-0.053
oby-0.052
 Simon-0.051
Token They
Token ID1119
Feature activation-1.72e-02

Pos logit contributions
mons+0.010
opard+0.009
aro+0.008
 badly+0.008
iw+0.008
Neg logit contributions
 Jason-0.010
 Gary-0.010
oby-0.009
 Simon-0.009
 Martin-0.009
Token share
Token ID2648
Feature activation-5.06e-02

Pos logit contributions
mons+0.034
opard+0.031
aro+0.028
 badly+0.028
iw+0.027
Neg logit contributions
 Jason-0.031
 Gary-0.029
 Martin-0.028
 Simon-0.027
Jason-0.027
Token their
Token ID511
Feature activation-2.93e-02

Pos logit contributions
opard+0.145
mons+0.138
t+0.128
drops+0.127
aro+0.126
Neg logit contributions
 Jason-0.043
 his-0.032
 Justin-0.029
Jason-0.027
 Gary-0.027
Token ice
Token ID4771
Feature activation-7.23e-02

Pos logit contributions
mons+0.047
opard+0.043
 badly+0.040
aro+0.040
drops+0.038
Neg logit contributions
 Jason-0.056
 Gary-0.053
oby-0.051
Jason-0.051
 Martin-0.050
Token-
Token ID12
Feature activation-9.73e-02

Pos logit contributions
mons+0.110
aro+0.104
opard+0.103
+0.101
 Sy+0.100
Neg logit contributions
oby-0.110
iny-0.107
 Jason-0.104
 journals-0.097
pa-0.097
Tokencream
Token ID36277
Feature activation-4.44e-02

Pos logit contributions
sed+0.148
+0.133
ses+0.131
 badly+0.121
mons+0.121
Neg logit contributions
iny-0.156
oby-0.151
 Jason-0.149
ock-0.146
ye-0.145
Token.
Token ID13
Feature activation-7.62e-03

Pos logit contributions
mons+0.087
opard+0.081
aro+0.078
 badly+0.072
 Sy+0.071
Neg logit contributions
 Jason-0.065
oby-0.058
 Gary-0.057
 Martin-0.056
 Simon-0.056
Token They
Token ID1119
Feature activation-1.21e-02

Pos logit contributions
mons+0.015
opard+0.014
aro+0.013
 badly+0.013
iw+0.012
Neg logit contributions
 Jason-0.014
 Gary-0.013
 Simon-0.012
oby-0.012
 Martin-0.012
Token talk
Token ID1561
Feature activation+5.52e-03

Pos logit contributions
mons+0.023
opard+0.021
aro+0.020
 badly+0.019
iw+0.019
Neg logit contributions
 Jason-0.022
 Gary-0.021
 Martin-0.019
Jason-0.019
 Simon-0.019
Token and
Token ID290
Feature activation+1.36e-02

Pos logit contributions
 Jason+0.013
 Gary+0.012
oby+0.012
Jason+0.012
 Simon+0.012
Neg logit contributions
mons-0.008
opard-0.007
 badly-0.006
aro-0.006
iw-0.006
Token."
Token ID526
Feature activation-1.86e-02

Pos logit contributions
mons+0.071
opard+0.063
pre+0.057
 badly+0.057
sed+0.055
Neg logit contributions
 Jason-0.061
 Gary-0.058
 Martin-0.054
oby-0.054
 Simon-0.053
Token Tim
Token ID5045
Feature activation-2.13e-02

Pos logit contributions
mons+0.037
opard+0.036
aro+0.034
 badly+0.033
pre+0.031
Neg logit contributions
 Jason-0.032
 Gary-0.031
 Martin-0.027
 Harry-0.027
 Peter-0.027
Token took
Token ID1718
Feature activation-1.59e-02

Pos logit contributions
mons+0.040
opard+0.036
aro+0.035
 badly+0.034
iw+0.033
Neg logit contributions
 Jason-0.040
 Gary-0.037
oby-0.035
Jason-0.034
 Martin-0.034
Token the
Token ID262
Feature activation-5.69e-02

Pos logit contributions
mons+0.034
opard+0.032
aro+0.029
 badly+0.029
iw+0.029
Neg logit contributions
 Jason-0.026
 Gary-0.024
 Martin-0.022
 Simon-0.022
oby-0.022
Token ice
Token ID4771
Feature activation-6.01e-02

Pos logit contributions
mons+0.111
aro+0.103
drops+0.094
opard+0.094
uzz+0.092
Neg logit contributions
 Jason-0.078
ye-0.072
Jason-0.067
 older-0.064
 conflict-0.064
Token-
Token ID12
Feature activation-9.72e-02

Pos logit contributions
mons+0.087
aro+0.081
 badly+0.080
opard+0.079
sed+0.078
Neg logit contributions
 Jason-0.106
oby-0.102
iny-0.096
 shield-0.093
father-0.092
Tokencream
Token ID36277
Feature activation-5.11e-02

Pos logit contributions
sed+0.141
ses+0.131
 badly+0.116
sing+0.114
mons+0.113
Neg logit contributions
 Jason-0.165
oby-0.162
umper-0.158
Jason-0.153
ye-0.152
Token and
Token ID290
Feature activation-3.93e-02

Pos logit contributions
mons+0.096
opard+0.089
aro+0.088
 badly+0.082
ggy+0.081
Neg logit contributions
 Jason-0.078
 Gary-0.069
 Simon-0.066
oby-0.066
 Martin-0.066
Token started
Token ID2067
Feature activation-4.54e-02

Pos logit contributions
mons+0.084
opard+0.082
 badly+0.076
aro+0.074
iw+0.071
Neg logit contributions
 Jason-0.062
 Gary-0.054
 Justin-0.050
 Martin-0.050
 Simon-0.050
Token to
Token ID284
Feature activation-1.34e-02

Pos logit contributions
mons+0.082
opard+0.081
aro+0.068
 badly+0.068
pre+0.066
Neg logit contributions
 Jason-0.082
 Gary-0.070
 Simon-0.070
 Justin-0.070
 Martin-0.069
Token eat
Token ID4483
Feature activation-3.90e-02

Pos logit contributions
mons+0.026
opard+0.024
aro+0.022
 badly+0.021
pre+0.020
Neg logit contributions
 Jason-0.025
 Gary-0.023
Jason-0.022
 Martin-0.022
 Simon-0.021
Token the
Token ID262
Feature activation-3.86e-02

Pos logit contributions
opard+0.116
mons+0.114
aro+0.107
drops+0.107
har+0.102
Neg logit contributions
 Jason-0.053
 Gary-0.043
 Martin-0.041
Jason-0.039
 Harry-0.039
Token rest
Token ID1334
Feature activation-3.96e-02

Pos logit contributions
mons+0.067
aro+0.061
opard+0.061
drops+0.054
 badly+0.054
Neg logit contributions
 Jason-0.071
oby-0.067
Jason-0.065
 Gary-0.062
 Martin-0.060
Token of
Token ID286
Feature activation-4.61e-02

Pos logit contributions
mons+0.089
opard+0.083
 badly+0.077
aro+0.076
 Sy+0.075
Neg logit contributions
 Jason-0.052
oby-0.049
 Gary-0.045
 Simon-0.043
 Martin-0.040
Token the
Token ID262
Feature activation-2.71e-02

Pos logit contributions
mons+0.124
opard+0.121
drops+0.116
t+0.113
pre+0.113
Neg logit contributions
 Jason-0.043
 Gary-0.037
 Justin-0.031
 Harry-0.031
 Emily-0.031
Token ice
Token ID4771
Feature activation-6.08e-02

Pos logit contributions
mons+0.048
opard+0.043
aro+0.042
 badly+0.038
drops+0.038
Neg logit contributions
 Jason-0.050
oby-0.046
Jason-0.045
 Gary-0.044
 Martin-0.043
Token-
Token ID12
Feature activation-9.70e-02

Pos logit contributions
mons+0.084
opard+0.081
aro+0.080
 badly+0.078
sed+0.074
Neg logit contributions
 Jason-0.112
oby-0.107
iny-0.103
father-0.101
Jason-0.098
Tokencream
Token ID36277
Feature activation-4.98e-02

Pos logit contributions
sed+0.154
ses+0.141
opard+0.124
mons+0.118
 badly+0.118
Neg logit contributions
 Jason-0.155
iny-0.149
reci-0.148
oby-0.147
my-0.144
Token and
Token ID290
Feature activation-2.51e-02

Pos logit contributions
mons+0.092
opard+0.089
aro+0.086
 badly+0.082
ork+0.078
Neg logit contributions
 Jason-0.078
 Gary-0.068
 Simon-0.067
oby-0.066
 Martin-0.066
Token played
Token ID2826
Feature activation-3.25e-02

Pos logit contributions
mons+0.050
opard+0.048
aro+0.044
 badly+0.043
iw+0.041
Neg logit contributions
 Jason-0.044
 Gary-0.039
 Martin-0.037
 Simon-0.037
 Justin-0.036
Token together
Token ID1978
Feature activation-6.96e-03

Pos logit contributions
mons+0.065
opard+0.061
aro+0.058
iw+0.056
drops+0.054
Neg logit contributions
 Jason-0.052
 Gary-0.049
 Martin-0.047
oby-0.045
Jason-0.045
Token.
Token ID13
Feature activation+3.27e-03

Pos logit contributions
mons+0.013
opard+0.012
aro+0.010
iw+0.010
 badly+0.010
Neg logit contributions
 Jason-0.013
 Gary-0.013
oby-0.012
 Martin-0.012
 Simon-0.012
Token,
Token ID11
Feature activation-1.36e-02

Pos logit contributions
mons+0.022
opard+0.020
iw+0.019
aro+0.018
round+0.018
Neg logit contributions
 Jason-0.022
 Gary-0.021
 Simon-0.019
oby-0.019
 Martin-0.019
Token "
Token ID366
Feature activation-1.90e-02

Pos logit contributions
mons+0.027
opard+0.025
iw+0.023
 badly+0.023
aro+0.023
Neg logit contributions
 Jason-0.024
 Gary-0.023
 Simon-0.021
 Martin-0.021
oby-0.021
TokenI
Token ID40
Feature activation-3.44e-02

Pos logit contributions
mons+0.035
opard+0.031
aro+0.029
 bars+0.029
iw+0.029
Neg logit contributions
 Jason-0.036
 Gary-0.034
oby-0.034
Jason-0.033
 Simon-0.032
Token want
Token ID765
Feature activation-2.89e-02

Pos logit contributions
mons+0.067
opard+0.059
aro+0.059
round+0.053
iw+0.052
Neg logit contributions
 Jason-0.063
 Gary-0.058
Jason-0.055
 Simon-0.055
oby-0.055
Token ice
Token ID4771
Feature activation-5.74e-02

Pos logit contributions
opard+0.051
mons+0.050
drops+0.043
pre+0.043
aro+0.041
Neg logit contributions
 Jason-0.058
 Gary-0.054
 Simon-0.051
oby-0.050
 Harry-0.050
Token-
Token ID12
Feature activation-9.69e-02

Pos logit contributions
mons+0.084
opard+0.080
aro+0.074
sed+0.069
 Sy+0.067
Neg logit contributions
 Jason-0.113
oby-0.109
 Simon-0.097
Jason-0.096
ye-0.095
Tokencream
Token ID36277
Feature activation-2.87e-02

Pos logit contributions
sed+0.134
opard+0.128
ses+0.126
mons+0.122
 fountain+0.117
Neg logit contributions
 Jason-0.160
oby-0.150
umper-0.146
ye-0.146
aus-0.144
Token!"
Token ID2474
Feature activation+1.66e-02

Pos logit contributions
mons+0.050
opard+0.045
aro+0.043
iw+0.040
pre+0.039
Neg logit contributions
 Jason-0.056
 Gary-0.052
oby-0.051
 Simon-0.049
 Martin-0.048
Token Suddenly
Token ID24975
Feature activation+1.98e-02

Pos logit contributions
 Jason+0.024
 Gary+0.023
oby+0.022
Jason+0.021
 Martin+0.021
Neg logit contributions
mons-0.037
opard-0.033
 badly-0.031
iw-0.031
aro-0.031
Token,
Token ID11
Feature activation-1.26e-03

Pos logit contributions
 Jason+0.041
 Gary+0.039
oby+0.038
Jason+0.038
 Martin+0.036
Neg logit contributions
mons-0.031
opard-0.028
 badly-0.026
aro-0.026
iw-0.024
Token two
Token ID734
Feature activation+3.53e-02

Pos logit contributions
mons+0.002
opard+0.002
aro+0.002
iw+0.002
 badly+0.002
Neg logit contributions
 Jason-0.002
 Gary-0.002
oby-0.002
 Simon-0.002
 Martin-0.002
Token,
Token ID11
Feature activation-1.44e-02

Pos logit contributions
mons+0.022
opard+0.020
aro+0.018
iw+0.018
 badly+0.018
Neg logit contributions
 Jason-0.021
 Gary-0.020
oby-0.019
 Simon-0.018
 Martin-0.018
Token can
Token ID460
Feature activation-3.10e-02

Pos logit contributions
mons+0.029
opard+0.026
iw+0.024
 badly+0.024
aro+0.024
Neg logit contributions
 Jason-0.025
 Gary-0.024
 Simon-0.022
oby-0.022
 Martin-0.022
Token we
Token ID356
Feature activation-6.65e-03

Pos logit contributions
mons+0.061
opard+0.057
drops+0.051
iw+0.051
 badly+0.050
Neg logit contributions
 Jason-0.055
 Gary-0.052
 Martin-0.048
 Simon-0.048
 Justin-0.047
Token have
Token ID423
Feature activation-4.92e-02

Pos logit contributions
mons+0.014
opard+0.013
aro+0.012
 badly+0.012
iw+0.011
Neg logit contributions
 Jason-0.011
 Gary-0.010
oby-0.010
Jason-0.009
 Martin-0.009
Token ice
Token ID4771
Feature activation-6.04e-02

Pos logit contributions
mons+0.100
opard+0.099
drops+0.088
pre+0.084
aro+0.082
Neg logit contributions
 Jason-0.083
 Gary-0.071
 Martin-0.070
Jason-0.069
 Simon-0.068
Token-
Token ID12
Feature activation-9.69e-02

Pos logit contributions
mons+0.083
opard+0.082
aro+0.080
 badly+0.071
drops+0.071
Neg logit contributions
 Jason-0.112
oby-0.109
Jason-0.099
ye-0.098
iny-0.096
Tokencream
Token ID36277
Feature activation-4.32e-02

Pos logit contributions
sed+0.135
opard+0.132
 badly+0.127
ses+0.127
mons+0.124
Neg logit contributions
 Jason-0.148
ye-0.145
oby-0.138
aus-0.138
 me-0.134
Token,
Token ID11
Feature activation-3.55e-02

Pos logit contributions
mons+0.081
opard+0.075
aro+0.073
pre+0.067
iw+0.066
Neg logit contributions
 Jason-0.070
 Gary-0.063
oby-0.063
 Simon-0.060
 Martin-0.060
Token please
Token ID3387
Feature activation-1.33e-02

Pos logit contributions
mons+0.081
opard+0.074
iw+0.067
aro+0.067
pre+0.067
Neg logit contributions
 Jason-0.053
 Gary-0.050
 Simon-0.046
 Harry-0.045
 Peter-0.045
Token?"
Token ID1701
Feature activation-1.22e-02

Pos logit contributions
mons+0.029
opard+0.027
aro+0.025
 badly+0.024
drops+0.024
Neg logit contributions
 Jason-0.021
 Gary-0.019
 Simon-0.018
oby-0.018
 Martin-0.018
Token Tim
Token ID5045
Feature activation+4.31e-02

Pos logit contributions
mons+0.023
opard+0.021
iw+0.019
 badly+0.019
round+0.019
Neg logit contributions
 Jason-0.023
 Gary-0.022
 Simon-0.020
 Martin-0.020
oby-0.020
Token all
Token ID477
Feature activation-1.57e-03

Pos logit contributions
mons+0.039
opard+0.036
iw+0.033
aro+0.032
drops+0.032
Neg logit contributions
 Jason-0.036
 Gary-0.034
 Martin-0.031
oby-0.031
 Simon-0.031
Token kinds
Token ID6982
Feature activation-3.57e-02

Pos logit contributions
mons+0.003
opard+0.003
aro+0.003
 badly+0.003
iw+0.003
Neg logit contributions
 Jason-0.003
 Gary-0.002
oby-0.002
 Simon-0.002
 Martin-0.002
Token of
Token ID286
Feature activation-2.20e-02

Pos logit contributions
mons+0.086
opard+0.080
iw+0.076
ric+0.071
pre+0.071
Neg logit contributions
 Jason-0.039
 Gary-0.037
oby-0.035
 Martin-0.032
 dragons-0.032
Token delicious
Token ID12625
Feature activation-1.84e-02

Pos logit contributions
mons+0.046
opard+0.043
aro+0.039
drops+0.037
iw+0.037
Neg logit contributions
 Jason-0.036
 Gary-0.033
Jason-0.032
oby-0.031
 Martin-0.031
Token ice
Token ID4771
Feature activation-5.20e-02

Pos logit contributions
mons+0.031
opard+0.029
aro+0.027
 badly+0.026
iw+0.025
Neg logit contributions
 Jason-0.036
 Gary-0.034
oby-0.033
Jason-0.032
 Martin-0.032
Token-
Token ID12
Feature activation-9.67e-02

Pos logit contributions
aro+0.068
opard+0.066
mons+0.065
 badly+0.061
sed+0.061
Neg logit contributions
 Jason-0.103
oby-0.098
Jason-0.093
iny-0.088
 Gary-0.088
Tokencream
Token ID36277
Feature activation-2.32e-02

Pos logit contributions
sed+0.158
ses+0.148
 fountain+0.129
opard+0.127
 badly+0.125
Neg logit contributions
 Jason-0.137
iny-0.136
oby-0.134
ock-0.132
aus-0.127
Token flavors
Token ID17361
Feature activation-2.57e-02

Pos logit contributions
mons+0.040
opard+0.037
aro+0.036
 badly+0.034
iw+0.034
Neg logit contributions
 Jason-0.044
 Gary-0.040
oby-0.039
 Martin-0.038
 Simon-0.038
Token.
Token ID13
Feature activation-2.18e-02

Pos logit contributions
mons+0.046
opard+0.045
aro+0.042
iw+0.039
 badly+0.038
Neg logit contributions
 Jason-0.047
oby-0.043
 Gary-0.042
 Simon-0.040
Jason-0.040
Token "
Token ID366
Feature activation-1.54e-02

Pos logit contributions
mons+0.053
opard+0.050
aro+0.050
 badly+0.048
iw+0.047
Neg logit contributions
 Jason-0.029
 Gary-0.026
 Martin-0.024
oby-0.023
 Simon-0.023
TokenCan
Token ID6090
Feature activation-3.45e-02

Pos logit contributions
mons+0.031
opard+0.028
aro+0.027
 badly+0.026
iw+0.025
Neg logit contributions
 Jason-0.026
 Gary-0.024
oby-0.024
Jason-0.024
 Martin-0.023
Token ride
Token ID6594
Feature activation-4.70e-02

Pos logit contributions
mons+0.080
opard+0.076
 badly+0.068
pre+0.068
iw+0.068
Neg logit contributions
 Jason-0.044
 Gary-0.043
 Simon-0.038
 Chris-0.037
oby-0.037
Token the
Token ID262
Feature activation-3.34e-02

Pos logit contributions
mons+0.112
opard+0.107
pre+0.104
iw+0.099
itt+0.096
Neg logit contributions
 Gary-0.059
 Jason-0.057
 Emily-0.052
 Luke-0.051
 Chris-0.050
Token merry
Token ID44570
Feature activation-5.11e-02

Pos logit contributions
mons+0.048
opard+0.038
iw+0.037
 badly+0.036
pre+0.035
Neg logit contributions
 Jason-0.069
oby-0.066
 Gary-0.065
Jason-0.065
ye-0.064
Token-
Token ID12
Feature activation-9.18e-02

Pos logit contributions
mons+0.083
iw+0.072
opard+0.068
pre+0.066
ometers+0.064
Neg logit contributions
oby-0.092
 Jason-0.090
 Gary-0.088
 forth-0.084
 Martin-0.082
Tokengo
Token ID2188
Feature activation-5.82e-02

Pos logit contributions
mons+0.188
sed+0.177
 badly+0.177
+0.172
ses+0.170
Neg logit contributions
ye-0.082
iny-0.080
ock-0.079
oby-0.076
rr-0.076
Token-
Token ID12
Feature activation-9.67e-02

Pos logit contributions
mons+0.100
iw+0.081
opard+0.080
pre+0.077
sed+0.076
Neg logit contributions
oby-0.091
ye-0.088
rr-0.086
 Gary-0.086
 Chris-0.086
Tokenround
Token ID744
Feature activation-4.44e-02

Pos logit contributions
mons+0.128
sed+0.125
 badly+0.120
ses+0.115
 wil+0.104
Neg logit contributions
oby-0.161
iny-0.158
ock-0.155
ye-0.150
 Chris-0.150
Token.
Token ID13
Feature activation+9.48e-03

Pos logit contributions
mons+0.091
opard+0.085
iw+0.080
aro+0.080
pre+0.079
Neg logit contributions
 Jason-0.069
 Gary-0.065
 Simon-0.061
oby-0.060
 Martin-0.060
Token She
Token ID1375
Feature activation-1.23e-02

Pos logit contributions
 Jason+0.020
 Gary+0.019
oby+0.018
Jason+0.018
 Martin+0.018
Neg logit contributions
mons-0.016
opard-0.014
iw-0.012
aro-0.012
 badly-0.012
Token liked
Token ID8288
Feature activation-2.04e-02

Pos logit contributions
mons+0.027
opard+0.024
aro+0.022
 badly+0.022
iw+0.022
Neg logit contributions
 Jason-0.020
 Gary-0.019
oby-0.017
Jason-0.017
 Simon-0.017
Token the
Token ID262
Feature activation-2.08e-02

Pos logit contributions
mons+0.043
opard+0.040
pre+0.036
iw+0.036
 badly+0.035
Neg logit contributions
 Jason-0.034
 Gary-0.032
 Simon-0.030
 Martin-0.029
oby-0.029
Token to
Token ID284
Feature activation-2.13e-02

Pos logit contributions
mons+0.088
opard+0.080
iw+0.074
pre+0.074
aro+0.072
Neg logit contributions
 Jason-0.074
 Gary-0.070
 Martin-0.068
oby-0.065
 Simon-0.065
Token the
Token ID262
Feature activation-1.49e-02

Pos logit contributions
mons+0.051
opard+0.049
pre+0.044
 badly+0.044
aro+0.043
Neg logit contributions
 Jason-0.032
 Gary-0.029
 Simon-0.027
 Martin-0.026
 Justin-0.026
Token merry
Token ID44570
Feature activation-4.61e-02

Pos logit contributions
mons+0.024
opard+0.020
iw+0.018
aro+0.018
 badly+0.018
Neg logit contributions
 Jason-0.033
 Gary-0.030
Jason-0.030
oby-0.030
 Martin-0.030
Token-
Token ID12
Feature activation-9.12e-02

Pos logit contributions
mons+0.076
iw+0.062
opard+0.060
pre+0.057
aro+0.054
Neg logit contributions
 Jason-0.090
oby-0.087
 Gary-0.082
 Martin-0.082
 Simon-0.080
Tokengo
Token ID2188
Feature activation-4.56e-02

Pos logit contributions
mons+0.164
 badly+0.157
sed+0.151
+0.148
ses+0.143
Neg logit contributions
ye-0.124
 Jason-0.109
rr-0.107
iny-0.106
oby-0.105
Token-
Token ID12
Feature activation-9.61e-02

Pos logit contributions
mons+0.073
opard+0.059
iw+0.056
 badly+0.053
drops+0.053
Neg logit contributions
 Jason-0.086
oby-0.082
ye-0.082
 Martin-0.080
 Simon-0.079
Tokenround
Token ID744
Feature activation-3.26e-02

Pos logit contributions
mons+0.129
 badly+0.117
sed+0.114
ses+0.101
iw+0.099
Neg logit contributions
oby-0.173
iny-0.170
 Jason-0.169
ye-0.168
ock-0.167
Token.
Token ID13
Feature activation-2.78e-03

Pos logit contributions
mons+0.062
opard+0.057
aro+0.053
iw+0.052
 badly+0.052
Neg logit contributions
 Jason-0.056
 Gary-0.051
oby-0.049
 Simon-0.049
 Martin-0.049
Token
Token ID198
Feature activation-1.23e-02

Pos logit contributions
mons+0.005
opard+0.005
 badly+0.004
aro+0.004
iw+0.004
Neg logit contributions
 Jason-0.005
 Gary-0.005
oby-0.005
 Simon-0.005
Jason-0.005
Token
Token ID198
Feature activation+1.92e-02

Pos logit contributions
mons+0.024
opard+0.022
 badly+0.020
aro+0.020
drops+0.019
Neg logit contributions
 Jason-0.023
 Gary-0.022
oby-0.021
Jason-0.021
 Simon-0.020
TokenThey
Token ID2990
Feature activation-1.13e-03

Pos logit contributions
 Jason+0.039
 Gary+0.037
 Martin+0.035
oby+0.035
 Simon+0.035
Neg logit contributions
mons-0.033
opard-0.030
iw-0.027
aro-0.026
 badly-0.026
Token,
Token ID11
Feature activation+2.86e-02

Pos logit contributions
mons+0.042
opard+0.039
aro+0.038
iw+0.036
pre+0.035
Neg logit contributions
 Jason-0.036
 Gary-0.032
 Martin-0.031
oby-0.030
 Simon-0.030
Token Tyler
Token ID14886
Feature activation-3.20e-02

Pos logit contributions
 Gary+0.046
 Jason+0.046
oby+0.043
 Justin+0.042
 Martin+0.042
Neg logit contributions
mons-0.056
opard-0.051
 badly-0.050
aro-0.047
drops-0.045
Token chose
Token ID7690
Feature activation-5.59e-02

Pos logit contributions
mons+0.066
opard+0.062
aro+0.060
iw+0.057
 badly+0.055
Neg logit contributions
 Jason-0.057
 Gary-0.050
Jason-0.048
 Martin-0.048
 Simon-0.048
Token the
Token ID262
Feature activation-5.31e-02

Pos logit contributions
opard+0.123
mons+0.120
aro+0.119
drops+0.114
pre+0.112
Neg logit contributions
 Jason-0.075
 Gary-0.060
 Harry-0.058
 Simon-0.056
oby-0.056
Token best
Token ID1266
Feature activation-6.55e-02

Pos logit contributions
aro+0.106
mons+0.100
opard+0.096
ork+0.083
har+0.083
Neg logit contributions
 Jason-0.085
oby-0.072
Jason-0.072
 Justin-0.069
 Simon-0.068
Token-
Token ID12
Feature activation-9.60e-02

Pos logit contributions
opard+0.126
mons+0.124
aro+0.124
drops+0.109
lves+0.108
Neg logit contributions
 Jason-0.093
oby-0.087
 his-0.076
 Peter-0.076
 brothers-0.074
Tokenlooking
Token ID11534
Feature activation-5.95e-02

Pos logit contributions
sed+0.147
ses+0.139
ric+0.131
 slam+0.128
drops+0.127
Neg logit contributions
 Jason-0.158
oby-0.148
ye-0.139
Jason-0.138
 Harry-0.136
Token ice
Token ID4771
Feature activation-7.86e-02

Pos logit contributions
mons+0.101
aro+0.099
opard+0.096
har+0.085
drops+0.082
Neg logit contributions
 Jason-0.102
oby-0.091
 Gary-0.088
 Simon-0.086
 Justin-0.086
Token cream
Token ID8566
Feature activation-4.02e-02

Pos logit contributions
lves+0.120
aro+0.118
 Sy+0.110
rils+0.110
har+0.109
Neg logit contributions
oby-0.117
 Jason-0.115
ye-0.097
ji-0.096
 Justin-0.094
Token,
Token ID11
Feature activation-4.52e-02

Pos logit contributions
mons+0.062
aro+0.059
opard+0.059
 badly+0.055
har+0.053
Neg logit contributions
 Jason-0.078
 Gary-0.071
oby-0.070
 Simon-0.067
 Justin-0.066
Token with
Token ID351
Feature activation-8.23e-03

Pos logit contributions
mons+0.087
opard+0.085
aro+0.079
pre+0.071
iw+0.069
Neg logit contributions
 Jason-0.086
 Gary-0.076
 Simon-0.072
 Martin-0.071
 Harry-0.070
Token Tim
Token ID5045
Feature activation+9.94e-03

Pos logit contributions
 Jason+0.032
 Gary+0.031
oby+0.030
Jason+0.030
 Simon+0.029
Neg logit contributions
mons-0.020
opard-0.018
aro-0.016
 badly-0.016
iw-0.016
Token.
Token ID13
Feature activation+9.69e-03

Pos logit contributions
 Jason+0.022
 Gary+0.021
oby+0.020
Jason+0.019
 Simon+0.019
Neg logit contributions
mons-0.015
opard-0.014
 badly-0.013
iw-0.012
aro-0.012
Token Tim
Token ID5045
Feature activation-1.13e-02

Pos logit contributions
 Jason+0.021
 Gary+0.020
oby+0.019
Jason+0.019
 Simon+0.019
Neg logit contributions
mons-0.016
opard-0.014
aro-0.012
iw-0.012
 badly-0.012
Token loved
Token ID6151
Feature activation+1.32e-02

Pos logit contributions
mons+0.020
opard+0.018
aro+0.017
iw+0.016
 badly+0.016
Neg logit contributions
 Jason-0.023
 Gary-0.021
oby-0.020
Jason-0.020
 Martin-0.020
Token ice
Token ID4771
Feature activation-7.16e-02

Pos logit contributions
 Jason+0.034
 Gary+0.033
oby+0.032
Jason+0.032
 Simon+0.031
Neg logit contributions
mons-0.015
opard-0.013
aro-0.011
iw-0.011
 badly-0.011
Token-
Token ID12
Feature activation-9.57e-02

Pos logit contributions
aro+0.108
sed+0.107
mons+0.104
opard+0.104
rils+0.101
Neg logit contributions
 brothers-0.104
oby-0.102
 Jason-0.097
iny-0.096
ie-0.094
Tokencream
Token ID36277
Feature activation-3.94e-02

Pos logit contributions
sed+0.140
ses+0.131
opard+0.118
mons+0.116
 salon+0.114
Neg logit contributions
 Jason-0.155
oby-0.146
umper-0.142
iny-0.141
 his-0.138
Token so
Token ID523
Feature activation-2.98e-02

Pos logit contributions
mons+0.068
opard+0.062
aro+0.061
har+0.057
iw+0.055
Neg logit contributions
 Jason-0.070
 Gary-0.065
oby-0.064
 Simon-0.062
 Martin-0.061
Token much
Token ID881
Feature activation+7.95e-04

Pos logit contributions
mons+0.060
opard+0.054
drops+0.050
iw+0.048
pre+0.047
Neg logit contributions
 Jason-0.052
 Gary-0.049
oby-0.046
 Martin-0.045
 Simon-0.045
Token.
Token ID13
Feature activation+2.97e-03

Pos logit contributions
 Jason+0.002
 Gary+0.002
oby+0.002
 Simon+0.002
Jason+0.002
Neg logit contributions
mons-0.001
opard-0.001
aro-0.001
iw-0.001
 badly-0.001
Token One
Token ID1881
Feature activation-1.80e-02

Pos logit contributions
 Jason+0.004
 Gary+0.004
oby+0.004
Jason+0.004
 Simon+0.004
Neg logit contributions
mons-0.007
opard-0.006
aro-0.006
 badly-0.006
iw-0.006
Token a
Token ID257
Feature activation-1.20e-02

Pos logit contributions
 Jason+0.002
 Gary+0.002
oby+0.002
Jason+0.002
 Simon+0.002
Neg logit contributions
mons-0.002
opard-0.001
aro-0.001
 badly-0.001
iw-0.001
Token little
Token ID1310
Feature activation-6.25e-03

Pos logit contributions
mons+0.025
opard+0.022
aro+0.022
 badly+0.021
iw+0.021
Neg logit contributions
 Jason-0.020
 Gary-0.019
Jason-0.018
oby-0.017
 Martin-0.017
Token monkey
Token ID21657
Feature activation-5.20e-02

Pos logit contributions
mons+0.013
opard+0.012
aro+0.011
 badly+0.011
iw+0.011
Neg logit contributions
 Jason-0.010
 Gary-0.010
oby-0.009
 Simon-0.009
 Martin-0.009
Token named
Token ID3706
Feature activation+1.42e-02

Pos logit contributions
mons+0.096
drops+0.083
iw+0.073
opard+0.073
har+0.072
Neg logit contributions
 Gary-0.092
 Jason-0.088
iny-0.086
oby-0.085
 Harry-0.082
Token Max
Token ID5436
Feature activation+6.58e-03

Pos logit contributions
 Jason+0.028
 Gary+0.026
oby+0.026
Jason+0.026
 Simon+0.025
Neg logit contributions
mons-0.024
opard-0.022
aro-0.020
iw-0.020
 badly-0.020
Token.
Token ID13
Feature activation+7.85e-02

Pos logit contributions
 Jason+0.015
 Gary+0.014
oby+0.013
Jason+0.013
 Simon+0.013
Neg logit contributions
mons-0.010
opard-0.009
 badly-0.008
aro-0.008
iw-0.008
Token Max
Token ID5436
Feature activation-3.11e-03

Pos logit contributions
inda+0.144
oby+0.142
Jason+0.138
 Simon+0.136
ye+0.134
Neg logit contributions
mons-0.093
 bars-0.091
 Whe-0.085
 Sy-0.084
round-0.084
Token liked
Token ID8288
Feature activation+3.01e-03

Pos logit contributions
mons+0.005
opard+0.004
aro+0.004
iw+0.004
 badly+0.004
Neg logit contributions
 Jason-0.007
 Gary-0.006
oby-0.006
Jason-0.006
 Martin-0.006
Token to
Token ID284
Feature activation+1.40e-02

Pos logit contributions
 Jason+0.008
 Gary+0.007
oby+0.007
Jason+0.007
 Simon+0.007
Neg logit contributions
mons-0.004
opard-0.003
aro-0.003
 badly-0.003
iw-0.003
Token play
Token ID711
Feature activation+1.38e-02

Pos logit contributions
 Jason+0.028
 Gary+0.026
oby+0.025
Jason+0.025
 Simon+0.024
Neg logit contributions
mons-0.025
opard-0.022
aro-0.021
 badly-0.020
iw-0.020
Token in
Token ID287
Feature activation+2.10e-02

Pos logit contributions
 Jason+0.036
 Gary+0.034
Jason+0.034
oby+0.033
 Simon+0.033
Neg logit contributions
mons-0.016
opard-0.014
 badly-0.011
aro-0.011
iw-0.011
Token."
Token ID526
Feature activation+3.84e-02

Pos logit contributions
mons+0.002
opard+0.002
aro+0.002
iw+0.001
 badly+0.001
Neg logit contributions
 Jason-0.003
 Gary-0.003
oby-0.003
Jason-0.003
 Simon-0.003
Token said
Token ID531
Feature activation+1.22e-02

Pos logit contributions
oby+0.066
 Jason+0.065
 Gary+0.065
Jason+0.061
umper+0.060
Neg logit contributions
mons-0.062
 badly-0.057
opard-0.056
 bars-0.054
 muff-0.054
Token Mom
Token ID11254
Feature activation+1.78e-02

Pos logit contributions
 Jason+0.017
 Gary+0.016
oby+0.015
Jason+0.015
 Simon+0.014
Neg logit contributions
mons-0.027
opard-0.025
 badly-0.024
aro-0.024
iw-0.024
Token.
Token ID13
Feature activation+3.70e-02

Pos logit contributions
 Jason+0.040
 Gary+0.039
oby+0.037
Jason+0.037
 Martin+0.036
Neg logit contributions
mons-0.025
opard-0.023
 badly-0.021
aro-0.020
iw-0.020
Token
Token ID198
Feature activation+3.29e-02

Pos logit contributions
 Gary+0.078
oby+0.077
 Jason+0.077
Jason+0.073
umper+0.072
Neg logit contributions
mons-0.048
opard-0.040
 badly-0.038
round-0.037
iw-0.037
Token
Token ID198
Feature activation+6.03e-02

Pos logit contributions
 Jason+0.079
 Gary+0.078
oby+0.073
 Simon+0.073
 Justin+0.072
Neg logit contributions
mons-0.036
opard-0.032
 badly-0.029
 bars-0.027
aro-0.027
TokenJames
Token ID14731
Feature activation+8.35e-03

Pos logit contributions
 Gary+0.129
 Jason+0.123
umper+0.120
 Simon+0.120
 Harry+0.119
Neg logit contributions
 badly-0.067
round-0.066
Because-0.065
mons-0.065
opard-0.063
Token took
Token ID1718
Feature activation+1.86e-02

Pos logit contributions
 Jason+0.016
 Gary+0.016
oby+0.015
Jason+0.015
 Simon+0.015
Neg logit contributions
mons-0.014
opard-0.013
 badly-0.012
aro-0.012
iw-0.012
Token a
Token ID257
Feature activation+1.53e-02

Pos logit contributions
 Jason+0.037
 Gary+0.036
oby+0.036
Jason+0.035
 Simon+0.034
Neg logit contributions
mons-0.029
opard-0.026
 badly-0.025
aro-0.024
 bars-0.024
Token few
Token ID1178
Feature activation+1.98e-02

Pos logit contributions
 Jason+0.029
 Gary+0.028
oby+0.027
 Simon+0.026
Jason+0.026
Neg logit contributions
mons-0.027
opard-0.025
 badly-0.023
iw-0.022
aro-0.022
Token small
Token ID1402
Feature activation+2.75e-02

Pos logit contributions
 Jason+0.038
 Gary+0.036
oby+0.035
Jason+0.034
 Simon+0.034
Neg logit contributions
mons-0.035
opard-0.032
 badly-0.031
aro-0.030
iw-0.030
Tokenin
Token ID259
Feature activation-5.53e-02

Pos logit contributions
mons+0.063
drops+0.056
opard+0.055
 bars+0.052
round+0.052
Neg logit contributions
 Jason-0.039
oby-0.038
 Gary-0.037
Jason-0.035
 Simon-0.034
Token named
Token ID3706
Feature activation+6.68e-05

Pos logit contributions
mons+0.097
drops+0.081
iw+0.072
aro+0.071
opard+0.070
Neg logit contributions
oby-0.100
 Gary-0.099
 Jason-0.098
iny-0.093
 Simon-0.093
Token P
Token ID350
Feature activation+2.31e-02

Pos logit contributions
 Jason+0.000
 Gary+0.000
oby+0.000
 Simon+0.000
 Martin+0.000
Neg logit contributions
mons-0.000
opard-0.000
 badly-0.000
aro-0.000
iw-0.000
Tokenudd
Token ID4185
Feature activation-1.11e-02

Pos logit contributions
 Jason+0.047
 Gary+0.046
 Martin+0.042
 Simon+0.042
Jason+0.041
Neg logit contributions
mons-0.039
opard-0.036
 badly-0.032
iw-0.032
pre-0.031
Tokenles
Token ID829
Feature activation-5.12e-02

Pos logit contributions
mons+0.027
opard+0.025
iw+0.024
aro+0.024
 badly+0.024
Neg logit contributions
 Jason-0.013
 Gary-0.012
oby-0.012
 Simon-0.011
Jason-0.011
Token.
Token ID13
Feature activation+5.43e-02

Pos logit contributions
mons+0.107
iw+0.094
drops+0.091
opard+0.090
har+0.088
Neg logit contributions
 Jason-0.076
 Gary-0.073
oby-0.073
 Simon-0.070
 Martin-0.068
Token P
Token ID350
Feature activation+1.08e-02

Pos logit contributions
 Jason+0.113
Jason+0.110
 Gary+0.106
 Martin+0.104
oby+0.101
Neg logit contributions
mons-0.089
iw-0.073
opard-0.072
 fountain-0.063
 Sy-0.061
Tokenudd
Token ID4185
Feature activation-2.43e-03

Pos logit contributions
 Jason+0.024
 Gary+0.023
oby+0.021
 Martin+0.021
 Simon+0.021
Neg logit contributions
mons-0.017
opard-0.015
 badly-0.013
iw-0.013
aro-0.013
Tokenles
Token ID829
Feature activation-2.14e-02

Pos logit contributions
mons+0.006
opard+0.006
iw+0.005
aro+0.005
 badly+0.005
Neg logit contributions
 Jason-0.003
 Gary-0.003
oby-0.003
 Simon-0.003
Jason-0.003
Token loved
Token ID6151
Feature activation-3.89e-06

Pos logit contributions
mons+0.041
opard+0.036
iw+0.035
aro+0.034
drops+0.033
Neg logit contributions
 Jason-0.039
 Gary-0.036
oby-0.036
 Simon-0.035
 Martin-0.034
Token to
Token ID284
Feature activation+1.02e-02

Feature not active on prev token;
no predictions were affected.
Token it
Token ID340
Feature activation+2.19e-02

Pos logit contributions
 Jason+0.011
 Gary+0.010
oby+0.010
Jason+0.010
 Simon+0.009
Neg logit contributions
mons-0.017
opard-0.016
 badly-0.015
aro-0.015
iw-0.015
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
 Jason+0.054
Jason+0.051
 Gary+0.051
oby+0.050
 Simon+0.049
Neg logit contributions
mons-0.028
 badly-0.025
opard-0.024
 bars-0.022
aro-0.022
Token
Token ID220
Feature activation-1.14e-02

Pos logit contributions
mons+0.021
opard+0.019
aro+0.018
 badly+0.018
iw+0.017
Neg logit contributions
 Jason-0.021
 Gary-0.020
 Martin-0.018
 Simon-0.018
oby-0.018
Token
Token ID198
Feature activation-1.30e-02

Pos logit contributions
mons+0.021
opard+0.019
aro+0.017
iw+0.017
 badly+0.017
Neg logit contributions
 Jason-0.022
 Gary-0.021
oby-0.020
Jason-0.020
 Simon-0.020
Token
Token ID198
Feature activation+1.54e-02

Pos logit contributions
mons+0.025
opard+0.023
aro+0.021
iw+0.021
drops+0.020
Neg logit contributions
 Jason-0.024
 Gary-0.023
oby-0.022
Jason-0.022
 Martin-0.021
TokenThe
Token ID464
Feature activation+5.60e-02

Pos logit contributions
 Jason+0.034
 Gary+0.032
 Simon+0.031
oby+0.031
 Martin+0.031
Neg logit contributions
mons-0.023
opard-0.022
 badly-0.020
aro-0.019
round-0.018
Token hunter
Token ID19177
Feature activation-1.23e-02

Pos logit contributions
 Jason+0.122
oby+0.115
 Simon+0.113
Jason+0.107
 Justin+0.105
Neg logit contributions
opard-0.085
mons-0.073
 le-0.067
 badly-0.066
 pigeon-0.065
Token was
Token ID373
Feature activation-2.30e-02

Pos logit contributions
mons+0.024
opard+0.021
iw+0.019
aro+0.019
 badly+0.019
Neg logit contributions
 Jason-0.023
 Gary-0.022
oby-0.020
 Martin-0.020
 Simon-0.020
Token sad
Token ID6507
Feature activation-4.36e-03

Pos logit contributions
mons+0.047
opard+0.041
iw+0.037
pre+0.037
aro+0.035
Neg logit contributions
 Jason-0.043
 Gary-0.042
 Martin-0.038
 Simon-0.037
Jason-0.037
Token he
Token ID339
Feature activation-3.87e-03

Pos logit contributions
mons+0.007
opard+0.006
aro+0.006
iw+0.006
round+0.005
Neg logit contributions
 Jason-0.009
 Gary-0.009
oby-0.009
 Simon-0.008
 Martin-0.008
Token didn
Token ID1422
Feature activation+2.27e-03

Pos logit contributions
mons+0.007
opard+0.006
aro+0.006
iw+0.006
 badly+0.006
Neg logit contributions
 Jason-0.007
 Gary-0.007
oby-0.007
 Simon-0.007
 Martin-0.007
Token
Token ID198
Feature activation+1.86e-02

Pos logit contributions
 Jason+0.034
 Gary+0.033
oby+0.032
 Martin+0.031
 Simon+0.031
Neg logit contributions
mons-0.022
opard-0.020
 badly-0.018
aro-0.018
iw-0.017
TokenBut
Token ID1537
Feature activation+1.29e-03

Pos logit contributions
 Jason+0.041
 Gary+0.040
oby+0.038
 Simon+0.038
 Martin+0.037
Neg logit contributions
mons-0.028
opard-0.026
 badly-0.024
aro-0.023
iw-0.022
Token Tom
Token ID4186
Feature activation+4.01e-04

Pos logit contributions
 Jason+0.003
 Gary+0.002
oby+0.002
Jason+0.002
 Simon+0.002
Neg logit contributions
mons-0.002
opard-0.002
aro-0.002
iw-0.002
 badly-0.002
Token didn
Token ID1422
Feature activation+8.20e-03

Pos logit contributions
 Jason+0.001
 Gary+0.001
oby+0.001
Jason+0.001
 Simon+0.001
Neg logit contributions
mons-0.001
opard-0.001
aro-0.001
iw-0.001
 badly-0.001
Token't
Token ID470
Feature activation-2.37e-04

Pos logit contributions
 Jason+0.022
 Gary+0.021
oby+0.020
Jason+0.020
 Simon+0.020
Neg logit contributions
mons-0.009
opard-0.007
 badly-0.006
aro-0.006
iw-0.006
Token laugh
Token ID6487
Feature activation+5.45e-02

Pos logit contributions
mons+0.000
opard+0.000
aro+0.000
iw+0.000
 badly+0.000
Neg logit contributions
 Jason-0.000
 Gary-0.000
oby-0.000
 Simon-0.000
Jason-0.000
Token.
Token ID13
Feature activation+3.70e-03

Pos logit contributions
 Jason+0.151
 Gary+0.148
Jason+0.146
 Simon+0.142
 Martin+0.141
Neg logit contributions
 badly-0.050
mons-0.035
opard-0.028
 bars-0.025
drops-0.025
Token He
Token ID679
Feature activation-3.94e-02

Pos logit contributions
 Jason+0.005
 Gary+0.005
oby+0.004
Jason+0.004
 Simon+0.004
Neg logit contributions
mons-0.009
opard-0.008
aro-0.008
 badly-0.008
iw-0.008
Token pushed
Token ID7121
Feature activation+1.29e-02

Pos logit contributions
mons+0.083
opard+0.073
iw+0.072
aro+0.071
round+0.066
Neg logit contributions
 Jason-0.063
 Gary-0.060
oby-0.057
Jason-0.054
 Simon-0.054
Token her
Token ID607
Feature activation-8.37e-05

Pos logit contributions
 Jason+0.021
 Gary+0.020
oby+0.019
Jason+0.018
 Martin+0.018
Neg logit contributions
mons-0.027
opard-0.025
 badly-0.024
aro-0.023
iw-0.023
Token away
Token ID1497
Feature activation+9.70e-04

Pos logit contributions
mons+0.000
opard+0.000
aro+0.000
iw+0.000
 badly+0.000
Neg logit contributions
 Jason-0.000
 Gary-0.000
oby-0.000
 Simon-0.000
 Martin-0.000
Token to
Token ID284
Feature activation+2.33e-02

Pos logit contributions
mons+0.030
opard+0.030
aro+0.027
round+0.025
iw+0.025
Neg logit contributions
 Jason-0.038
 Gary-0.035
 Simon-0.034
Jason-0.034
oby-0.033
Token draw
Token ID3197
Feature activation+2.20e-02

Pos logit contributions
 Gary+0.043
 Jason+0.043
oby+0.041
 Justin+0.039
Jason+0.039
Neg logit contributions
mons-0.039
 badly-0.034
opard-0.034
 bars-0.033
 cherry-0.032
Token with
Token ID351
Feature activation+1.59e-02

Pos logit contributions
 Jason+0.050
 Gary+0.049
oby+0.046
Jason+0.046
 Simon+0.045
Neg logit contributions
mons-0.031
opard-0.026
 badly-0.025
 bars-0.025
aro-0.023
Token chalk
Token ID30860
Feature activation+2.68e-02

Pos logit contributions
 Jason+0.025
 Gary+0.024
oby+0.023
Jason+0.022
 Martin+0.022
Neg logit contributions
mons-0.034
opard-0.030
 badly-0.029
aro-0.028
iw-0.028
Token.
Token ID13
Feature activation+4.45e-03

Pos logit contributions
 Jason+0.064
 Gary+0.063
Jason+0.060
oby+0.060
 Simon+0.059
Neg logit contributions
mons-0.038
opard-0.031
 bars-0.029
iw-0.027
drops-0.027
Token One
Token ID1881
Feature activation+5.65e-03

Pos logit contributions
 Jason+0.008
 Gary+0.008
oby+0.007
Jason+0.007
 Simon+0.007
Neg logit contributions
mons-0.008
opard-0.008
aro-0.007
 badly-0.007
iw-0.007
Token day
Token ID1110
Feature activation-1.36e-02

Pos logit contributions
 Jason+0.009
 Gary+0.008
oby+0.007
Jason+0.007
 Simon+0.007
Neg logit contributions
mons-0.013
opard-0.012
 badly-0.011
aro-0.011
iw-0.011
Token,
Token ID11
Feature activation-1.71e-02

Pos logit contributions
mons+0.027
opard+0.026
iw+0.024
aro+0.023
round+0.023
Neg logit contributions
 Jason-0.023
 Gary-0.022
 Simon-0.021
oby-0.020
 Martin-0.020
Token M
Token ID337
Feature activation+1.44e-02

Pos logit contributions
mons+0.038
opard+0.037
round+0.034
aro+0.034
 badly+0.034
Neg logit contributions
 Jason-0.025
 Gary-0.024
 Simon-0.023
oby-0.022
 Justin-0.022
Tokenandy
Token ID10757
Feature activation-3.27e-04

Pos logit contributions
 Jason+0.017
 Gary+0.015
 Martin+0.014
Jason+0.014
 Simon+0.013
Neg logit contributions
mons-0.038
opard-0.036
iw-0.033
aro-0.033
 badly-0.033
Token was
Token ID373
Feature activation-2.39e-02

Pos logit contributions
mons+0.001
opard+0.001
aro+0.001
 badly+0.001
iw+0.001
Neg logit contributions
 Jason-0.001
 Gary-0.001
oby-0.001
Jason-0.001
 Simon-0.001
Token smiled
Token ID13541
Feature activation+4.62e-02

Pos logit contributions
 Jason+0.055
 Gary+0.054
oby+0.053
 Martin+0.050
 Simon+0.050
Neg logit contributions
mons-0.044
opard-0.040
 badly-0.039
iw-0.037
 bars-0.037
Token and
Token ID290
Feature activation+1.19e-02

Pos logit contributions
 Gary+0.131
 Jason+0.129
Jason+0.126
oby+0.125
Gary+0.123
Neg logit contributions
 badly-0.033
mons-0.021
opard-0.017
 cherry-0.014
pre-0.013
Token told
Token ID1297
Feature activation+1.14e-02

Pos logit contributions
 Jason+0.020
 Gary+0.019
oby+0.019
Jason+0.018
 Martin+0.017
Neg logit contributions
mons-0.024
opard-0.022
aro-0.020
iw-0.020
 badly-0.020
Token him
Token ID683
Feature activation-2.40e-02

Pos logit contributions
 Jason+0.016
 Gary+0.015
oby+0.014
Jason+0.014
 Simon+0.013
Neg logit contributions
mons-0.026
opard-0.024
 badly-0.023
aro-0.023
iw-0.023
Token it
Token ID340
Feature activation+6.82e-03

Pos logit contributions
mons+0.040
opard+0.036
iw+0.034
aro+0.031
pre+0.031
Neg logit contributions
 Jason-0.052
 Gary-0.050
 Simon-0.046
 Martin-0.046
oby-0.046
Token was
Token ID373
Feature activation+4.17e-02

Pos logit contributions
 Jason+0.016
 Gary+0.015
oby+0.014
Jason+0.014
 Simon+0.014
Neg logit contributions
mons-0.010
opard-0.009
 badly-0.008
aro-0.008
iw-0.007
Token okay
Token ID8788
Feature activation-1.19e-02

Pos logit contributions
 Gary+0.083
 Jason+0.083
oby+0.082
Jason+0.080
 Simon+0.078
Neg logit contributions
 badly-0.062
mons-0.057
 cherry-0.049
opard-0.047
 Twe-0.046
Token.
Token ID13
Feature activation+5.85e-03

Pos logit contributions
mons+0.021
opard+0.020
aro+0.018
iw+0.018
round+0.017
Neg logit contributions
 Jason-0.023
 Gary-0.022
oby-0.022
 Simon-0.021
 Martin-0.020
Token She
Token ID1375
Feature activation+3.62e-03

Pos logit contributions
 Jason+0.010
 Gary+0.010
oby+0.009
Jason+0.009
 Simon+0.009
Neg logit contributions
mons-0.012
opard-0.011
 badly-0.010
aro-0.010
iw-0.010
Token said
Token ID531
Feature activation-5.01e-03

Pos logit contributions
 Jason+0.006
 Gary+0.006
oby+0.005
Jason+0.005
 Simon+0.005
Neg logit contributions
mons-0.007
opard-0.007
aro-0.006
 badly-0.006
iw-0.006
Token he
Token ID339
Feature activation-1.19e-02

Pos logit contributions
mons+0.008
opard+0.008
iw+0.007
aro+0.007
 badly+0.006
Neg logit contributions
 Jason-0.011
 Gary-0.010
 Simon-0.009
oby-0.009
 Martin-0.009
Token Max
Token ID5436
Feature activation-2.51e-02

Pos logit contributions
 Jason+0.056
oby+0.055
 Gary+0.054
Jason+0.052
 Simon+0.051
Neg logit contributions
mons-0.051
opard-0.045
 badly-0.043
iw-0.040
 Sy-0.040
Token said
Token ID531
Feature activation+1.77e-02

Pos logit contributions
mons+0.051
opard+0.046
aro+0.045
iw+0.044
 badly+0.043
Neg logit contributions
 Jason-0.043
 Gary-0.041
oby-0.038
 Martin-0.037
Jason-0.037
Token he
Token ID339
Feature activation-3.39e-02

Pos logit contributions
 Jason+0.035
oby+0.033
 Gary+0.033
Jason+0.032
 Simon+0.031
Neg logit contributions
mons-0.030
opard-0.027
 badly-0.027
aro-0.026
 cherry-0.024
Token would
Token ID561
Feature activation-2.03e-02

Pos logit contributions
mons+0.070
aro+0.068
opard+0.063
iw+0.062
round+0.062
Neg logit contributions
 Jason-0.054
 Gary-0.050
oby-0.048
Jason-0.047
 Martin-0.045
Token listen
Token ID6004
Feature activation+5.02e-03

Pos logit contributions
mons+0.042
opard+0.038
aro+0.036
iw+0.034
pre+0.033
Neg logit contributions
 Jason-0.035
 Gary-0.034
 Simon-0.031
 Martin-0.031
oby-0.031
Token sometimes
Token ID3360
Feature activation+2.91e-02

Pos logit contributions
 Jason+0.012
 Gary+0.012
oby+0.012
Jason+0.011
 Simon+0.011
Neg logit contributions
mons-0.006
opard-0.005
 badly-0.005
aro-0.005
iw-0.005
Token and
Token ID290
Feature activation+1.25e-02

Pos logit contributions
 Jason+0.069
oby+0.067
 Gary+0.067
Jason+0.065
 Simon+0.063
Neg logit contributions
mons-0.035
 badly-0.032
opard-0.030
 bars-0.027
 fountain-0.026
Token not
Token ID407
Feature activation+8.66e-03

Pos logit contributions
 Jason+0.024
 Gary+0.022
oby+0.022
Jason+0.021
 Simon+0.021
Neg logit contributions
mons-0.023
opard-0.020
 badly-0.019
aro-0.019
iw-0.019
Token be
Token ID307
Feature activation+1.25e-03

Pos logit contributions
 Jason+0.017
 Gary+0.016
oby+0.016
Jason+0.015
 Simon+0.015
Neg logit contributions
mons-0.015
opard-0.014
 badly-0.013
aro-0.013
iw-0.012
Token mean
Token ID1612
Feature activation+5.60e-03

Pos logit contributions
 Jason+0.002
 Gary+0.002
oby+0.002
Jason+0.002
 Simon+0.002
Neg logit contributions
mons-0.002
opard-0.002
aro-0.002
iw-0.002
 badly-0.002
Token.
Token ID13
Feature activation+2.98e-02

Pos logit contributions
 Jason+0.013
 Gary+0.013
oby+0.012
Jason+0.012
 Simon+0.012
Neg logit contributions
mons-0.008
opard-0.007
 badly-0.006
aro-0.006
iw-0.006
Token
Token ID26391
Feature activation-3.42e-02

Pos logit contributions
mons+0.025
opard+0.022
aro+0.021
 badly+0.021
iw+0.020
Neg logit contributions
 Jason-0.026
 Gary-0.024
oby-0.024
Jason-0.023
 Martin-0.023
Token
Token ID129
Feature activation+7.36e-04

Pos logit contributions
mons+0.062
opard+0.054
aro+0.052
iw+0.052
 cherry+0.050
Neg logit contributions
 Jason-0.070
 Gary-0.064
Jason-0.063
 Simon-0.061
 Martin-0.061
Token
Token ID241
Feature activation-5.70e-02

Pos logit contributions
 Jason+0.001
 Gary+0.001
oby+0.001
Jason+0.001
 Simon+0.001
Neg logit contributions
mons-0.001
opard-0.001
aro-0.001
iw-0.001
 badly-0.001
TokenLittle
Token ID22253
Feature activation+1.99e-02

Pos logit contributions
mons+0.117
opard+0.100
aro+0.097
iw+0.094
 bars+0.094
Neg logit contributions
 Jason-0.103
oby-0.099
Jason-0.094
 Simon-0.091
 Gary-0.090
Token boy
Token ID2933
Feature activation-2.95e-02

Pos logit contributions
 Jason+0.036
 Gary+0.035
oby+0.033
Jason+0.033
 Simon+0.032
Neg logit contributions
mons-0.036
opard-0.033
 badly-0.031
aro-0.030
iw-0.029
Token,
Token ID11
Feature activation+4.21e-03

Pos logit contributions
mons+0.058
opard+0.050
iw+0.046
aro+0.046
drops+0.045
Neg logit contributions
 Jason-0.055
 Gary-0.052
 Simon-0.049
oby-0.049
 Martin-0.048
Token the
Token ID262
Feature activation+1.38e-02

Pos logit contributions
 Jason+0.008
 Gary+0.008
oby+0.008
Jason+0.007
 Simon+0.007
Neg logit contributions
mons-0.007
opard-0.007
aro-0.006
 badly-0.006
iw-0.006
Token harbor
Token ID25451
Feature activation-1.40e-02

Pos logit contributions
 Jason+0.027
 Gary+0.026
oby+0.025
Jason+0.024
 Simon+0.023
Neg logit contributions
mons-0.024
opard-0.023
aro-0.020
 badly-0.020
 fountain-0.020
Token is
Token ID318
Feature activation+1.42e-02

Pos logit contributions
mons+0.024
opard+0.021
iw+0.019
aro+0.019
 badly+0.019
Neg logit contributions
 Jason-0.029
 Gary-0.028
oby-0.027
 Simon-0.026
 Martin-0.026
Token full
Token ID1336
Feature activation+2.40e-02

Pos logit contributions
 Jason+0.030
 Gary+0.029
oby+0.028
Jason+0.027
 Martin+0.027
Neg logit contributions
mons-0.022
opard-0.020
 badly-0.019
aro-0.018
iw-0.018
Token of
Token ID286
Feature activation+8.02e-03

Pos logit contributions
 Jason+0.052
 Gary+0.050
Jason+0.048
oby+0.047
 Martin+0.046
Neg logit contributions
mons-0.037
opard-0.033
 badly-0.030
aro-0.030
iw-0.029
Tokenmy
Token ID1820
Feature activation+1.44e-02

Pos logit contributions
 Jason+0.083
 Gary+0.082
 Martin+0.080
 Simon+0.076
Jason+0.075
Neg logit contributions
mons-0.078
opard-0.073
 bars-0.073
 badly-0.072
drops-0.072
Token heard
Token ID2982
Feature activation+1.93e-02

Pos logit contributions
 Jason+0.028
 Gary+0.026
oby+0.026
Jason+0.025
 Martin+0.025
Neg logit contributions
mons-0.025
opard-0.023
aro-0.021
 badly-0.021
iw-0.020
Token Lily
Token ID20037
Feature activation+1.44e-02

Pos logit contributions
 Jason+0.038
 Gary+0.036
oby+0.036
Jason+0.035
 Martin+0.034
Neg logit contributions
mons-0.032
 badly-0.027
opard-0.027
aro-0.026
 cherry-0.026
Token's
Token ID338
Feature activation+1.62e-02

Pos logit contributions
 Jason+0.030
 Gary+0.029
oby+0.028
Jason+0.027
 Simon+0.027
Neg logit contributions
mons-0.023
opard-0.021
 badly-0.020
aro-0.019
 bars-0.019
Token scream
Token ID8196
Feature activation+4.12e-02

Pos logit contributions
 Jason+0.033
 Gary+0.031
oby+0.030
Jason+0.030
 Martin+0.029
Neg logit contributions
mons-0.027
opard-0.024
 badly-0.023
aro-0.022
 bars-0.022
Token and
Token ID290
Feature activation+2.13e-02

Pos logit contributions
 Jason+0.108
 Gary+0.105
Jason+0.104
oby+0.102
 Martin+0.100
Neg logit contributions
 badly-0.040
mons-0.038
drops-0.031
opard-0.030
 bars-0.030
Token ran
Token ID4966
Feature activation-2.22e-02

Pos logit contributions
 Jason+0.043
oby+0.041
 Gary+0.040
Jason+0.039
 Martin+0.038
Neg logit contributions
mons-0.034
opard-0.030
aro-0.030
 badly-0.029
iw-0.028
Token to
Token ID284
Feature activation-1.17e-02

Pos logit contributions
mons+0.039
opard+0.036
iw+0.032
aro+0.031
pre+0.031
Neg logit contributions
 Jason-0.044
 Gary-0.043
oby-0.040
 Martin-0.039
 Simon-0.039
Token the
Token ID262
Feature activation-6.93e-03

Pos logit contributions
mons+0.027
opard+0.026
aro+0.023
iw+0.023
round+0.023
Neg logit contributions
 Jason-0.018
 Gary-0.017
 Simon-0.015
 Martin-0.015
oby-0.015
Token table
Token ID3084
Feature activation-2.39e-04

Pos logit contributions
mons+0.014
opard+0.013
aro+0.013
iw+0.012
 badly+0.012
Neg logit contributions
 Jason-0.012
 Gary-0.011
oby-0.010
Jason-0.010
 Simon-0.010
Token.
Token ID13
Feature activation-1.72e-04

Pos logit contributions
mons+0.000
opard+0.000
aro+0.000
iw+0.000
 badly+0.000
Neg logit contributions
 Jason-0.001
 Gary-0.000
oby-0.000
 Simon-0.000
Jason-0.000
Token many
Token ID867
Feature activation-3.98e-03

Pos logit contributions
mons+0.026
opard+0.024
round+0.022
iw+0.021
 bars+0.021
Neg logit contributions
 Jason-0.028
 Gary-0.027
 Simon-0.025
oby-0.024
 Justin-0.024
Token new
Token ID649
Feature activation-1.71e-02

Pos logit contributions
mons+0.007
opard+0.007
aro+0.006
 badly+0.006
iw+0.006
Neg logit contributions
 Jason-0.007
 Gary-0.007
oby-0.007
 Simon-0.006
 Martin-0.006
Token things
Token ID1243
Feature activation+4.12e-03

Pos logit contributions
mons+0.033
opard+0.032
aro+0.029
round+0.028
 badly+0.028
Neg logit contributions
 Gary-0.028
 Jason-0.028
oby-0.026
 Simon-0.025
 Martin-0.025
Token to
Token ID284
Feature activation-8.40e-03

Pos logit contributions
 Jason+0.009
 Gary+0.009
oby+0.008
Jason+0.008
 Simon+0.008
Neg logit contributions
mons-0.006
opard-0.006
aro-0.005
 badly-0.005
iw-0.005
Token eat
Token ID4483
Feature activation-1.93e-03

Pos logit contributions
mons+0.016
opard+0.015
aro+0.014
 badly+0.013
iw+0.013
Neg logit contributions
 Jason-0.015
 Gary-0.015
oby-0.014
 Simon-0.014
 Martin-0.013
Token.
Token ID13
Feature activation-1.86e-02

Pos logit contributions
mons+0.003
opard+0.003
aro+0.003
 badly+0.003
iw+0.003
Neg logit contributions
 Jason-0.004
 Gary-0.004
oby-0.004
 Simon-0.004
Jason-0.004
Token From
Token ID3574
Feature activation-5.80e-03

Pos logit contributions
mons+0.040
opard+0.037
aro+0.035
pre+0.034
 badly+0.033
Neg logit contributions
 Jason-0.031
 Gary-0.030
 Martin-0.028
 Simon-0.027
 Justin-0.027
Token that
Token ID326
Feature activation+3.38e-02

Pos logit contributions
mons+0.009
opard+0.008
aro+0.007
iw+0.007
 badly+0.007
Neg logit contributions
 Jason-0.013
 Gary-0.013
oby-0.012
 Simon-0.012
 Martin-0.012
Token day
Token ID1110
Feature activation+3.75e-02

Pos logit contributions
 Jason+0.067
Jason+0.063
 Gary+0.061
oby+0.060
 Martin+0.058
Neg logit contributions
opard-0.052
mons-0.052
iw-0.047
 cherry-0.047
 badly-0.046
Token on
Token ID319
Feature activation+9.84e-03

Pos logit contributions
 Jason+0.087
oby+0.084
 Gary+0.083
Jason+0.082
die+0.080
Neg logit contributions
mons-0.047
opard-0.044
 badly-0.043
aro-0.041
t-0.036
Token,
Token ID11
Feature activation-2.57e-02

Pos logit contributions
 Jason+0.020
 Gary+0.019
oby+0.019
Jason+0.019
 Simon+0.018
Neg logit contributions
mons-0.016
opard-0.015
 badly-0.013
aro-0.013
iw-0.013
Token.
Token ID13
Feature activation-6.13e-03

Pos logit contributions
mons+0.014
opard+0.013
aro+0.012
iw+0.012
 badly+0.011
Neg logit contributions
 Jason-0.017
 Gary-0.016
oby-0.015
 Simon-0.015
 Martin-0.015
Token
Token ID220
Feature activation-2.00e-02

Pos logit contributions
mons+0.012
opard+0.011
aro+0.010
 badly+0.010
iw+0.010
Neg logit contributions
 Jason-0.011
 Gary-0.011
oby-0.010
 Martin-0.010
 Simon-0.010
Token
Token ID198
Feature activation-1.22e-02

Pos logit contributions
mons+0.037
opard+0.035
aro+0.032
iw+0.031
drops+0.031
Neg logit contributions
 Jason-0.037
 Gary-0.035
oby-0.033
Jason-0.033
 Simon-0.032
Token
Token ID198
Feature activation+7.82e-03

Pos logit contributions
mons+0.023
opard+0.021
aro+0.019
iw+0.019
drops+0.019
Neg logit contributions
 Jason-0.023
 Gary-0.022
oby-0.021
Jason-0.021
 Simon-0.020
TokenAs
Token ID1722
Feature activation-2.78e-03

Pos logit contributions
 Jason+0.015
 Gary+0.014
oby+0.014
 Simon+0.013
 Martin+0.013
Neg logit contributions
mons-0.014
opard-0.013
 badly-0.012
aro-0.012
iw-0.012
Token she
Token ID673
Feature activation-2.13e-02

Pos logit contributions
mons+0.005
opard+0.005
aro+0.004
iw+0.004
 badly+0.004
Neg logit contributions
 Jason-0.005
 Gary-0.005
oby-0.005
 Simon-0.005
 Martin-0.005
Token walked
Token ID6807
Feature activation-3.42e-03

Pos logit contributions
mons+0.038
opard+0.036
aro+0.033
 badly+0.033
iw+0.032
Neg logit contributions
 Jason-0.038
 Gary-0.036
oby-0.035
Jason-0.033
 Simon-0.033
Token,
Token ID11
Feature activation-3.70e-02

Pos logit contributions
mons+0.006
opard+0.006
 badly+0.005
aro+0.005
iw+0.005
Neg logit contributions
 Jason-0.006
 Gary-0.006
oby-0.006
 Martin-0.006
 Simon-0.006
Token she
Token ID673
Feature activation-8.92e-03

Pos logit contributions
mons+0.091
opard+0.090
round+0.084
iw+0.083
aro+0.083
Neg logit contributions
 Jason-0.050
 Gary-0.045
 Emily-0.043
 Martin-0.041
 Simon-0.040
Token saw
Token ID2497
Feature activation-1.39e-02

Pos logit contributions
mons+0.017
opard+0.016
aro+0.015
 badly+0.014
iw+0.014
Neg logit contributions
 Jason-0.016
 Gary-0.015
Jason-0.015
oby-0.014
 Simon-0.014
Token a
Token ID257
Feature activation-2.57e-02

Pos logit contributions
mons+0.027
opard+0.026
iw+0.023
aro+0.023
round+0.023
Neg logit contributions
 Jason-0.025
 Gary-0.024
oby-0.022
 Simon-0.022
 Martin-0.022
TokenOnce
Token ID7454
Feature activation+1.79e-02

Pos logit contributions
mons+0.024
opard+0.022
aro+0.020
 badly+0.020
iw+0.020
Neg logit contributions
 Jason-0.025
 Gary-0.024
oby-0.023
 Martin-0.022
Jason-0.022
Token upon
Token ID2402
Feature activation-2.33e-02

Pos logit contributions
 Jason+0.033
 Gary+0.031
oby+0.030
Jason+0.030
 Martin+0.029
Neg logit contributions
mons-0.033
opard-0.030
 badly-0.029
aro-0.028
iw-0.027
Token a
Token ID257
Feature activation+5.54e-03

Pos logit contributions
mons+0.048
opard+0.043
aro+0.042
iw+0.040
drops+0.039
Neg logit contributions
 Jason-0.041
 Gary-0.039
Jason-0.037
oby-0.037
 Martin-0.036
Token time
Token ID640
Feature activation-1.45e-02

Pos logit contributions
 Jason+0.007
 Gary+0.007
oby+0.006
Jason+0.006
 Simon+0.006
Neg logit contributions
mons-0.013
opard-0.013
 badly-0.012
aro-0.012
iw-0.012
Token,
Token ID11
Feature activation+1.42e-03

Pos logit contributions
mons+0.029
opard+0.027
iw+0.024
drops+0.024
aro+0.024
Neg logit contributions
 Jason-0.025
 Gary-0.024
oby-0.022
 Simon-0.022
 Martin-0.022
Token there
Token ID612
Feature activation-1.69e-02

Pos logit contributions
 Jason+0.003
 Gary+0.003
oby+0.003
Jason+0.003
 Simon+0.003
Neg logit contributions
mons-0.002
opard-0.002
aro-0.002
iw-0.002
 badly-0.002
Token was
Token ID373
Feature activation+5.06e-03

Pos logit contributions
mons+0.030
opard+0.027
aro+0.025
iw+0.025
drops+0.024
Neg logit contributions
 Jason-0.034
 Gary-0.032
oby-0.031
 Simon-0.030
 Martin-0.030
Token a
Token ID257
Feature activation-1.18e-02

Pos logit contributions
 Jason+0.011
 Gary+0.010
oby+0.010
Jason+0.010
 Simon+0.010
Neg logit contributions
mons-0.008
opard-0.007
 badly-0.006
aro-0.006
iw-0.006
Token big
Token ID1263
Feature activation+3.20e-03

Pos logit contributions
mons+0.025
opard+0.022
aro+0.022
iw+0.021
 badly+0.021
Neg logit contributions
 Jason-0.020
 Gary-0.018
Jason-0.017
oby-0.017
 Martin-0.017
Token,
Token ID11
Feature activation+2.55e-02

Pos logit contributions
 Jason+0.006
 Gary+0.006
oby+0.006
Jason+0.006
 Simon+0.006
Neg logit contributions
mons-0.006
opard-0.005
aro-0.005
 badly-0.005
iw-0.005
Token rough
Token ID5210
Feature activation-2.49e-02

Pos logit contributions
 Jason+0.050
 Gary+0.048
oby+0.048
 Simon+0.045
Jason+0.045
Neg logit contributions
mons-0.042
opard-0.040
 badly-0.037
 cherry-0.036
iw-0.035
Token an
Token ID281
Feature activation-1.54e-03

Pos logit contributions
 Jason+0.008
 Gary+0.008
oby+0.007
Jason+0.007
 Simon+0.007
Neg logit contributions
mons-0.007
opard-0.006
aro-0.006
 badly-0.006
iw-0.006
Token orange
Token ID10912
Feature activation-4.27e-02

Pos logit contributions
mons+0.003
opard+0.003
aro+0.003
iw+0.003
 badly+0.003
Neg logit contributions
 Jason-0.003
 Gary-0.002
oby-0.002
 Simon-0.002
 Martin-0.002
Token flower
Token ID15061
Feature activation-2.94e-02

Pos logit contributions
mons+0.078
opard+0.068
aro+0.068
har+0.064
 badly+0.064
Neg logit contributions
 Gary-0.071
 Jason-0.071
oby-0.068
 Simon-0.065
 Martin-0.064
Token,
Token ID11
Feature activation+1.73e-03

Pos logit contributions
mons+0.048
opard+0.043
aro+0.039
iw+0.038
 badly+0.038
Neg logit contributions
 Jason-0.059
 Gary-0.057
 Simon-0.053
oby-0.053
 Martin-0.053
Token sweet
Token ID6029
Feature activation+1.83e-02

Pos logit contributions
 Jason+0.003
 Gary+0.003
oby+0.003
Jason+0.003
 Simon+0.003
Neg logit contributions
mons-0.003
opard-0.003
aro-0.003
 badly-0.003
iw-0.003
Tokenie
Token ID494
Feature activation-1.02e-02

Pos logit contributions
 Jason+0.021
 Gary+0.020
Jason+0.018
oby+0.017
 Martin+0.017
Neg logit contributions
mons-0.047
opard-0.044
 badly-0.042
iw-0.041
aro-0.041
Token,"
Token ID553
Feature activation+1.89e-02

Pos logit contributions
mons+0.016
opard+0.013
aro+0.012
iw+0.012
 badly+0.012
Neg logit contributions
 Jason-0.023
 Gary-0.022
oby-0.021
 Simon-0.021
 Martin-0.020
Token Mom
Token ID11254
Feature activation+4.18e-02

Pos logit contributions
 Jason+0.035
 Gary+0.034
oby+0.033
Jason+0.032
 Martin+0.031
Neg logit contributions
mons-0.033
opard-0.030
 badly-0.029
aro-0.028
iw-0.027
Tokenmy
Token ID1820
Feature activation+2.27e-02

Pos logit contributions
 Gary+0.064
 Jason+0.063
 Martin+0.059
Jason+0.058
oby+0.056
Neg logit contributions
mons-0.083
iw-0.076
opard-0.075
round-0.075
 badly-0.073
Token said
Token ID531
Feature activation-9.67e-03

Pos logit contributions
 Jason+0.038
 Gary+0.036
oby+0.035
Jason+0.034
 Martin+0.033
Neg logit contributions
mons-0.045
opard-0.041
aro-0.039
iw-0.038
 badly-0.038
Token.
Token ID13
Feature activation-3.69e-03

Pos logit contributions
mons+0.017
opard+0.016
iw+0.014
aro+0.014
 badly+0.013
Neg logit contributions
 Jason-0.020
 Gary-0.018
 Simon-0.017
 Martin-0.017
oby-0.017
Token was
Token ID373
Feature activation-8.08e-03

Pos logit contributions
mons+0.004
opard+0.004
aro+0.004
iw+0.004
 badly+0.003
Neg logit contributions
 Jason-0.005
 Gary-0.005
oby-0.005
 Simon-0.005
Jason-0.005
Token very
Token ID845
Feature activation-2.72e-03

Pos logit contributions
mons+0.014
opard+0.012
iw+0.011
aro+0.011
pre+0.010
Neg logit contributions
 Jason-0.017
 Gary-0.016
 Martin-0.015
oby-0.015
 Simon-0.015
Token sad
Token ID6507
Feature activation-1.73e-03

Pos logit contributions
mons+0.005
opard+0.004
aro+0.004
iw+0.004
round+0.004
Neg logit contributions
 Jason-0.006
 Gary-0.005
oby-0.005
 Simon-0.005
Jason-0.005
Token.
Token ID13
Feature activation-1.57e-02

Pos logit contributions
mons+0.003
opard+0.003
aro+0.002
iw+0.002
 badly+0.002
Neg logit contributions
 Jason-0.004
 Gary-0.003
oby-0.003
 Simon-0.003
 Martin-0.003
Token
Token ID198
Feature activation-1.42e-02

Pos logit contributions
mons+0.035
opard+0.032
aro+0.030
drops+0.030
pre+0.030
Neg logit contributions
 Jason-0.024
 Gary-0.023
oby-0.021
 Simon-0.021
 Martin-0.021
Token
Token ID198
Feature activation-4.69e-03

Pos logit contributions
mons+0.028
opard+0.025
drops+0.023
iw+0.023
pre+0.022
Neg logit contributions
 Jason-0.026
 Gary-0.025
oby-0.024
Jason-0.023
 Simon-0.023
TokenBob
Token ID18861
Feature activation+2.62e-02

Pos logit contributions
mons+0.009
opard+0.008
iw+0.008
aro+0.007
drops+0.007
Neg logit contributions
 Jason-0.008
 Gary-0.008
oby-0.008
Jason-0.008
 Martin-0.007
Token's
Token ID338
Feature activation-6.98e-03

Pos logit contributions
 Jason+0.052
 Gary+0.050
oby+0.049
Jason+0.048
 Simon+0.046
Neg logit contributions
mons-0.041
opard-0.039
 badly-0.037
 bars-0.036
aro-0.034
Token friend
Token ID1545
Feature activation+2.77e-02

Pos logit contributions
mons+0.013
opard+0.012
aro+0.011
iw+0.011
round+0.010
Neg logit contributions
 Jason-0.013
 Gary-0.013
oby-0.012
 Simon-0.012
Jason-0.012
Token,
Token ID11
Feature activation-1.01e-02

Pos logit contributions
 Jason+0.058
oby+0.056
 Gary+0.055
Jason+0.055
 Martin+0.053
Neg logit contributions
mons-0.040
opard-0.037
 badly-0.034
aro-0.033
 bars-0.032
Token a
Token ID257
Feature activation+1.21e-03

Pos logit contributions
mons+0.019
opard+0.017
iw+0.015
aro+0.015
 badly+0.015
Neg logit contributions
 Jason-0.020
 Gary-0.019
 Simon-0.018
oby-0.018
 Martin-0.017
Token named
Token ID3706
Feature activation-1.64e-02

Pos logit contributions
mons+0.024
opard+0.021
 badly+0.019
aro+0.019
drops+0.018
Neg logit contributions
 Jason-0.042
 Gary-0.040
oby-0.039
 Simon-0.038
 Martin-0.038
Token Mia
Token ID32189
Feature activation+5.43e-03

Pos logit contributions
mons+0.033
opard+0.032
aro+0.030
 badly+0.029
pre+0.029
Neg logit contributions
 Jason-0.027
 Gary-0.026
 Emily-0.024
 Martin-0.023
oby-0.023
Token went
Token ID1816
Feature activation+1.10e-02

Pos logit contributions
 Jason+0.009
 Gary+0.009
oby+0.008
Jason+0.008
 Simon+0.008
Neg logit contributions
mons-0.011
opard-0.010
aro-0.009
 badly-0.009
iw-0.009
Token to
Token ID284
Feature activation+3.10e-03

Pos logit contributions
 Jason+0.028
 Gary+0.027
oby+0.026
Jason+0.026
 Simon+0.025
Neg logit contributions
mons-0.013
opard-0.011
aro-0.010
 badly-0.010
iw-0.010
Token the
Token ID262
Feature activation+1.30e-02

Pos logit contributions
 Jason+0.006
 Gary+0.005
oby+0.005
Jason+0.005
 Simon+0.005
Neg logit contributions
mons-0.006
opard-0.006
aro-0.005
 badly-0.005
iw-0.005
Token gym
Token ID11550
Feature activation-6.87e-02

Pos logit contributions
 Jason+0.027
 Gary+0.025
oby+0.024
Jason+0.024
 Simon+0.024
Neg logit contributions
mons-0.022
opard-0.020
iw-0.018
 badly-0.018
aro-0.017
Token with
Token ID351
Feature activation+2.60e-02

Pos logit contributions
mons+0.139
opard+0.134
aro+0.127
drops+0.122
ric+0.122
Neg logit contributions
 Jason-0.089
 Gary-0.085
 Emily-0.081
oby-0.077
 Luke-0.077
Token her
Token ID607
Feature activation+6.60e-03

Pos logit contributions
 Jason+0.046
oby+0.046
 Gary+0.045
Jason+0.042
 Simon+0.042
Neg logit contributions
mons-0.048
 cherry-0.042
 bars-0.041
 badly-0.041
 purse-0.040
Token mom
Token ID1995
Feature activation+3.55e-02

Pos logit contributions
 Jason+0.014
 Gary+0.013
oby+0.013
Jason+0.013
 Simon+0.013
Neg logit contributions
mons-0.011
opard-0.010
aro-0.009
 badly-0.009
iw-0.009
Token.
Token ID13
Feature activation-2.02e-03

Pos logit contributions
 Gary+0.095
 Jason+0.093
oby+0.091
Jason+0.090
 Martin+0.089
Neg logit contributions
mons-0.034
iw-0.025
opard-0.024
 bars-0.023
 cherry-0.023
Token The
Token ID383
Feature activation+1.47e-02

Pos logit contributions
mons+0.004
opard+0.003
aro+0.003
 badly+0.003
iw+0.003
Neg logit contributions
 Jason-0.004
 Gary-0.004
oby-0.004
 Simon-0.003
 Martin-0.003
Token,
Token ID11
Feature activation+2.79e-03

Pos logit contributions
mons+0.050
opard+0.047
iw+0.042
round+0.041
har+0.041
Neg logit contributions
 Jason-0.060
 Gary-0.056
 Simon-0.054
 Martin-0.053
 Justin-0.052
Token
Token ID6184
Feature activation-4.53e-02

Pos logit contributions
 Jason+0.005
 Gary+0.005
oby+0.005
Jason+0.005
 Simon+0.005
Neg logit contributions
mons-0.005
opard-0.005
aro-0.004
 badly-0.004
iw-0.004
Token
Token ID95
Feature activation-3.34e-02

Pos logit contributions
mons+0.069
aro+0.059
 badly+0.059
opard+0.059
iw+0.059
Neg logit contributions
 Jason-0.087
 Gary-0.084
oby-0.079
 Simon-0.079
 Martin-0.077
Token
Token ID26391
Feature activation-5.57e-02

Pos logit contributions
mons+0.060
 badly+0.055
aro+0.053
opard+0.052
iw+0.051
Neg logit contributions
 Jason-0.062
 Gary-0.059
oby-0.058
Jason-0.055
 Martin-0.053
Token
Token ID129
Feature activation-1.51e-02

Pos logit contributions
mons+0.091
aro+0.082
 badly+0.081
opard+0.080
iw+0.079
Neg logit contributions
 Jason-0.106
 Gary-0.103
Jason-0.095
 Steven-0.095
 Simon-0.094
Token
Token ID241
Feature activation-7.03e-02

Pos logit contributions
mons+0.029
opard+0.025
iw+0.024
aro+0.024
 badly+0.024
Neg logit contributions
 Jason-0.028
 Gary-0.027
oby-0.025
 Simon-0.025
 Martin-0.025
TokenBe
Token ID3856
Feature activation-3.85e-03

Pos logit contributions
mons+0.130
opard+0.118
aro+0.116
har+0.111
drops+0.111
Neg logit contributions
 Jason-0.119
oby-0.118
Jason-0.110
 Simon-0.108
 Gary-0.104
Token careful
Token ID8161
Feature activation-1.14e-02

Pos logit contributions
mons+0.007
opard+0.006
aro+0.006
iw+0.006
 badly+0.006
Neg logit contributions
 Jason-0.007
 Gary-0.007
oby-0.007
Jason-0.007
 Simon-0.006
Token when
Token ID618
Feature activation-1.15e-02

Pos logit contributions
mons+0.020
opard+0.018
iw+0.017
aro+0.016
 badly+0.015
Neg logit contributions
 Jason-0.023
 Gary-0.022
oby-0.021
 Simon-0.021
 Martin-0.021
Token touching
Token ID15241
Feature activation-3.36e-02

Pos logit contributions
mons+0.021
opard+0.020
iw+0.018
aro+0.018
 badly+0.017
Neg logit contributions
 Jason-0.022
 Gary-0.021
oby-0.019
 Simon-0.019
 Martin-0.019
Token the
Token ID262
Feature activation-1.96e-02

Pos logit contributions
mons+0.066
opard+0.061
iw+0.055
pre+0.054
round+0.053
Neg logit contributions
 Jason-0.061
 Gary-0.057
 Simon-0.054
oby-0.053
 Martin-0.052
Token was
Token ID373
Feature activation-2.94e-02

Pos logit contributions
mons+0.004
opard+0.004
aro+0.004
iw+0.004
 badly+0.003
Neg logit contributions
 Jason-0.006
 Gary-0.006
oby-0.005
Jason-0.005
 Martin-0.005
Token playing
Token ID2712
Feature activation-5.59e-03

Pos logit contributions
mons+0.056
opard+0.052
aro+0.050
round+0.049
iw+0.046
Neg logit contributions
 Jason-0.055
 Gary-0.052
 Martin-0.048
 Simon-0.047
 Emily-0.047
Token hide
Token ID7808
Feature activation-3.44e-02

Pos logit contributions
mons+0.008
opard+0.007
aro+0.006
iw+0.006
 badly+0.006
Neg logit contributions
 Jason-0.013
 Gary-0.013
oby-0.012
Jason-0.012
 Martin-0.012
Token-
Token ID12
Feature activation-5.52e-02

Pos logit contributions
mons+0.059
opard+0.053
iw+0.050
aro+0.050
pre+0.048
Neg logit contributions
 Jason-0.063
 Gary-0.062
oby-0.061
 dragons-0.056
 Simon-0.056
Tokenand
Token ID392
Feature activation-2.71e-02

Pos logit contributions
mons+0.100
+0.097
opard+0.093
sed+0.090
 badly+0.090
Neg logit contributions
oby-0.082
 Jason-0.081
 Gary-0.079
Jason-0.075
iny-0.074
Token-
Token ID12
Feature activation-7.29e-02

Pos logit contributions
mons+0.036
opard+0.032
iw+0.030
aro+0.027
+0.026
Neg logit contributions
 Jason-0.062
 Gary-0.060
oby-0.058
 Simon-0.057
 Martin-0.056
Tokenseek
Token ID36163
Feature activation-2.21e-02

Pos logit contributions
iw+0.125
 cherry+0.125
mons+0.125
 fountain+0.122
+0.122
Neg logit contributions
oby-0.106
 Jason-0.100
 Gary-0.098
iny-0.094
 dragons-0.091
Token with
Token ID351
Feature activation+2.03e-02

Pos logit contributions
mons+0.037
opard+0.034
aro+0.031
iw+0.031
pre+0.029
Neg logit contributions
 Jason-0.045
 Gary-0.043
oby-0.042
 Simon-0.041
 Martin-0.040
Token her
Token ID607
Feature activation-3.92e-03

Pos logit contributions
 Jason+0.034
 Gary+0.031
oby+0.031
Jason+0.030
 Simon+0.029
Neg logit contributions
mons-0.042
 badly-0.037
opard-0.037
 bars-0.036
iw-0.036
Token best
Token ID1266
Feature activation-2.98e-03

Pos logit contributions
mons+0.008
opard+0.007
aro+0.007
 badly+0.007
iw+0.007
Neg logit contributions
 Jason-0.007
 Gary-0.006
oby-0.006
 Simon-0.006
 Martin-0.006
Token friend
Token ID1545
Feature activation+2.72e-02

Pos logit contributions
mons+0.006
opard+0.005
aro+0.005
iw+0.005
 badly+0.005
Neg logit contributions
 Jason-0.006
 Gary-0.005
oby-0.005
 Simon-0.005
 Martin-0.005
Token wanted
Token ID2227
Feature activation-3.37e-02

Pos logit contributions
mons+0.019
opard+0.017
aro+0.016
iw+0.016
 badly+0.016
Neg logit contributions
 Jason-0.019
 Gary-0.018
oby-0.017
Jason-0.017
 Simon-0.017
Token to
Token ID284
Feature activation-2.81e-02

Pos logit contributions
opard+0.068
mons+0.065
pre+0.061
har+0.058
drops+0.057
Neg logit contributions
 Jason-0.057
 Gary-0.057
 Emily-0.053
 Harry-0.052
 Simon-0.050
Token step
Token ID2239
Feature activation-4.62e-02

Pos logit contributions
mons+0.068
opard+0.066
iw+0.060
pre+0.059
 badly+0.058
Neg logit contributions
 Gary-0.036
 Jason-0.035
 Harry-0.031
 Simon-0.030
 Emily-0.030
Token in
Token ID287
Feature activation-1.30e-02

Pos logit contributions
mons+0.104
opard+0.099
iw+0.091
 pige+0.091
pre+0.091
Neg logit contributions
 Gary-0.061
 Jason-0.060
 Toby-0.058
 Simon-0.056
 Emily-0.055
Token the
Token ID262
Feature activation-1.33e-02

Pos logit contributions
mons+0.026
opard+0.024
pre+0.021
iw+0.021
round+0.021
Neg logit contributions
 Jason-0.024
 Gary-0.023
 Simon-0.021
oby-0.021
 Martin-0.021
Token p
Token ID279
Feature activation-5.65e-02

Pos logit contributions
mons+0.025
opard+0.022
aro+0.020
iw+0.020
 badly+0.019
Neg logit contributions
 Jason-0.024
 Gary-0.023
oby-0.023
 Simon-0.021
Jason-0.021
Tokenuddle
Token ID24500
Feature activation-2.95e-02

Pos logit contributions
mons+0.084
opard+0.082
aro+0.077
pre+0.075
 Sy+0.073
Neg logit contributions
oby-0.090
ilo-0.089
 Jason-0.088
 Gary-0.085
 Emily-0.084
Token.
Token ID13
Feature activation-3.96e-02

Pos logit contributions
mons+0.059
opard+0.057
iw+0.050
pre+0.050
aro+0.050
Neg logit contributions
 Jason-0.047
 Gary-0.046
oby-0.043
 Simon-0.042
 Emily-0.041
Token
Token ID198
Feature activation-1.96e-02

Pos logit contributions
mons+0.084
 badly+0.082
opard+0.081
aro+0.081
pre+0.079
Neg logit contributions
 Gary-0.053
 Jason-0.049
 Harry-0.046
 Emily-0.044
 Simon-0.043
Token
Token ID198
Feature activation-3.16e-02

Pos logit contributions
mons+0.038
opard+0.034
drops+0.032
aro+0.031
iw+0.031
Neg logit contributions
 Jason-0.036
 Gary-0.034
oby-0.033
Jason-0.032
 Simon-0.031
TokenS
Token ID50
Feature activation-8.29e-03

Pos logit contributions
mons+0.053
aro+0.047
iw+0.046
pre+0.046
opard+0.046
Neg logit contributions
 Gary-0.055
 Jason-0.051
oby-0.051
iny-0.049
Emily-0.048
Token an
Token ID281
Feature activation+1.14e-02

Pos logit contributions
mons+0.029
opard+0.028
aro+0.024
iw+0.024
round+0.023
Neg logit contributions
 Jason-0.035
 Gary-0.033
oby-0.031
 Simon-0.031
Jason-0.031
Token idea
Token ID2126
Feature activation-1.78e-02

Pos logit contributions
 Jason+0.016
 Gary+0.015
oby+0.014
Jason+0.014
 Simon+0.014
Neg logit contributions
mons-0.026
opard-0.024
 badly-0.023
aro-0.023
iw-0.022
Token!
Token ID0
Feature activation-2.07e-02

Pos logit contributions
mons+0.032
opard+0.029
iw+0.026
pre+0.025
aro+0.025
Neg logit contributions
 Jason-0.035
 Gary-0.033
oby-0.031
 Simon-0.031
 Martin-0.030
Token Let
Token ID3914
Feature activation+2.37e-02

Pos logit contributions
mons+0.040
opard+0.036
 badly+0.034
aro+0.033
iw+0.033
Neg logit contributions
 Jason-0.038
 Gary-0.036
oby-0.034
 Simon-0.034
 Martin-0.033
Tokenâ
Token ID22940
Feature activation+1.06e-02

Pos logit contributions
 Jason+0.043
 Gary+0.042
oby+0.040
Jason+0.039
 Simon+0.039
Neg logit contributions
mons-0.041
opard-0.038
 badly-0.036
 bars-0.035
aro-0.034
Token
Token ID26391
Feature activation-5.64e-02

Pos logit contributions
 Jason+0.021
 Gary+0.020
oby+0.019
 Simon+0.019
Jason+0.019
Neg logit contributions
mons-0.018
opard-0.017
aro-0.015
 badly-0.015
iw-0.015
Token
Token ID8151
Feature activation-6.33e-02

Pos logit contributions
mons+0.079
opard+0.071
aro+0.071
iw+0.068
 badly+0.068
Neg logit contributions
 Jason-0.123
 Gary-0.118
 Steven-0.112
 Chris-0.110
Jason-0.109
Tokens
Token ID82
Feature activation-1.60e-02

Pos logit contributions
mons+0.113
opard+0.100
pre+0.096
iw+0.090
drops+0.089
Neg logit contributions
 Jason-0.112
 Gary-0.105
oby-0.100
 Emily-0.097
 Simon-0.095
Token spin
Token ID7906
Feature activation-2.27e-02

Pos logit contributions
mons+0.032
opard+0.029
iw+0.027
aro+0.027
 badly+0.026
Neg logit contributions
 Jason-0.028
 Gary-0.027
oby-0.025
 Simon-0.025
 Martin-0.025
Token together
Token ID1978
Feature activation-1.17e-02

Pos logit contributions
mons+0.043
opard+0.039
iw+0.035
pre+0.034
aro+0.034
Neg logit contributions
 Jason-0.043
 Gary-0.042
oby-0.040
 Simon-0.039
 Martin-0.038
Token and
Token ID290
Feature activation-2.13e-02

Pos logit contributions
mons+0.019
opard+0.017
aro+0.015
iw+0.015
 badly+0.015
Neg logit contributions
 Jason-0.025
 Gary-0.024
oby-0.023
 Simon-0.022
 Martin-0.022