TOP ACTIVATIONS
MAX = 3.831

have fun , my d arl ings ?" she asks .
of Santa and his re ind eer . They hope they
let out a big sn arl and the mouse knew he
Spot grow ls and sn arl s . He tries to
have fun , my d arl ings ?" Their mother asked
We know , my d arl ings . We miss them
'm sorry , my d arl ings . The tornado took
perfect fish , my d arl ings ," mom says .
, Rudolph and his re ind eer friends were all out
" Hello , my d arl ings . I 'm so
One day a mis chie vous monkey saw the bear
Christmas and he loved re ind eer . He would often
there was a happy re ind eer named Rudolph . He
saw a group of re ind eer running in the field
. Rex sn arl s . He does not
you go , my d arl ings ," Mom said .
's okay , my d arl ings . I forgive you
you too , my d arl ings ," she said .
What happened , my d arl ings ? Why are you
's good , my d arl ings . I 'm glad

MIN ACTIVATIONS
MIN = -5.853

s wrong , rh in oc eros ? â said
give to the rh in oc eros . Lily walked to
it to the rh in oc eros . When he tasted
" The rh in oc eros is in there ,
't know the rh in oc eros was wild . Can
mess . The rh in oc eros had destroyed her room
, " The rh in oc eros made a big mess
mom said , " C oc oa is a strong drink
She loved to eat av oc ados . One day ,
't touch the rh in oc eros ! It might bite
goodbye to the rh in oc eros . They say they
replied the rh in oc eros sadly . It had
it , the rh in oc eros smiled . He had
I will buy more av oc ados tomorrow . You can
book . The rh in oc eros was mesmer ized by
Unicorn !" The rh in oc eros said , feeling much
fence where the rh in oc eros was . She saw
Did you know that av oc ados are very healthy for
net on the rh in oc eros . They put the
She loved to eat av oc ados because they were y

INTERVAL 1.410 - 3.831
CONTAINS 0.481%

. <|endoftext|> Ben and Mia like to play with trains .
rough paper and some cr ay ons . They sit on
ride the waves on his surf board . One day ,
some ac orns and took them to his friends . They
. He loved holding his treasure . One day , while

INTERVAL -1.011 - 1.410
CONTAINS 97.433%

purple balloon . As Sus ie and her
to get better ." Mia picked up the arrow and put
He was big and strong ! He was wearing an orange
ase !" Anna says . " Can we play with it
?" The tree smiled and said kindly ,

INTERVAL -3.432 - -1.011
CONTAINS 2.085%

a sign that said " Safety First ". Lily remembered what
will have dessert . How does that sound ?"
Everything is going to be okay ." The
" I 'm here to talk to you about taking a
learning new things . One sunny day , she was playing

INTERVAL -5.853 - -3.432
CONTAINS 0.002%

eros . The rh in oc eros was very big and
The rh in oc eros couldn 't believe his
She loved to eat av oc ados because they were y
net on the rh in oc eros . They put the
shaking . Mom watched in amaz ement from a distance ,
Token have
Token ID423
Feature activation-2.40e-01

Pos logit contributions
 brothers+0.011
 chambers+0.010
mun+0.009
 promises+0.009
 more+0.009
Neg logit contributions
tha-0.024
flake-0.024
icol-0.024
iya-0.023
essa-0.023
Token fun
Token ID1257
Feature activation-3.12e-01

Pos logit contributions
 brothers+0.006
 more+0.005
 friends+0.005
 chambers+0.005
 chores+0.004
Neg logit contributions
flake-0.023
tha-0.022
ich-0.021
icol-0.021
AP-0.021
Token,
Token ID11
Feature activation+1.88e-01

Pos logit contributions
 brothers+0.010
 more+0.009
 friends+0.009
 of+0.009
 questions+0.007
Neg logit contributions
tha-0.028
icol-0.027
iya-0.027
OW-0.026
essa-0.026
Token my
Token ID616
Feature activation+1.31e+00

Pos logit contributions
flake+0.015
icol+0.015
tha+0.014
iya+0.014
OW+0.014
Neg logit contributions
 brothers-0.007
 chambers-0.005
 friends-0.005
 more-0.005
 promises-0.005
Token d
Token ID288
Feature activation+5.16e-01

Pos logit contributions
tha+0.092
flake+0.092
icol+0.090
enda+0.088
AR+0.087
Neg logit contributions
 brothers-0.060
 friends-0.052
 chambers-0.047
 questions-0.046
 promises-0.046
Tokenarl
Token ID7063
Feature activation+3.56e+00

Pos logit contributions
icol+0.035
tha+0.034
flake+0.033
 peac+0.033
iya+0.032
Neg logit contributions
 brothers-0.023
ins-0.021
 of-0.021
 chambers-0.020
 questions-0.019
Tokenings
Token ID654
Feature activation+2.52e-01

Pos logit contributions
tha+0.160
flake+0.156
icol+0.155
 peac+0.153
iya+0.150
Neg logit contributions
 brothers-0.224
 chambers-0.210
mun-0.207
 promises-0.203
 friends-0.196
Token?"
Token ID1701
Feature activation+1.06e+00

Pos logit contributions
icol+0.017
tha+0.016
iya+0.015
flake+0.015
OW+0.015
Neg logit contributions
 of-0.013
 brothers-0.013
 more-0.011
mun-0.011
 chambers-0.011
Token she
Token ID673
Feature activation-7.64e-01

Pos logit contributions
flake+0.081
tha+0.078
icol+0.077
iya+0.075
 peac+0.074
Neg logit contributions
 brothers-0.037
 chambers-0.034
mun-0.032
 promises-0.030
 more-0.029
Token asks
Token ID7893
Feature activation-7.01e-02

Pos logit contributions
 chambers+0.032
mun+0.031
 brothers+0.030
ins+0.029
 ways+0.027
Neg logit contributions
tha-0.045
essa-0.044
la-0.044
 peac-0.044
iya-0.044
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
 chambers+0.003
 brothers+0.003
mun+0.003
 promises+0.003
 goals+0.002
Neg logit contributions
tha-0.005
flake-0.004
essa-0.004
 peac-0.004
iya-0.004
Token of
Token ID286
Feature activation+8.46e-01

Pos logit contributions
tha+0.035
flake+0.035
 peac+0.034
icol+0.034
iya+0.033
Neg logit contributions
 brothers-0.007
 chambers-0.006
mun-0.005
 more-0.005
 promises-0.005
Token Santa
Token ID8909
Feature activation+1.44e+00

Pos logit contributions
tha+0.052
flake+0.051
iya+0.049
 peac+0.049
essa+0.048
Neg logit contributions
 brothers-0.037
 chambers-0.036
mun-0.035
 promises-0.032
ins-0.031
Token and
Token ID290
Feature activation+7.37e-01

Pos logit contributions
flake+0.080
tha+0.078
iya+0.073
essa+0.072
 peac+0.071
Neg logit contributions
 brothers-0.074
 chambers-0.073
mun-0.071
 promises-0.067
 goals-0.067
Token his
Token ID465
Feature activation+7.21e-01

Pos logit contributions
tha+0.052
flake+0.051
 peac+0.050
iya+0.050
icol+0.050
Neg logit contributions
 brothers-0.026
mun-0.025
 chambers-0.025
 promises-0.022
ins-0.022
Token re
Token ID302
Feature activation+1.04e+00

Pos logit contributions
tha+0.050
flake+0.049
icol+0.048
iya+0.047
 peac+0.047
Neg logit contributions
 brothers-0.029
 chambers-0.027
mun-0.025
 promises-0.025
 more-0.023
Tokenind
Token ID521
Feature activation+3.53e+00

Pos logit contributions
icol+0.039
flake+0.037
tha+0.036
storm+0.036
 peac+0.035
Neg logit contributions
 brothers-0.075
 promises-0.070
 chambers-0.070
ins-0.069
mun-0.069
Tokeneer
Token ID28153
Feature activation+1.30e+00

Pos logit contributions
icol+0.195
tha+0.194
flake+0.191
 peac+0.186
AR+0.180
Neg logit contributions
 brothers-0.192
 chambers-0.181
mun-0.171
 promises-0.167
 questions-0.164
Token.
Token ID13
Feature activation+4.59e-01

Pos logit contributions
flake+0.097
tha+0.096
 peac+0.092
iya+0.091
icol+0.090
Neg logit contributions
 brothers-0.041
 chambers-0.039
mun-0.039
 promises-0.035
 goals-0.032
Token They
Token ID1119
Feature activation+4.77e-01

Pos logit contributions
tha+0.030
flake+0.030
icol+0.029
iya+0.028
essa+0.028
Neg logit contributions
 brothers-0.019
 chambers-0.018
mun-0.018
 promises-0.017
 more-0.016
Token hope
Token ID2911
Feature activation+6.55e-01

Pos logit contributions
tha+0.034
flake+0.034
icol+0.032
iya+0.032
 peac+0.032
Neg logit contributions
 brothers-0.018
 chambers-0.017
mun-0.016
 promises-0.015
 more-0.014
Token they
Token ID484
Feature activation+8.23e-01

Pos logit contributions
flake+0.042
tha+0.041
icol+0.040
 peac+0.039
AR+0.039
Neg logit contributions
 brothers-0.030
 chambers-0.028
 more-0.028
 promises-0.027
mun-0.027
Token let
Token ID1309
Feature activation+2.47e-01

Pos logit contributions
tha+0.017
icol+0.017
flake+0.017
iya+0.017
essa+0.017
Neg logit contributions
 brothers-0.008
 chambers-0.007
mun-0.007
 more-0.006
 promises-0.006
Token out
Token ID503
Feature activation-6.51e-01

Pos logit contributions
flake+0.018
tha+0.018
icol+0.017
iya+0.017
 peac+0.017
Neg logit contributions
 brothers-0.009
 chambers-0.008
mun-0.008
 promises-0.008
 more-0.008
Token a
Token ID257
Feature activation-5.97e-01

Pos logit contributions
 brothers+0.029
mun+0.029
 chambers+0.028
 promises+0.026
 goals+0.025
Neg logit contributions
flake-0.039
tha-0.038
 peac-0.038
icol-0.037
iya-0.036
Token big
Token ID1263
Feature activation+1.47e-01

Pos logit contributions
 brothers+0.025
 chambers+0.023
mun+0.023
 promises+0.022
 goals+0.020
Neg logit contributions
flake-0.039
tha-0.039
icol-0.038
 peac-0.037
iya-0.037
Token sn
Token ID3013
Feature activation+3.27e-01

Pos logit contributions
tha+0.010
flake+0.010
la+0.010
iya+0.010
essa+0.010
Neg logit contributions
 brothers-0.006
 chambers-0.005
 more-0.005
 promises-0.005
mun-0.005
Tokenarl
Token ID7063
Feature activation+3.50e+00

Pos logit contributions
tha+0.017
flake+0.016
icol+0.016
iya+0.015
 peac+0.015
Neg logit contributions
 brothers-0.019
 chambers-0.018
mun-0.017
 promises-0.017
 more-0.017
Token and
Token ID290
Feature activation+5.57e-02

Pos logit contributions
tha+0.224
flake+0.220
icol+0.216
iya+0.215
 peac+0.215
Neg logit contributions
 brothers-0.153
 chambers-0.141
mun-0.136
 promises-0.130
 more-0.126
Token the
Token ID262
Feature activation+4.45e-01

Pos logit contributions
tha+0.004
flake+0.004
icol+0.004
 peac+0.004
iya+0.004
Neg logit contributions
 brothers-0.002
 chambers-0.002
mun-0.002
 promises-0.002
 goals-0.002
Token mouse
Token ID10211
Feature activation+1.96e-01

Pos logit contributions
flake+0.026
tha+0.025
 peac+0.024
iya+0.023
icol+0.023
Neg logit contributions
 brothers-0.023
 chambers-0.022
mun-0.021
 promises-0.020
 goals-0.019
Token knew
Token ID2993
Feature activation+5.16e-01

Pos logit contributions
flake+0.012
tha+0.012
 peac+0.012
icol+0.011
iya+0.011
Neg logit contributions
 brothers-0.009
 chambers-0.008
mun-0.008
 promises-0.008
 goals-0.007
Token he
Token ID339
Feature activation-3.81e-01

Pos logit contributions
tha+0.035
flake+0.035
icol+0.033
iya+0.033
 peac+0.033
Neg logit contributions
 brothers-0.021
 chambers-0.020
mun-0.019
 promises-0.018
 more-0.017
TokenSpot
Token ID32565
Feature activation-3.41e-01

Pos logit contributions
 brothers+0.018
 chambers+0.018
mun+0.017
 promises+0.016
 questions+0.016
Neg logit contributions
tha-0.019
flake-0.019
iya-0.018
 peac-0.017
icol-0.017
Token grow
Token ID1663
Feature activation+7.39e-02

Pos logit contributions
 brothers+0.013
 chambers+0.012
mun+0.011
 promises+0.010
ins+0.010
Neg logit contributions
flake-0.023
tha-0.023
icol-0.023
iya-0.022
 peac-0.022
Tokenls
Token ID7278
Feature activation+2.21e-01

Pos logit contributions
flake+0.003
la+0.003
tha+0.003
ller+0.003
rus+0.003
Neg logit contributions
 chambers-0.004
mun-0.004
 brothers-0.003
 promises-0.003
 importantly-0.003
Token and
Token ID290
Feature activation+1.49e-01

Pos logit contributions
flake+0.012
tha+0.011
 peac+0.011
icol+0.011
la+0.011
Neg logit contributions
mun-0.011
 chambers-0.011
 brothers-0.011
ins-0.010
 chores-0.010
Token sn
Token ID3013
Feature activation+4.97e-01

Pos logit contributions
icol+0.009
tha+0.009
flake+0.009
 peac+0.009
da+0.008
Neg logit contributions
 brothers-0.006
 chambers-0.006
ins-0.006
mun-0.006
 importantly-0.005
Tokenarl
Token ID7063
Feature activation+3.45e+00

Pos logit contributions
tha+0.026
flake+0.026
icol+0.025
iya+0.024
 peac+0.024
Neg logit contributions
 brothers-0.028
 chambers-0.027
mun-0.026
 promises-0.025
 more-0.024
Tokens
Token ID82
Feature activation+5.18e-01

Pos logit contributions
flake+0.191
tha+0.187
icol+0.176
essa+0.174
iya+0.173
Neg logit contributions
 chambers-0.175
 brothers-0.174
mun-0.168
 promises-0.161
 more-0.153
Token.
Token ID13
Feature activation+2.95e-01

Pos logit contributions
tha+0.031
flake+0.031
icol+0.030
iya+0.029
 peac+0.029
Neg logit contributions
 brothers-0.025
 chambers-0.024
mun-0.023
 promises-0.022
 more-0.021
Token He
Token ID679
Feature activation+1.79e-01

Pos logit contributions
icol+0.021
tha+0.021
flake+0.020
iya+0.020
 peac+0.019
Neg logit contributions
 brothers-0.010
mun-0.010
 chambers-0.010
 promises-0.009
ins-0.009
Token tries
Token ID8404
Feature activation-7.66e-01

Pos logit contributions
flake+0.012
tha+0.012
icol+0.012
 peac+0.012
iya+0.011
Neg logit contributions
 brothers-0.007
 chambers-0.006
mun-0.006
 promises-0.005
ins-0.005
Token to
Token ID284
Feature activation+3.25e-01

Pos logit contributions
 brothers+0.042
 chambers+0.040
mun+0.039
 promises+0.038
 more+0.037
Neg logit contributions
tha-0.041
flake-0.041
icol-0.039
iya-0.039
 peac-0.038
Token have
Token ID423
Feature activation-1.43e-01

Pos logit contributions
 brothers+0.008
 chambers+0.007
 promises+0.006
mun+0.006
 more+0.006
Neg logit contributions
tha-0.018
flake-0.018
icol-0.017
iya-0.017
essa-0.017
Token fun
Token ID1257
Feature activation-2.20e-01

Pos logit contributions
 more+0.003
 friends+0.003
 brothers+0.002
 cookies+0.002
 chambers+0.002
Neg logit contributions
flake-0.014
tha-0.014
ich-0.013
icol-0.013
essa-0.013
Token,
Token ID11
Feature activation+5.82e-02

Pos logit contributions
 brothers+0.008
 more+0.008
 friends+0.007
 of+0.007
 chambers+0.006
Neg logit contributions
icol-0.018
tha-0.018
essa-0.018
iya-0.018
OW-0.017
Token my
Token ID616
Feature activation+1.22e+00

Pos logit contributions
flake+0.004
icol+0.004
tha+0.004
iya+0.004
OW+0.004
Neg logit contributions
 brothers-0.002
 chambers-0.002
 more-0.002
 friends-0.002
 promises-0.002
Token d
Token ID288
Feature activation+5.09e-01

Pos logit contributions
AR+0.092
flake+0.091
da+0.088
icol+0.088
storm+0.088
Neg logit contributions
 brothers-0.047
 friends-0.046
 promises-0.038
 questions-0.037
 more-0.036
Tokenarl
Token ID7063
Feature activation+3.45e+00

Pos logit contributions
icol+0.037
tha+0.037
flake+0.036
iya+0.035
da+0.034
Neg logit contributions
 of-0.019
 brothers-0.018
ins-0.018
 chambers-0.015
oll-0.015
Tokenings
Token ID654
Feature activation+2.61e-01

Pos logit contributions
tha+0.163
icol+0.162
 peac+0.162
flake+0.159
iya+0.156
Neg logit contributions
 brothers-0.205
mun-0.189
 chambers-0.187
 promises-0.185
 friends-0.183
Token?"
Token ID1701
Feature activation+9.30e-01

Pos logit contributions
icol+0.016
tha+0.015
iya+0.014
flake+0.014
 peac+0.014
Neg logit contributions
 of-0.015
 brothers-0.014
 more-0.014
mun-0.013
 chambers-0.013
Token Their
Token ID5334
Feature activation-8.18e-02

Pos logit contributions
flake+0.066
tha+0.063
icol+0.063
iya+0.060
OW+0.060
Neg logit contributions
 brothers-0.039
 chambers-0.035
mun-0.033
 more-0.032
 promises-0.032
Token mother
Token ID2802
Feature activation-1.30e-01

Pos logit contributions
 brothers+0.004
 friends+0.003
 chambers+0.003
 promises+0.003
 questions+0.003
Neg logit contributions
flake-0.006
storm-0.005
tha-0.005
da-0.005
icol-0.005
Token asked
Token ID1965
Feature activation+4.47e-02

Pos logit contributions
 goals+0.008
 chambers+0.008
 chores+0.008
 brothers+0.007
 ways+0.007
Neg logit contributions
tha-0.006
flake-0.006
la-0.006
 peac-0.006
da-0.005
TokenWe
Token ID1135
Feature activation-2.18e-01

Pos logit contributions
 brothers+0.003
mun+0.003
 chambers+0.003
 promises+0.002
 more+0.002
Neg logit contributions
tha-0.004
icol-0.004
flake-0.004
iya-0.004
 peac-0.004
Token know
Token ID760
Feature activation-9.48e-01

Pos logit contributions
 brothers+0.008
mun+0.007
 promises+0.007
 chambers+0.007
 more+0.007
Neg logit contributions
tha-0.016
flake-0.016
icol-0.016
iya-0.015
 peac-0.015
Token,
Token ID11
Feature activation+2.46e-01

Pos logit contributions
 brothers+0.044
 chambers+0.041
 more+0.040
mun+0.039
 promises+0.039
Neg logit contributions
flake-0.062
tha-0.060
icol-0.058
iya-0.057
 peac-0.057
Token my
Token ID616
Feature activation+9.38e-01

Pos logit contributions
flake+0.015
tha+0.015
icol+0.014
iya+0.014
 peac+0.014
Neg logit contributions
 brothers-0.012
 chambers-0.011
mun-0.011
 promises-0.011
 more-0.010
Token d
Token ID288
Feature activation+2.70e-01

Pos logit contributions
tha+0.074
flake+0.074
iya+0.072
icol+0.071
 peac+0.071
Neg logit contributions
 brothers-0.032
 chambers-0.028
 promises-0.027
 friends-0.026
mun-0.026
Tokenarl
Token ID7063
Feature activation+3.44e+00

Pos logit contributions
tha+0.017
flake+0.017
icol+0.016
iya+0.016
 peac+0.016
Neg logit contributions
 brothers-0.013
 chambers-0.012
ins-0.011
 of-0.011
mun-0.011
Tokenings
Token ID654
Feature activation+4.17e-03

Pos logit contributions
tha+0.151
flake+0.147
icol+0.145
 peac+0.145
iya+0.142
Neg logit contributions
 brothers-0.218
 chambers-0.204
mun-0.204
 promises-0.200
 friends-0.193
Token.
Token ID13
Feature activation+9.03e-02

Pos logit contributions
tha+0.000
icol+0.000
flake+0.000
iya+0.000
 peac+0.000
Neg logit contributions
 brothers-0.000
mun-0.000
 more-0.000
 chambers-0.000
 of-0.000
Token We
Token ID775
Feature activation-1.18e-01

Pos logit contributions
flake+0.006
tha+0.006
iya+0.006
 peac+0.006
essa+0.006
Neg logit contributions
 brothers-0.004
 chambers-0.004
 promises-0.003
mun-0.003
 goals-0.003
Token miss
Token ID2051
Feature activation+6.18e-01

Pos logit contributions
 brothers+0.004
 promises+0.003
 friends+0.003
mun+0.003
 more+0.003
Neg logit contributions
icol-0.010
tha-0.010
flake-0.009
ich-0.009
iya-0.009
Token them
Token ID606
Feature activation+1.19e+00

Pos logit contributions
flake+0.047
icol+0.045
storm+0.043
opter+0.043
ANG+0.043
Neg logit contributions
 more-0.027
 brothers-0.026
 friends-0.026
 questions-0.024
 promises-0.024
Token'm
Token ID1101
Feature activation+8.51e-01

Pos logit contributions
 brothers+0.003
mun+0.003
 promises+0.003
 chambers+0.003
 more+0.002
Neg logit contributions
tha-0.006
flake-0.006
icol-0.006
ich-0.006
iya-0.006
Token sorry
Token ID7926
Feature activation-4.34e-01

Pos logit contributions
flake+0.079
icol+0.076
tha+0.072
storm+0.072
OW+0.072
Neg logit contributions
 brothers-0.023
 more-0.018
 friends-0.016
 promises-0.014
 chambers-0.014
Token,
Token ID11
Feature activation+2.25e-01

Pos logit contributions
 brothers+0.017
 chambers+0.015
 more+0.015
 friends+0.015
 promises+0.014
Neg logit contributions
flake-0.032
tha-0.031
icol-0.030
 peac-0.030
iya-0.030
Token my
Token ID616
Feature activation+8.95e-01

Pos logit contributions
flake+0.016
icol+0.015
tha+0.015
 peac+0.014
storm+0.014
Neg logit contributions
 brothers-0.010
 more-0.009
 promises-0.009
 friends-0.008
 chambers-0.008
Token d
Token ID288
Feature activation+1.85e-01

Pos logit contributions
tha+0.069
flake+0.069
iya+0.068
 peac+0.067
icol+0.065
Neg logit contributions
 brothers-0.031
 chambers-0.027
 friends-0.027
 promises-0.027
mun-0.025
Tokenarl
Token ID7063
Feature activation+3.38e+00

Pos logit contributions
tha+0.012
flake+0.012
icol+0.011
iya+0.011
 peac+0.011
Neg logit contributions
 brothers-0.009
 chambers-0.008
 of-0.008
ins-0.008
mun-0.007
Tokenings
Token ID654
Feature activation-2.63e-02

Pos logit contributions
tha+0.156
 peac+0.153
icol+0.152
flake+0.149
iya+0.147
Neg logit contributions
 brothers-0.207
mun-0.193
 chambers-0.191
 promises-0.188
 friends-0.183
Token.
Token ID13
Feature activation+1.22e-01

Pos logit contributions
 brothers+0.001
 of+0.001
 more+0.001
mun+0.000
 chambers+0.000
Neg logit contributions
tha-0.002
icol-0.002
flake-0.002
iya-0.002
 peac-0.002
Token The
Token ID383
Feature activation+4.39e-01

Pos logit contributions
flake+0.007
tha+0.007
iya+0.007
 peac+0.007
icol+0.007
Neg logit contributions
 brothers-0.006
 chambers-0.006
 promises-0.006
mun-0.005
 more-0.005
Token tornado
Token ID33718
Feature activation+8.76e-01

Pos logit contributions
tha+0.033
flake+0.033
iya+0.032
icol+0.031
essa+0.031
Neg logit contributions
 brothers-0.016
 chambers-0.015
 promises-0.014
 more-0.014
 friends-0.013
Token took
Token ID1718
Feature activation-4.36e-01

Pos logit contributions
icol+0.069
tha+0.068
iya+0.068
flake+0.067
essa+0.067
Neg logit contributions
 brothers-0.027
 promises-0.025
mun-0.025
 chambers-0.023
 more-0.023
Token perfect
Token ID2818
Feature activation+4.79e-01

Pos logit contributions
tha+0.022
flake+0.022
icol+0.021
iya+0.021
 peac+0.021
Neg logit contributions
 brothers-0.014
 chambers-0.013
mun-0.012
 promises-0.012
 more-0.011
Token fish
Token ID5916
Feature activation+6.01e-01

Pos logit contributions
flake+0.037
icol+0.036
tha+0.036
OW+0.035
da+0.035
Neg logit contributions
 brothers-0.019
 friends-0.018
 more-0.015
 of-0.015
 sisters-0.013
Token,
Token ID11
Feature activation+3.54e-01

Pos logit contributions
icol+0.045
tha+0.043
flake+0.042
iya+0.042
enda+0.042
Neg logit contributions
 brothers-0.024
 friends-0.021
 of-0.021
 more-0.020
 chambers-0.020
Token my
Token ID616
Feature activation+1.01e+00

Pos logit contributions
flake+0.025
tha+0.025
icol+0.024
iya+0.024
 peac+0.023
Neg logit contributions
 brothers-0.014
 chambers-0.013
mun-0.012
 promises-0.012
 more-0.011
Token d
Token ID288
Feature activation+2.79e-01

Pos logit contributions
tha+0.076
enda+0.074
flake+0.074
storm+0.073
la+0.071
Neg logit contributions
 brothers-0.044
 friends-0.042
 more-0.035
 promises-0.034
 goals-0.033
Tokenarl
Token ID7063
Feature activation+3.37e+00

Pos logit contributions
tha+0.019
flake+0.018
icol+0.017
storm+0.017
iya+0.016
Neg logit contributions
 brothers-0.013
 of-0.013
ins-0.012
 goals-0.011
 chambers-0.011
Tokenings
Token ID654
Feature activation+2.07e-02

Pos logit contributions
tha+0.155
flake+0.151
icol+0.148
 peac+0.148
iya+0.145
Neg logit contributions
 brothers-0.210
 chambers-0.195
mun-0.192
 promises-0.189
 friends-0.185
Token,"
Token ID553
Feature activation+3.04e-01

Pos logit contributions
icol+0.002
tha+0.002
iya+0.002
flake+0.002
 peac+0.002
Neg logit contributions
 of-0.001
 brothers-0.001
 more-0.001
 chambers-0.000
mun-0.000
Token mom
Token ID1995
Feature activation-9.86e-01

Pos logit contributions
tha+0.017
flake+0.017
 peac+0.016
iya+0.016
icol+0.016
Neg logit contributions
 chambers-0.015
 brothers-0.015
mun-0.014
 promises-0.013
ins-0.013
Token says
Token ID1139
Feature activation-5.19e-01

Pos logit contributions
 chambers+0.046
mun+0.042
 goals+0.041
 brothers+0.041
 chores+0.040
Neg logit contributions
essa-0.054
tha-0.054
la-0.053
flake-0.052
iya-0.049
Token.
Token ID13
Feature activation-4.08e-01

Pos logit contributions
 chambers+0.025
 brothers+0.024
mun+0.023
 goals+0.022
 exercises+0.020
Neg logit contributions
tha-0.030
flake-0.029
essa-0.028
work-0.028
icol-0.027
Token,
Token ID11
Feature activation-1.32e-01

Pos logit contributions
flake+0.068
tha+0.067
OW+0.064
iya+0.064
essa+0.064
Neg logit contributions
 brothers-0.031
mun-0.027
 chambers-0.026
 friends-0.026
 more-0.026
Token Rudolph
Token ID48684
Feature activation+9.75e-01

Pos logit contributions
 brothers+0.005
 chambers+0.004
 friends+0.004
mun+0.004
 more+0.004
Neg logit contributions
flake-0.010
tha-0.009
icol-0.009
 peac-0.009
essa-0.009
Token and
Token ID290
Feature activation+1.25e-01

Pos logit contributions
icol+0.084
tha+0.083
AR+0.082
storm+0.081
flake+0.081
Neg logit contributions
 brothers-0.025
 friends-0.020
's-0.018
 more-0.018
mun-0.017
Token his
Token ID465
Feature activation+2.22e-01

Pos logit contributions
tha+0.010
flake+0.010
icol+0.010
iya+0.010
 peac+0.010
Neg logit contributions
 brothers-0.003
 chambers-0.003
mun-0.003
 promises-0.003
 more-0.002
Token re
Token ID302
Feature activation+9.76e-01

Pos logit contributions
flake+0.018
tha+0.018
icol+0.018
essa+0.017
iya+0.017
Neg logit contributions
 brothers-0.007
 friends-0.006
 chambers-0.005
 promises-0.005
 more-0.005
Tokenind
Token ID521
Feature activation+3.36e+00

Pos logit contributions
icol+0.037
flake+0.037
storm+0.034
tha+0.034
 peac+0.032
Neg logit contributions
 brothers-0.072
 friends-0.066
 chambers-0.065
mun-0.064
 promises-0.064
Tokeneer
Token ID28153
Feature activation+1.17e+00

Pos logit contributions
icol+0.205
tha+0.199
flake+0.196
AR+0.193
 peac+0.191
Neg logit contributions
 brothers-0.173
 chambers-0.158
mun-0.149
 friends-0.146
 questions-0.142
Token friends
Token ID2460
Feature activation+7.95e-01

Pos logit contributions
icol+0.095
tha+0.094
flake+0.093
essa+0.090
AR+0.089
Neg logit contributions
 brothers-0.036
 friends-0.030
mun-0.030
 chambers-0.029
 more-0.028
Token were
Token ID547
Feature activation+7.39e-01

Pos logit contributions
icol+0.068
flake+0.066
tha+0.066
AR+0.065
ich+0.064
Neg logit contributions
 brothers-0.022
mun-0.019
 friends-0.018
 more-0.017
 of-0.016
Token all
Token ID477
Feature activation+9.55e-01

Pos logit contributions
flake+0.057
icol+0.056
tha+0.056
essa+0.054
 peac+0.053
Neg logit contributions
 brothers-0.027
 friends-0.023
 more-0.023
mun-0.021
 chambers-0.020
Token out
Token ID503
Feature activation+4.10e-01

Pos logit contributions
tha+0.064
flake+0.064
icol+0.062
iya+0.061
 peac+0.061
Neg logit contributions
 brothers-0.038
 chambers-0.036
mun-0.035
 promises-0.033
 more-0.031
Token"
Token ID1
Feature activation+8.82e-01

Pos logit contributions
flake+0.019
tha+0.018
icol+0.018
 peac+0.017
iya+0.017
Neg logit contributions
 brothers-0.013
 chambers-0.013
mun-0.012
 promises-0.012
 more-0.011
TokenHello
Token ID15496
Feature activation+9.15e-01

Pos logit contributions
tha+0.053
flake+0.053
icol+0.051
 peac+0.050
iya+0.050
Neg logit contributions
 brothers-0.042
 chambers-0.040
mun-0.039
 more-0.037
 promises-0.036
Token,
Token ID11
Feature activation-2.80e-01

Pos logit contributions
flake+0.070
icol+0.068
 peac+0.067
storm+0.066
tha+0.066
Neg logit contributions
 brothers-0.031
 more-0.028
 chambers-0.027
 friends-0.027
mun-0.026
Token my
Token ID616
Feature activation+8.22e-01

Pos logit contributions
 brothers+0.014
 chambers+0.014
mun+0.013
 promises+0.013
 more+0.012
Neg logit contributions
tha-0.016
flake-0.016
icol-0.015
iya-0.015
 peac-0.015
Token d
Token ID288
Feature activation+7.18e-02

Pos logit contributions
flake+0.058
tha+0.057
 peac+0.056
storm+0.054
iya+0.054
Neg logit contributions
 brothers-0.035
 chambers-0.029
 friends-0.029
 more-0.029
 promises-0.028
Tokenarl
Token ID7063
Feature activation+3.32e+00

Pos logit contributions
tha+0.005
flake+0.005
 peac+0.004
icol+0.004
iya+0.004
Neg logit contributions
 brothers-0.003
 chambers-0.003
 of-0.003
ins-0.003
 questions-0.003
Tokenings
Token ID654
Feature activation-7.58e-02

Pos logit contributions
tha+0.147
 peac+0.145
icol+0.143
flake+0.142
iya+0.139
Neg logit contributions
 brothers-0.208
 chambers-0.195
mun-0.194
 promises-0.189
 friends-0.182
Token.
Token ID13
Feature activation-1.86e-01

Pos logit contributions
 brothers+0.003
 of+0.003
 more+0.003
mun+0.003
 chambers+0.003
Neg logit contributions
tha-0.005
icol-0.005
flake-0.005
 peac-0.005
iya-0.005
Token I
Token ID314
Feature activation-1.03e-02

Pos logit contributions
 brothers+0.008
 chambers+0.008
mun+0.007
 questions+0.007
 promises+0.007
Neg logit contributions
flake-0.012
tha-0.012
iya-0.011
 peac-0.011
icol-0.011
Token'm
Token ID1101
Feature activation+1.03e+00

Pos logit contributions
 brothers+0.000
mun+0.000
 chambers+0.000
 promises+0.000
 more+0.000
Neg logit contributions
tha-0.001
icol-0.001
flake-0.001
iya-0.001
essa-0.001
Token so
Token ID523
Feature activation+7.30e-01

Pos logit contributions
flake+0.082
icol+0.077
OW+0.074
tha+0.073
opter+0.073
Neg logit contributions
 brothers-0.039
 friends-0.033
 more-0.033
 sleepy-0.031
 of-0.030
Token
Token ID198
Feature activation+5.80e-01

Pos logit contributions
tha+0.028
flake+0.028
icol+0.027
iya+0.026
 peac+0.026
Neg logit contributions
 brothers-0.014
 chambers-0.013
mun-0.013
 promises-0.012
 more-0.011
TokenOne
Token ID3198
Feature activation+6.91e-01

Pos logit contributions
flake+0.036
tha+0.035
 peac+0.034
iya+0.034
icol+0.033
Neg logit contributions
 brothers-0.027
 chambers-0.025
mun-0.025
 promises-0.024
 more-0.022
Token day
Token ID1110
Feature activation-2.82e-01

Pos logit contributions
flake+0.029
 peac+0.028
tha+0.026
iya+0.026
storm+0.025
Neg logit contributions
mun-0.046
 chambers-0.045
ins-0.044
 promises-0.043
 goals-0.042
Token a
Token ID257
Feature activation+2.86e-01

Pos logit contributions
 brothers+0.012
 chambers+0.012
mun+0.011
 promises+0.011
 more+0.010
Neg logit contributions
tha-0.018
flake-0.018
icol-0.017
iya-0.017
 peac-0.017
Token mis
Token ID2984
Feature activation-6.24e-01

Pos logit contributions
tha+0.021
flake+0.021
icol+0.020
iya+0.020
essa+0.019
Neg logit contributions
 brothers-0.011
 chambers-0.010
mun-0.009
 more-0.009
 promises-0.008
Tokenchie
Token ID3043
Feature activation+3.31e+00

Pos logit contributions
 brothers+0.054
 chambers+0.053
mun+0.052
 promises+0.050
 more+0.050
Neg logit contributions
tha-0.013
flake-0.013
icol-0.012
iya-0.010
 peac-0.010
Tokenvous
Token ID31222
Feature activation+1.66e-01

Pos logit contributions
tha+0.224
flake+0.224
icol+0.214
iya+0.213
 peac+0.213
Neg logit contributions
 brothers-0.131
 chambers-0.124
mun-0.119
 promises-0.114
 more-0.107
Token monkey
Token ID21657
Feature activation+2.82e-01

Pos logit contributions
tha+0.012
flake+0.011
la+0.011
iya+0.011
icol+0.011
Neg logit contributions
 brothers-0.007
 chambers-0.006
mun-0.006
 friends-0.006
 more-0.006
Token saw
Token ID2497
Feature activation+2.87e-01

Pos logit contributions
flake+0.018
tha+0.018
 peac+0.017
icol+0.017
iya+0.017
Neg logit contributions
 brothers-0.013
 chambers-0.012
mun-0.011
 promises-0.011
 goals-0.011
Token the
Token ID262
Feature activation+5.18e-01

Pos logit contributions
flake+0.023
tha+0.023
icol+0.022
iya+0.022
storm+0.021
Neg logit contributions
 brothers-0.009
 chambers-0.008
mun-0.008
 more-0.008
 promises-0.007
Token bear
Token ID6842
Feature activation+3.51e-01

Pos logit contributions
tha+0.034
flake+0.034
icol+0.032
iya+0.032
 peac+0.032
Neg logit contributions
 brothers-0.022
 chambers-0.021
mun-0.020
 promises-0.019
 more-0.018
Token Christmas
Token ID6786
Feature activation+4.92e-01

Pos logit contributions
tha+0.022
flake+0.022
 peac+0.022
icol+0.021
iya+0.021
Neg logit contributions
 brothers-0.028
 chambers-0.027
mun-0.027
 promises-0.026
 goals-0.025
Token and
Token ID290
Feature activation+2.94e-01

Pos logit contributions
flake+0.033
tha+0.033
icol+0.031
iya+0.031
 peac+0.031
Neg logit contributions
 brothers-0.020
 chambers-0.019
mun-0.018
 promises-0.017
 goals-0.016
Token he
Token ID339
Feature activation+3.22e-01

Pos logit contributions
tha+0.016
iya+0.016
icol+0.015
flake+0.015
essa+0.015
Neg logit contributions
 chambers-0.015
 brothers-0.015
mun-0.014
ins-0.014
 promises-0.014
Token loved
Token ID6151
Feature activation+7.83e-01

Pos logit contributions
tha+0.021
flake+0.021
icol+0.020
iya+0.020
 peac+0.020
Neg logit contributions
 brothers-0.014
 chambers-0.013
mun-0.013
 promises-0.012
 more-0.011
Token re
Token ID302
Feature activation+7.83e-01

Pos logit contributions
tha+0.039
flake+0.039
icol+0.036
iya+0.036
 peac+0.036
Neg logit contributions
 brothers-0.046
 chambers-0.044
mun-0.043
 promises-0.041
 more-0.040
Tokenind
Token ID521
Feature activation+3.31e+00

Pos logit contributions
flake+0.021
tha+0.021
icol+0.020
 peac+0.019
iya+0.019
Neg logit contributions
 brothers-0.063
 chambers-0.061
mun-0.060
 promises-0.059
 more-0.057
Tokeneer
Token ID28153
Feature activation+9.39e-01

Pos logit contributions
flake+0.156
tha+0.155
iya+0.145
icol+0.144
essa+0.143
Neg logit contributions
 brothers-0.198
 chambers-0.192
mun-0.188
 promises-0.183
 more-0.175
Token.
Token ID13
Feature activation+9.92e-02

Pos logit contributions
flake+0.053
 peac+0.051
work+0.051
la+0.050
tha+0.050
Neg logit contributions
 chambers-0.040
mun-0.038
 brothers-0.038
 promises-0.036
 cabinets-0.036
Token He
Token ID679
Feature activation+1.15e-01

Pos logit contributions
flake+0.007
tha+0.007
icol+0.007
iya+0.007
 peac+0.006
Neg logit contributions
 brothers-0.004
 chambers-0.004
mun-0.003
 promises-0.003
 more-0.003
Token would
Token ID561
Feature activation+6.01e-01

Pos logit contributions
tha+0.008
flake+0.008
icol+0.008
AR+0.008
 peac+0.008
Neg logit contributions
 brothers-0.004
 chambers-0.004
mun-0.004
 more-0.004
 promises-0.004
Token often
Token ID1690
Feature activation+8.65e-01

Pos logit contributions
flake+0.044
tha+0.044
icol+0.042
essa+0.041
ich+0.041
Neg logit contributions
 brothers-0.021
 chambers-0.019
mun-0.019
 more-0.018
 promises-0.018
Token there
Token ID612
Feature activation-1.66e-01

Pos logit contributions
tha+0.013
flake+0.013
icol+0.013
iya+0.012
 peac+0.012
Neg logit contributions
 brothers-0.007
 chambers-0.006
mun-0.006
 promises-0.006
 more-0.005
Token was
Token ID373
Feature activation+5.07e-01

Pos logit contributions
 brothers+0.007
 chambers+0.006
mun+0.006
 promises+0.006
 questions+0.006
Neg logit contributions
flake-0.011
tha-0.011
iya-0.010
icol-0.010
 peac-0.010
Token a
Token ID257
Feature activation+1.57e-01

Pos logit contributions
flake+0.028
tha+0.028
iya+0.027
icol+0.027
 peac+0.027
Neg logit contributions
 chambers-0.025
 brothers-0.024
mun-0.024
 promises-0.023
 questions-0.022
Token happy
Token ID3772
Feature activation-2.92e-01

Pos logit contributions
tha+0.011
flake+0.011
icol+0.010
iya+0.010
 peac+0.010
Neg logit contributions
 brothers-0.006
 chambers-0.006
mun-0.005
 promises-0.005
 more-0.005
Token re
Token ID302
Feature activation+7.99e-01

Pos logit contributions
 brothers+0.009
 friends+0.009
 chambers+0.007
 of+0.007
 more+0.007
Neg logit contributions
tha-0.023
OW-0.022
la-0.022
flake-0.022
enda-0.022
Tokenind
Token ID521
Feature activation+3.30e+00

Pos logit contributions
icol+0.030
flake+0.027
tha+0.027
OW+0.026
storm+0.025
Neg logit contributions
 brothers-0.058
 chambers-0.056
mun-0.055
ins-0.053
 friends-0.053
Tokeneer
Token ID28153
Feature activation+9.06e-01

Pos logit contributions
tha+0.178
icol+0.178
flake+0.174
 peac+0.168
iya+0.164
Neg logit contributions
 brothers-0.180
 chambers-0.170
mun-0.163
 promises-0.156
 more-0.154
Token named
Token ID3706
Feature activation+1.33e-01

Pos logit contributions
tha+0.068
icol+0.067
flake+0.066
iya+0.064
essa+0.064
Neg logit contributions
 brothers-0.032
 chambers-0.028
mun-0.028
 more-0.026
 friends-0.025
Token Rudolph
Token ID48684
Feature activation+1.35e+00

Pos logit contributions
flake+0.009
storm+0.008
icol+0.008
 peac+0.008
tha+0.008
Neg logit contributions
 brothers-0.006
 his-0.005
 friends-0.005
 bears-0.005
 more-0.005
Token.
Token ID13
Feature activation+8.95e-02

Pos logit contributions
icol+0.120
tha+0.119
flake+0.115
OW+0.113
 peac+0.113
Neg logit contributions
 brothers-0.030
 chambers-0.022
mun-0.020
 friends-0.019
 more-0.019
Token He
Token ID679
Feature activation+3.68e-01

Pos logit contributions
tha+0.004
flake+0.004
 peac+0.004
OW+0.004
icol+0.004
Neg logit contributions
 brothers-0.005
 chambers-0.005
mun-0.005
 promises-0.005
 more-0.005
Token saw
Token ID2497
Feature activation+6.29e-02

Pos logit contributions
 brothers+0.021
 chambers+0.018
mun+0.018
 friends+0.017
 more+0.017
Neg logit contributions
tha-0.038
flake-0.036
icol-0.036
iya-0.035
essa-0.035
Token a
Token ID257
Feature activation-3.10e-02

Pos logit contributions
tha+0.005
flake+0.005
icol+0.005
iya+0.005
OW+0.004
Neg logit contributions
 brothers-0.002
 more-0.002
 chambers-0.002
mun-0.002
 friends-0.002
Token group
Token ID1448
Feature activation+3.80e-01

Pos logit contributions
 brothers+0.001
 more+0.001
 chambers+0.001
mun+0.001
 friends+0.001
Neg logit contributions
tha-0.002
la-0.002
iya-0.002
essa-0.002
icol-0.002
Token of
Token ID286
Feature activation+8.26e-01

Pos logit contributions
 peac+0.030
tha+0.027
storm+0.027
flake+0.027
essa+0.027
Neg logit contributions
 promises-0.010
 brothers-0.010
 chambers-0.010
 goals-0.009
mun-0.009
Token re
Token ID302
Feature activation+6.90e-01

Pos logit contributions
tha+0.060
flake+0.059
 peac+0.058
iya+0.057
icol+0.057
Neg logit contributions
 brothers-0.027
 chambers-0.026
mun-0.025
 promises-0.024
 goals-0.021
Tokenind
Token ID521
Feature activation+3.30e+00

Pos logit contributions
flake+0.022
tha+0.021
icol+0.021
 peac+0.018
essa+0.018
Neg logit contributions
 brothers-0.053
 chambers-0.052
mun-0.051
 promises-0.049
ins-0.049
Tokeneer
Token ID28153
Feature activation+5.34e-01

Pos logit contributions
tha+0.162
flake+0.161
icol+0.153
iya+0.150
 peac+0.150
Neg logit contributions
 brothers-0.194
 chambers-0.186
mun-0.181
 promises-0.176
 more-0.170
Token running
Token ID2491
Feature activation+2.64e-03

Pos logit contributions
flake+0.035
tha+0.035
 peac+0.034
ich+0.033
iya+0.033
Neg logit contributions
 chambers-0.021
 brothers-0.021
mun-0.019
 promises-0.019
 goals-0.018
Token in
Token ID287
Feature activation+7.01e-01

Pos logit contributions
tha+0.000
flake+0.000
iya+0.000
essa+0.000
icol+0.000
Neg logit contributions
 brothers-0.000
 chambers-0.000
 more-0.000
mun-0.000
 friends-0.000
Token the
Token ID262
Feature activation-3.19e-01

Pos logit contributions
tha+0.046
flake+0.045
icol+0.044
 peac+0.043
iya+0.043
Neg logit contributions
 brothers-0.029
 chambers-0.027
mun-0.027
 promises-0.025
ins-0.024
Token field
Token ID2214
Feature activation-1.06e+00

Pos logit contributions
 brothers+0.011
 chambers+0.011
mun+0.010
 promises+0.010
 more+0.009
Neg logit contributions
tha-0.024
flake-0.023
icol-0.022
iya-0.022
essa-0.022
Token.
Token ID13
Feature activation-1.98e-02

Pos logit contributions
 chambers+0.003
 brothers+0.003
mun+0.003
 promises+0.003
 goals+0.003
Neg logit contributions
tha-0.004
flake-0.004
essa-0.004
icol-0.004
 peac-0.004
Token
Token ID198
Feature activation-3.54e-01

Pos logit contributions
 brothers+0.001
 chambers+0.001
mun+0.001
 promises+0.001
 goals+0.001
Neg logit contributions
flake-0.001
tha-0.001
icol-0.001
 peac-0.001
iya-0.001
Token
Token ID198
Feature activation-1.14e-01

Pos logit contributions
 brothers+0.013
 chambers+0.013
mun+0.012
 promises+0.011
 more+0.011
Neg logit contributions
tha-0.025
flake-0.025
icol-0.024
iya-0.023
 peac-0.023
TokenRex
Token ID47389
Feature activation-2.45e-01

Pos logit contributions
 brothers+0.006
 chambers+0.006
mun+0.006
 promises+0.006
 ways+0.006
Neg logit contributions
tha-0.006
flake-0.006
 peac-0.006
icol-0.006
iya-0.005
Token sn
Token ID3013
Feature activation+1.53e-01

Pos logit contributions
 brothers+0.008
 chambers+0.008
mun+0.008
 promises+0.007
 more+0.007
Neg logit contributions
tha-0.018
flake-0.018
icol-0.017
iya-0.017
 peac-0.017
Tokenarl
Token ID7063
Feature activation+3.29e+00

Pos logit contributions
tha+0.008
flake+0.008
icol+0.007
iya+0.007
 peac+0.007
Neg logit contributions
 brothers-0.009
 chambers-0.009
mun-0.008
 promises-0.008
 more-0.008
Tokens
Token ID82
Feature activation+1.56e-02

Pos logit contributions
flake+0.173
tha+0.171
icol+0.160
iya+0.157
 peac+0.156
Neg logit contributions
 brothers-0.179
 chambers-0.177
mun-0.170
 promises-0.164
 more-0.158
Token.
Token ID13
Feature activation+2.06e-01

Pos logit contributions
tha+0.001
flake+0.001
 peac+0.001
icol+0.001
iya+0.001
Neg logit contributions
 brothers-0.001
 chambers-0.001
mun-0.001
 promises-0.001
ins-0.001
Token He
Token ID679
Feature activation+2.23e-01

Pos logit contributions
flake+0.015
tha+0.015
icol+0.015
 peac+0.014
iya+0.014
Neg logit contributions
mun-0.007
 chambers-0.007
 brothers-0.007
 promises-0.006
ins-0.006
Token does
Token ID857
Feature activation-5.09e-01

Pos logit contributions
tha+0.014
flake+0.014
icol+0.014
 peac+0.014
la+0.014
Neg logit contributions
 brothers-0.009
 chambers-0.008
mun-0.007
ins-0.007
 ways-0.007
Token not
Token ID407
Feature activation-5.30e-02

Pos logit contributions
 brothers+0.029
 chambers+0.027
mun+0.026
 promises+0.026
 more+0.026
Neg logit contributions
tha-0.027
flake-0.026
icol-0.025
iya-0.025
 peac-0.025
Token you
Token ID345
Feature activation-6.60e-01

Pos logit contributions
 brothers+0.002
 promises+0.002
 chambers+0.002
mun+0.002
 friends+0.002
Neg logit contributions
flake-0.003
icol-0.003
tha-0.003
iya-0.003
essa-0.003
Token go
Token ID467
Feature activation-4.42e-01

Pos logit contributions
mun+0.036
 chambers+0.031
 importantly+0.030
 brothers+0.030
ins+0.030
Neg logit contributions
 peac-0.034
OW-0.033
AR-0.032
flake-0.032
AP-0.031
Token,
Token ID11
Feature activation-2.01e-01

Pos logit contributions
 of+0.012
 more+0.012
 brothers+0.010
 friends+0.010
 chambers+0.009
Neg logit contributions
iya-0.039
flake-0.039
essa-0.038
icol-0.038
tha-0.037
Token my
Token ID616
Feature activation+8.96e-01

Pos logit contributions
 brothers+0.008
 chambers+0.007
 promises+0.007
mun+0.007
 more+0.007
Neg logit contributions
flake-0.014
tha-0.014
icol-0.014
iya-0.013
 peac-0.013
Token d
Token ID288
Feature activation+2.20e-01

Pos logit contributions
tha+0.068
iya+0.066
la+0.065
flake+0.064
icol+0.064
Neg logit contributions
 brothers-0.035
 friends-0.032
 promises-0.028
 of-0.027
 chambers-0.026
Tokenarl
Token ID7063
Feature activation+3.28e+00

Pos logit contributions
tha+0.014
flake+0.013
icol+0.013
iya+0.013
 peac+0.013
Neg logit contributions
 brothers-0.011
 chambers-0.010
 of-0.009
mun-0.009
ins-0.009
Tokenings
Token ID654
Feature activation-4.75e-02

Pos logit contributions
tha+0.151
 peac+0.148
iya+0.146
flake+0.146
icol+0.146
Neg logit contributions
 brothers-0.200
 chambers-0.184
mun-0.183
 promises-0.182
 friends-0.179
Token,"
Token ID553
Feature activation+3.19e-01

Pos logit contributions
 of+0.002
 more+0.002
 brothers+0.002
mun+0.002
 cookies+0.002
Neg logit contributions
icol-0.003
tha-0.003
iya-0.003
flake-0.003
 peac-0.003
Token Mom
Token ID11254
Feature activation-1.35e+00

Pos logit contributions
tha+0.021
flake+0.021
icol+0.020
 peac+0.020
iya+0.020
Neg logit contributions
 brothers-0.013
 chambers-0.013
mun-0.012
 promises-0.012
 goals-0.011
Token said
Token ID531
Feature activation-4.54e-01

Pos logit contributions
 chambers+0.075
 goals+0.075
 brothers+0.071
 chores+0.069
mun+0.069
Neg logit contributions
tha-0.068
flake-0.067
 peac-0.064
essa-0.064
la-0.063
Token.
Token ID13
Feature activation-3.85e-01

Pos logit contributions
 chambers+0.020
 brothers+0.019
mun+0.018
 goals+0.017
 promises+0.016
Neg logit contributions
tha-0.029
flake-0.028
essa-0.028
icol-0.027
iya-0.026
Token's
Token ID338
Feature activation-4.70e-01

Pos logit contributions
 brothers+0.008
 chambers+0.007
mun+0.007
 promises+0.006
 questions+0.006
Neg logit contributions
flake-0.017
tha-0.017
 peac-0.016
icol-0.016
essa-0.016
Token okay
Token ID8788
Feature activation-9.61e-01

Pos logit contributions
 brothers+0.018
 chambers+0.017
mun+0.016
 promises+0.016
 more+0.015
Neg logit contributions
tha-0.033
flake-0.033
icol-0.031
iya-0.031
 peac-0.031
Token,
Token ID11
Feature activation-2.04e-01

Pos logit contributions
 brothers+0.036
 chambers+0.034
mun+0.032
 promises+0.031
 more+0.029
Neg logit contributions
tha-0.068
flake-0.068
icol-0.065
iya-0.065
 peac-0.065
Token my
Token ID616
Feature activation+6.90e-01

Pos logit contributions
 brothers+0.009
 promises+0.007
 chambers+0.007
 friends+0.007
 more+0.007
Neg logit contributions
flake-0.015
tha-0.014
icol-0.014
iya-0.014
OW-0.013
Token d
Token ID288
Feature activation-1.15e-02

Pos logit contributions
tha+0.049
flake+0.048
iya+0.045
AR+0.045
la+0.045
Neg logit contributions
 brothers-0.030
 friends-0.026
 questions-0.026
 promises-0.026
 chambers-0.024
Tokenarl
Token ID7063
Feature activation+3.28e+00

Pos logit contributions
 brothers+0.001
 chambers+0.000
 of+0.000
ins+0.000
 questions+0.000
Neg logit contributions
tha-0.001
flake-0.001
 peac-0.001
icol-0.001
iya-0.001
Tokenings
Token ID654
Feature activation-1.43e-01

Pos logit contributions
tha+0.147
flake+0.142
 peac+0.140
icol+0.139
iya+0.137
Neg logit contributions
 brothers-0.207
 chambers-0.192
mun-0.192
 promises-0.189
 friends-0.182
Token.
Token ID13
Feature activation+9.82e-02

Pos logit contributions
 brothers+0.004
 chambers+0.003
mun+0.003
 more+0.003
 promises+0.003
Neg logit contributions
tha-0.012
flake-0.012
icol-0.012
iya-0.012
 peac-0.012
Token I
Token ID314
Feature activation-1.07e-01

Pos logit contributions
tha+0.005
flake+0.005
iya+0.005
 peac+0.005
icol+0.005
Neg logit contributions
 brothers-0.005
 chambers-0.005
 promises-0.005
mun-0.005
 more-0.005
Token forgive
Token ID20927
Feature activation-7.76e-02

Pos logit contributions
 brothers+0.004
 chambers+0.004
mun+0.004
 promises+0.004
 more+0.004
Neg logit contributions
tha-0.007
flake-0.007
icol-0.007
iya-0.007
essa-0.007
Token you
Token ID345
Feature activation-7.42e-01

Pos logit contributions
 brothers+0.004
 more+0.004
 friends+0.004
 promises+0.003
 chambers+0.003
Neg logit contributions
flake-0.005
icol-0.005
tha-0.005
storm-0.005
iya-0.005
Token you
Token ID345
Feature activation-7.64e-02

Pos logit contributions
flake+0.010
icol+0.009
tha+0.009
AP+0.008
ANG+0.008
Neg logit contributions
 brothers-0.007
 friends-0.006
 more-0.006
 promises-0.006
mun-0.006
Token too
Token ID1165
Feature activation-6.13e-01

Pos logit contributions
 brothers+0.003
 more+0.002
 friends+0.002
 chambers+0.002
 sisters+0.002
Neg logit contributions
icol-0.006
flake-0.006
tha-0.006
iya-0.006
 peac-0.006
Token,
Token ID11
Feature activation+2.09e-02

Pos logit contributions
 brothers+0.025
 chambers+0.023
 more+0.022
 friends+0.021
mun+0.020
Neg logit contributions
flake-0.046
tha-0.043
icol-0.043
 peac-0.042
iya-0.041
Token my
Token ID616
Feature activation+9.99e-01

Pos logit contributions
flake+0.001
tha+0.001
icol+0.001
iya+0.001
 peac+0.001
Neg logit contributions
 brothers-0.001
 chambers-0.001
mun-0.001
 promises-0.001
 more-0.001
Token d
Token ID288
Feature activation+2.59e-01

Pos logit contributions
tha+0.074
flake+0.073
icol+0.072
 peac+0.071
iya+0.069
Neg logit contributions
 brothers-0.040
 friends-0.034
 promises-0.032
 more-0.031
mun-0.030
Tokenarl
Token ID7063
Feature activation+3.28e+00

Pos logit contributions
tha+0.018
flake+0.017
icol+0.017
 peac+0.017
iya+0.017
Neg logit contributions
 brothers-0.011
 of-0.010
ins-0.010
 chambers-0.009
mun-0.009
Tokenings
Token ID654
Feature activation+8.20e-02

Pos logit contributions
tha+0.150
flake+0.148
 peac+0.147
icol+0.146
iya+0.142
Neg logit contributions
 brothers-0.202
mun-0.189
 chambers-0.186
 promises-0.185
 friends-0.179
Token,"
Token ID553
Feature activation+2.85e-01

Pos logit contributions
icol+0.006
tha+0.006
iya+0.006
flake+0.006
ich+0.005
Neg logit contributions
 of-0.004
 brothers-0.004
 more-0.004
mun-0.003
 chambers-0.003
Token she
Token ID673
Feature activation-9.36e-01

Pos logit contributions
tha+0.019
flake+0.019
icol+0.019
iya+0.018
 peac+0.018
Neg logit contributions
 brothers-0.012
 chambers-0.011
mun-0.010
 promises-0.010
 more-0.009
Token said
Token ID531
Feature activation-4.81e-01

Pos logit contributions
 chambers+0.045
 brothers+0.044
mun+0.042
 promises+0.040
 goals+0.040
Neg logit contributions
flake-0.054
tha-0.054
 peac-0.052
essa-0.052
icol-0.052
Token.
Token ID13
Feature activation-3.01e-01

Pos logit contributions
 chambers+0.018
 brothers+0.017
mun+0.016
 goals+0.015
 promises+0.015
Neg logit contributions
tha-0.034
flake-0.033
essa-0.032
iya-0.032
icol-0.032
TokenWhat
Token ID2061
Feature activation+3.11e-01

Pos logit contributions
tha+0.014
flake+0.014
icol+0.014
iya+0.013
 peac+0.013
Neg logit contributions
 brothers-0.010
 chambers-0.009
mun-0.009
 promises-0.008
 more-0.008
Token happened
Token ID3022
Feature activation-2.80e-01

Pos logit contributions
flake+0.012
 peac+0.012
essa+0.012
OW+0.012
work+0.012
Neg logit contributions
 chambers-0.017
mun-0.017
 ang-0.016
irms-0.016
 promises-0.016
Token,
Token ID11
Feature activation-7.34e-02

Pos logit contributions
 brothers+0.009
 questions+0.008
 of+0.008
 more+0.007
 friends+0.007
Neg logit contributions
flake-0.022
tha-0.022
la-0.021
iya-0.021
icol-0.021
Token my
Token ID616
Feature activation+8.11e-01

Pos logit contributions
 brothers+0.003
 chambers+0.003
mun+0.003
 promises+0.002
 goals+0.002
Neg logit contributions
tha-0.005
flake-0.005
icol-0.005
iya-0.005
 peac-0.005
Token d
Token ID288
Feature activation+2.56e-01

Pos logit contributions
flake+0.063
 peac+0.062
AR+0.062
iya+0.061
nes+0.060
Neg logit contributions
 brothers-0.029
 friends-0.025
 twins-0.021
 promises-0.021
 toys-0.021
Tokenarl
Token ID7063
Feature activation+3.28e+00

Pos logit contributions
tha+0.017
flake+0.017
icol+0.016
iya+0.016
 peac+0.016
Neg logit contributions
 brothers-0.011
 of-0.010
 chambers-0.010
ins-0.010
mun-0.009
Tokenings
Token ID654
Feature activation+2.66e-02

Pos logit contributions
tha+0.152
 peac+0.151
icol+0.151
flake+0.148
iya+0.147
Neg logit contributions
 brothers-0.198
mun-0.181
 chambers-0.180
 promises-0.177
 friends-0.175
Token?
Token ID30
Feature activation+1.22e+00

Pos logit contributions
icol+0.002
tha+0.002
iya+0.002
flake+0.002
 peac+0.002
Neg logit contributions
 brothers-0.001
 of-0.001
 chambers-0.001
mun-0.001
 more-0.001
Token Why
Token ID4162
Feature activation+1.35e-01

Pos logit contributions
tha+0.086
flake+0.085
iya+0.083
icol+0.083
essa+0.082
Neg logit contributions
 brothers-0.048
 chambers-0.042
mun-0.040
 promises-0.037
 cabinets-0.035
Token are
Token ID389
Feature activation-2.77e-01

Pos logit contributions
tha+0.011
flake+0.011
icol+0.010
iya+0.010
 peac+0.010
Neg logit contributions
 brothers-0.004
 chambers-0.004
mun-0.003
 promises-0.003
 more-0.003
Token you
Token ID345
Feature activation-4.76e-01

Pos logit contributions
 brothers+0.015
 chambers+0.014
 friends+0.014
 more+0.013
 promises+0.013
Neg logit contributions
flake-0.016
icol-0.016
tha-0.015
iya-0.014
 peac-0.014
Token's
Token ID338
Feature activation-4.94e-01

Pos logit contributions
 brothers+0.007
 more+0.006
mun+0.005
 promises+0.005
 friends+0.004
Neg logit contributions
icol-0.048
tha-0.047
AR-0.046
iya-0.045
OW-0.045
Token good
Token ID922
Feature activation+2.12e-01

Pos logit contributions
 brothers+0.021
 chambers+0.020
mun+0.019
 promises+0.018
 goals+0.017
Neg logit contributions
tha-0.033
flake-0.032
icol-0.031
iya-0.031
 peac-0.031
Token,
Token ID11
Feature activation+1.65e-02

Pos logit contributions
flake+0.016
tha+0.016
icol+0.016
iya+0.015
 peac+0.015
Neg logit contributions
 brothers-0.008
 chambers-0.007
mun-0.006
 friends-0.006
 more-0.006
Token my
Token ID616
Feature activation+8.73e-01

Pos logit contributions
flake+0.001
tha+0.001
icol+0.001
iya+0.001
 peac+0.001
Neg logit contributions
 brothers-0.001
 chambers-0.001
 promises-0.001
 more-0.001
 friends-0.001
Token d
Token ID288
Feature activation+2.26e-01

Pos logit contributions
AR+0.063
storm+0.062
flake+0.059
icol+0.058
nes+0.058
Neg logit contributions
 brothers-0.039
 friends-0.039
 promises-0.034
 more-0.032
 sisters-0.031
Tokenarl
Token ID7063
Feature activation+3.27e+00

Pos logit contributions
icol+0.015
tha+0.015
flake+0.015
iya+0.015
storm+0.014
Neg logit contributions
 of-0.010
 brothers-0.009
ins-0.009
 chambers-0.008
oll-0.008
Tokenings
Token ID654
Feature activation+8.20e-04

Pos logit contributions
icol+0.148
tha+0.148
 peac+0.147
flake+0.145
iya+0.143
Neg logit contributions
 brothers-0.200
mun-0.186
 chambers-0.184
 promises-0.183
 friends-0.177
Token.
Token ID13
Feature activation-4.97e-02

Pos logit contributions
tha+0.000
icol+0.000
flake+0.000
iya+0.000
 peac+0.000
Neg logit contributions
 brothers-0.000
 chambers-0.000
mun-0.000
 more-0.000
 of-0.000
Token I
Token ID314
Feature activation-6.59e-02

Pos logit contributions
 brothers+0.002
 chambers+0.002
 promises+0.002
mun+0.002
 goals+0.002
Neg logit contributions
flake-0.003
tha-0.003
iya-0.003
essa-0.003
la-0.003
Token'm
Token ID1101
Feature activation+8.70e-01

Pos logit contributions
 brothers+0.003
mun+0.002
 promises+0.002
 chambers+0.002
 more+0.002
Neg logit contributions
tha-0.005
icol-0.004
flake-0.004
iya-0.004
essa-0.004
Token glad
Token ID9675
Feature activation+3.15e-01

Pos logit contributions
flake+0.075
icol+0.073
tha+0.071
storm+0.070
iya+0.069
Neg logit contributions
 brothers-0.024
 more-0.021
 friends-0.019
 promises-0.018
mun-0.017
Tokens
Token ID82
Feature activation-1.25e+00

Pos logit contributions
 brothers+0.033
mun+0.030
 chambers+0.028
 promises+0.025
 of+0.024
Neg logit contributions
tha-0.090
flake-0.090
icol-0.090
 peac-0.087
iya-0.087
Token wrong
Token ID2642
Feature activation+1.86e-01

Pos logit contributions
 brothers+0.063
 chambers+0.058
 promises+0.054
 chores+0.054
 more+0.054
Neg logit contributions
flake-0.078
icol-0.076
tha-0.074
 peac-0.071
iya-0.071
Token,
Token ID11
Feature activation-5.13e-01

Pos logit contributions
flake+0.013
 peac+0.012
OW+0.012
tha+0.012
icol+0.012
Neg logit contributions
 brothers-0.008
 friends-0.007
 of-0.006
 chambers-0.006
 more-0.006
Token rh
Token ID9529
Feature activation-4.81e-01

Pos logit contributions
 brothers+0.025
 friends+0.021
 more+0.020
 promises+0.020
 chambers+0.020
Neg logit contributions
flake-0.035
icol-0.033
tha-0.033
storm-0.031
 peac-0.031
Tokenin
Token ID259
Feature activation+1.18e-01

Pos logit contributions
 brothers+0.018
 chambers+0.016
mun+0.016
 promises+0.014
 more+0.014
Neg logit contributions
tha-0.035
flake-0.035
icol-0.034
iya-0.033
 peac-0.033
Tokenoc
Token ID420
Feature activation-4.63e+00

Pos logit contributions
icol+0.007
tha+0.007
flake+0.007
essa+0.006
iya+0.006
Neg logit contributions
 brothers-0.006
mun-0.005
 chambers-0.005
 more-0.005
 promises-0.005
Tokeneros
Token ID27498
Feature activation+2.55e-01

Pos logit contributions
 brothers+0.298
mun+0.268
ins+0.266
 chambers+0.260
 friends+0.257
Neg logit contributions
flake-0.219
iya-0.210
tha-0.210
icol-0.209
storm-0.201
Token?
Token ID30
Feature activation+7.98e-01

Pos logit contributions
icol+0.016
tha+0.015
flake+0.015
iya+0.015
essa+0.015
Neg logit contributions
 brothers-0.014
 friends-0.012
mun-0.011
 chambers-0.011
 of-0.011
Tokenâ
Token ID22940
Feature activation+7.63e-01

Pos logit contributions
flake+0.055
tha+0.055
icol+0.054
iya+0.052
essa+0.052
Neg logit contributions
 brothers-0.034
 chambers-0.029
mun-0.028
 of-0.026
 So-0.026
Token
Token ID26391
Feature activation-3.10e-01

Pos logit contributions
 peac+0.040
icol+0.037
flake+0.037
iya+0.037
tha+0.037
Neg logit contributions
 brothers-0.042
 promises-0.038
mun-0.037
 exercises-0.035
 chambers-0.035
Token said
Token ID531
Feature activation-7.06e-02

Pos logit contributions
 brothers+0.011
mun+0.009
 chambers+0.008
 friends+0.008
es+0.008
Neg logit contributions
flake-0.022
tha-0.022
essa-0.022
 peac-0.021
work-0.021
Token give
Token ID1577
Feature activation-6.43e-01

Pos logit contributions
 brothers+0.026
 more+0.025
 chambers+0.025
 friends+0.023
 promises+0.023
Neg logit contributions
icol-0.063
tha-0.062
flake-0.061
iya-0.060
essa-0.060
Token to
Token ID284
Feature activation-1.12e-01

Pos logit contributions
 more+0.026
 brothers+0.026
 promises+0.025
 friends+0.025
mun+0.023
Neg logit contributions
icol-0.045
flake-0.045
storm-0.044
tha-0.044
iya-0.043
Token the
Token ID262
Feature activation-2.81e-01

Pos logit contributions
 brothers+0.004
 chambers+0.003
 promises+0.003
 more+0.003
 friends+0.003
Neg logit contributions
flake-0.009
tha-0.009
icol-0.008
iya-0.008
essa-0.008
Token rh
Token ID9529
Feature activation-6.23e-01

Pos logit contributions
 brothers+0.012
 friends+0.010
 chambers+0.010
 more+0.010
 promises+0.009
Neg logit contributions
tha-0.020
icol-0.020
iya-0.020
flake-0.019
la-0.019
Tokenin
Token ID259
Feature activation+2.07e-01

Pos logit contributions
 brothers+0.024
 chambers+0.023
mun+0.022
 promises+0.021
 more+0.020
Neg logit contributions
flake-0.043
tha-0.042
 peac-0.040
iya-0.040
icol-0.040
Tokenoc
Token ID420
Feature activation-4.61e+00

Pos logit contributions
tha+0.018
flake+0.018
icol+0.018
iya+0.017
essa+0.017
Neg logit contributions
 brothers-0.005
 chambers-0.004
mun-0.004
 promises-0.003
 more-0.003
Tokeneros
Token ID27498
Feature activation-2.10e-02

Pos logit contributions
 brothers+0.311
 promises+0.284
mun+0.278
 chambers+0.277
 more+0.268
Neg logit contributions
flake-0.195
iya-0.190
tha-0.188
icol-0.187
essa-0.185
Token.
Token ID13
Feature activation-8.74e-02

Pos logit contributions
 brothers+0.001
 chambers+0.001
 more+0.001
 friends+0.001
 promises+0.001
Neg logit contributions
tha-0.002
icol-0.002
flake-0.002
iya-0.002
essa-0.002
Token Lily
Token ID20037
Feature activation-4.76e-01

Pos logit contributions
 brothers+0.002
 chambers+0.002
 So+0.002
mun+0.002
 promises+0.002
Neg logit contributions
flake-0.007
tha-0.007
iya-0.007
essa-0.007
 peac-0.007
Token walked
Token ID6807
Feature activation-8.75e-01

Pos logit contributions
 brothers+0.016
mun+0.014
 chambers+0.014
 promises+0.013
 more+0.012
Neg logit contributions
tha-0.037
flake-0.036
 peac-0.035
icol-0.035
iya-0.035
Token to
Token ID284
Feature activation+3.77e-02

Pos logit contributions
 brothers+0.033
 more+0.032
 chambers+0.031
 questions+0.029
 friends+0.029
Neg logit contributions
flake-0.062
tha-0.062
 peac-0.061
icol-0.060
iya-0.060
Token it
Token ID340
Feature activation+7.36e-01

Pos logit contributions
flake+0.006
storm+0.006
icol+0.006
tha+0.006
 peac+0.006
Neg logit contributions
 brothers-0.003
 friends-0.003
 promises-0.003
 more-0.003
mun-0.003
Token to
Token ID284
Feature activation-2.33e-01

Pos logit contributions
tha+0.054
flake+0.052
iya+0.051
icol+0.051
essa+0.048
Neg logit contributions
 more-0.030
 brothers-0.030
 friends-0.029
 promises-0.028
 chambers-0.027
Token the
Token ID262
Feature activation-5.53e-01

Pos logit contributions
 brothers+0.008
 friends+0.007
 more+0.007
 promises+0.006
 other+0.006
Neg logit contributions
flake-0.019
icol-0.019
tha-0.018
ANG-0.018
ich-0.017
Token rh
Token ID9529
Feature activation-5.57e-01

Pos logit contributions
 brothers+0.025
 more+0.022
 friends+0.022
 chambers+0.020
 other+0.020
Neg logit contributions
tha-0.039
icol-0.037
flake-0.037
enda-0.037
da-0.037
Tokenin
Token ID259
Feature activation+1.25e-02

Pos logit contributions
 brothers+0.021
 chambers+0.020
mun+0.019
 promises+0.018
 more+0.017
Neg logit contributions
tha-0.039
flake-0.039
icol-0.037
iya-0.037
 peac-0.037
Tokenoc
Token ID420
Feature activation-4.42e+00

Pos logit contributions
tha+0.001
flake+0.001
icol+0.001
iya+0.001
essa+0.001
Neg logit contributions
 brothers-0.000
 chambers-0.000
mun-0.000
 promises-0.000
 more-0.000
Tokeneros
Token ID27498
Feature activation-8.10e-02

Pos logit contributions
 brothers+0.298
 promises+0.272
mun+0.259
 chambers+0.259
 friends+0.253
Neg logit contributions
flake-0.189
iya-0.187
essa-0.183
icol-0.183
tha-0.180
Token.
Token ID13
Feature activation+2.18e-02

Pos logit contributions
 brothers+0.002
 chambers+0.002
mun+0.002
 promises+0.002
 more+0.002
Neg logit contributions
tha-0.007
icol-0.006
flake-0.006
iya-0.006
essa-0.006
Token When
Token ID1649
Feature activation+1.32e-01

Pos logit contributions
flake+0.002
tha+0.002
 peac+0.002
essa+0.002
icol+0.002
Neg logit contributions
 brothers-0.001
 So-0.001
 chambers-0.001
mun-0.000
 friends-0.000
Token he
Token ID339
Feature activation-2.91e-01

Pos logit contributions
flake+0.011
icol+0.011
tha+0.011
OW+0.011
essa+0.011
Neg logit contributions
 brothers-0.004
 more-0.003
 friends-0.003
 chambers-0.003
 cookies-0.003
Token tasted
Token ID29187
Feature activation-6.91e-01

Pos logit contributions
 brothers+0.010
mun+0.009
 chambers+0.008
 more+0.008
 promises+0.008
Neg logit contributions
tha-0.022
flake-0.022
icol-0.022
essa-0.021
iya-0.021
Token
Token ID198
Feature activation+3.79e-01

Pos logit contributions
flake+0.009
tha+0.009
icol+0.009
 peac+0.008
iya+0.008
Neg logit contributions
 brothers-0.004
 chambers-0.004
mun-0.004
 promises-0.003
 more-0.003
Token"
Token ID1
Feature activation+7.09e-01

Pos logit contributions
flake+0.025
tha+0.024
icol+0.024
 peac+0.023
iya+0.023
Neg logit contributions
 brothers-0.017
 chambers-0.016
mun-0.015
 promises-0.014
 more-0.014
TokenThe
Token ID464
Feature activation+3.65e-01

Pos logit contributions
tha+0.045
icol+0.045
flake+0.044
iya+0.042
 peac+0.042
Neg logit contributions
 brothers-0.030
mun-0.029
 chambers-0.028
 more-0.027
 promises-0.026
Token rh
Token ID9529
Feature activation-1.74e-01

Pos logit contributions
flake+0.024
tha+0.024
iya+0.023
icol+0.023
enda+0.023
Neg logit contributions
 brothers-0.017
 friends-0.015
 chambers-0.015
 more-0.015
 questions-0.015
Tokenin
Token ID259
Feature activation+1.92e-01

Pos logit contributions
 brothers+0.007
 chambers+0.006
mun+0.006
 promises+0.005
 more+0.005
Neg logit contributions
icol-0.013
tha-0.013
flake-0.012
iya-0.012
essa-0.012
Tokenoc
Token ID420
Feature activation-4.32e+00

Pos logit contributions
icol+0.019
essa+0.018
iya+0.018
tha+0.018
flake+0.018
Neg logit contributions
 brothers-0.003
 chambers-0.002
 promises-0.002
 friends-0.002
 more-0.002
Tokeneros
Token ID27498
Feature activation-6.87e-02

Pos logit contributions
 brothers+0.287
 promises+0.261
mun+0.254
 chambers+0.253
ins+0.248
Neg logit contributions
icol-0.186
iya-0.186
flake-0.182
storm-0.178
essa-0.177
Token is
Token ID318
Feature activation+2.64e-01

Pos logit contributions
 brothers+0.002
 promises+0.002
 more+0.002
 chambers+0.002
 friends+0.002
Neg logit contributions
icol-0.006
iya-0.006
essa-0.006
flake-0.006
tha-0.005
Token in
Token ID287
Feature activation-1.02e-01

Pos logit contributions
flake+0.021
icol+0.021
iya+0.021
tha+0.020
essa+0.020
Neg logit contributions
 more-0.010
 brothers-0.010
 friends-0.008
 of-0.008
 chambers-0.007
Token there
Token ID612
Feature activation-8.95e-01

Pos logit contributions
 brothers+0.003
 more+0.003
 chambers+0.003
 of+0.003
 friends+0.003
Neg logit contributions
flake-0.008
icol-0.008
tha-0.008
essa-0.008
iya-0.008
Token,
Token ID11
Feature activation-3.19e-01

Pos logit contributions
 more+0.034
 brothers+0.034
 of+0.033
 friends+0.032
 chambers+0.030
Neg logit contributions
icol-0.072
flake-0.065
 peac-0.065
tha-0.065
iya-0.064
Token't
Token ID470
Feature activation+7.47e-01

Pos logit contributions
 more+0.001
 brothers+0.000
 of+0.000
 cookies+0.000
 friends+0.000
Neg logit contributions
flake-0.001
icol-0.001
tha-0.001
iya-0.001
ich-0.001
Token know
Token ID760
Feature activation-3.56e-01

Pos logit contributions
flake+0.059
icol+0.059
tha+0.058
iya+0.055
essa+0.053
Neg logit contributions
 brothers-0.026
 friends-0.023
 more-0.022
 chambers-0.022
 promises-0.021
Token the
Token ID262
Feature activation+1.87e-01

Pos logit contributions
 brothers+0.012
 chambers+0.011
 more+0.011
 friends+0.010
 ways+0.010
Neg logit contributions
flake-0.028
icol-0.028
tha-0.028
iya-0.027
 peac-0.026
Token rh
Token ID9529
Feature activation-7.89e-02

Pos logit contributions
tha+0.013
icol+0.013
iya+0.012
flake+0.012
enda+0.012
Neg logit contributions
 brothers-0.008
 more-0.007
 chambers-0.007
 friends-0.007
 questions-0.007
Tokenin
Token ID259
Feature activation+7.18e-01

Pos logit contributions
 brothers+0.003
 chambers+0.003
mun+0.003
 promises+0.002
 more+0.002
Neg logit contributions
tha-0.006
icol-0.006
flake-0.006
iya-0.005
 peac-0.005
Tokenoc
Token ID420
Feature activation-4.29e+00

Pos logit contributions
tha+0.065
icol+0.064
iya+0.063
flake+0.063
essa+0.062
Neg logit contributions
 brothers-0.014
mun-0.011
 chambers-0.010
 promises-0.010
 more-0.010
Tokeneros
Token ID27498
Feature activation+6.33e-01

Pos logit contributions
 brothers+0.288
 promises+0.265
mun+0.263
 chambers+0.255
ins+0.250
Neg logit contributions
flake-0.181
iya-0.180
icol-0.177
tha-0.175
essa-0.170
Token was
Token ID373
Feature activation+2.23e-01

Pos logit contributions
icol+0.053
flake+0.051
tha+0.051
iya+0.050
essa+0.049
Neg logit contributions
 brothers-0.019
 chambers-0.016
mun-0.015
 more-0.015
 friends-0.015
Token wild
Token ID4295
Feature activation-2.25e-01

Pos logit contributions
flake+0.016
icol+0.016
tha+0.016
iya+0.016
essa+0.016
Neg logit contributions
 brothers-0.009
 more-0.009
 friends-0.008
 chambers-0.007
 of-0.007
Token.
Token ID13
Feature activation+7.99e-02

Pos logit contributions
 brothers+0.008
 chambers+0.007
mun+0.007
 promises+0.006
 more+0.006
Neg logit contributions
tha-0.017
flake-0.017
iya-0.017
icol-0.016
 peac-0.016
Token Can
Token ID1680
Feature activation-3.59e-01

Pos logit contributions
flake+0.007
tha+0.007
icol+0.006
essa+0.006
iya+0.006
Neg logit contributions
 brothers-0.002
 So-0.002
 chambers-0.002
 of-0.001
mun-0.001
Token mess
Token ID2085
Feature activation+3.46e-01

Pos logit contributions
flake+0.005
tha+0.005
la+0.005
essa+0.005
OW+0.005
Neg logit contributions
 brothers-0.003
 more-0.003
 chambers-0.002
 promises-0.002
 friends-0.002
Token.
Token ID13
Feature activation-4.35e-02

Pos logit contributions
tha+0.027
flake+0.027
icol+0.027
iya+0.026
 peac+0.026
Neg logit contributions
 brothers-0.010
 chambers-0.009
mun-0.009
 more-0.008
 promises-0.008
Token The
Token ID383
Feature activation+1.13e-01

Pos logit contributions
 brothers+0.001
 chambers+0.001
mun+0.001
 promises+0.001
 ways+0.001
Neg logit contributions
flake-0.004
tha-0.004
 peac-0.004
icol-0.003
iya-0.003
Token rh
Token ID9529
Feature activation-3.79e-01

Pos logit contributions
tha+0.008
flake+0.008
icol+0.007
iya+0.007
la+0.007
Neg logit contributions
 brothers-0.005
 chambers-0.004
 friends-0.004
 more-0.004
mun-0.004
Tokenin
Token ID259
Feature activation+2.54e-01

Pos logit contributions
 brothers+0.015
 chambers+0.014
mun+0.013
 promises+0.013
 more+0.012
Neg logit contributions
flake-0.026
tha-0.026
 peac-0.024
iya-0.024
icol-0.024
Tokenoc
Token ID420
Feature activation-4.27e+00

Pos logit contributions
tha+0.022
flake+0.022
icol+0.021
iya+0.021
essa+0.021
Neg logit contributions
 brothers-0.006
 chambers-0.005
mun-0.004
 promises-0.004
 more-0.004
Tokeneros
Token ID27498
Feature activation-1.29e-01

Pos logit contributions
 brothers+0.292
 chambers+0.271
 promises+0.269
mun+0.268
ins+0.254
Neg logit contributions
flake-0.166
iya-0.165
icol-0.160
tha-0.160
OW-0.155
Token had
Token ID550
Feature activation-1.50e-01

Pos logit contributions
 brothers+0.004
 chambers+0.004
mun+0.004
 more+0.003
 promises+0.003
Neg logit contributions
tha-0.010
icol-0.010
flake-0.010
iya-0.010
essa-0.010
Token destroyed
Token ID6572
Feature activation+1.02e+00

Pos logit contributions
 brothers+0.006
 more+0.006
 chambers+0.006
 friends+0.006
 of+0.005
Neg logit contributions
tha-0.011
flake-0.011
icol-0.010
iya-0.010
essa-0.010
Token her
Token ID607
Feature activation-7.29e-01

Pos logit contributions
flake+0.083
tha+0.082
iya+0.081
 peac+0.080
icol+0.080
Neg logit contributions
 brothers-0.029
 more-0.027
 chambers-0.027
 ways-0.025
 friends-0.024
Token room
Token ID2119
Feature activation-8.85e-01

Pos logit contributions
 brothers+0.030
 chambers+0.027
 promises+0.026
 friends+0.026
 more+0.026
Neg logit contributions
tha-0.051
flake-0.050
iya-0.050
icol-0.049
essa-0.049
Token,
Token ID11
Feature activation-2.72e-01

Pos logit contributions
icol+0.015
flake+0.015
AR+0.014
tha+0.014
iya+0.014
Neg logit contributions
 more-0.004
 of-0.004
 brothers-0.003
 friends-0.003
 questions-0.003
Token "
Token ID366
Feature activation-3.75e-01

Pos logit contributions
 brothers+0.006
 questions+0.005
 of+0.004
 more+0.004
 friends+0.003
Neg logit contributions
tha-0.024
flake-0.024
icol-0.024
iya-0.023
essa-0.023
TokenThe
Token ID464
Feature activation+1.48e-01

Pos logit contributions
mun+0.015
 brothers+0.015
 promises+0.013
 more+0.013
 chambers+0.013
Neg logit contributions
tha-0.025
icol-0.025
flake-0.025
iya-0.023
essa-0.023
Token rh
Token ID9529
Feature activation-5.04e-01

Pos logit contributions
flake+0.010
tha+0.009
enda+0.009
icol+0.009
la+0.009
Neg logit contributions
 brothers-0.008
 friends-0.007
 more-0.007
 promises-0.006
 other-0.006
Tokenin
Token ID259
Feature activation-1.56e-02

Pos logit contributions
 brothers+0.019
 chambers+0.017
mun+0.017
 promises+0.016
 more+0.015
Neg logit contributions
tha-0.036
flake-0.036
icol-0.035
iya-0.034
 peac-0.034
Tokenoc
Token ID420
Feature activation-4.26e+00

Pos logit contributions
 brothers+0.000
mun+0.000
 promises+0.000
 chambers+0.000
 more+0.000
Neg logit contributions
icol-0.002
tha-0.001
essa-0.001
iya-0.001
flake-0.001
Tokeneros
Token ID27498
Feature activation-2.05e-01

Pos logit contributions
 brothers+0.283
 promises+0.257
mun+0.256
 chambers+0.251
ins+0.242
Neg logit contributions
iya-0.183
flake-0.179
icol-0.179
essa-0.173
 Gina-0.172
Token made
Token ID925
Feature activation+3.35e-01

Pos logit contributions
 brothers+0.007
 chambers+0.006
 promises+0.006
mun+0.005
 friends+0.005
Neg logit contributions
icol-0.017
flake-0.016
tha-0.016
iya-0.016
essa-0.016
Token a
Token ID257
Feature activation-4.20e-01

Pos logit contributions
flake+0.024
tha+0.023
icol+0.022
storm+0.022
iya+0.022
Neg logit contributions
 brothers-0.016
 more-0.015
 friends-0.015
 promises-0.014
 of-0.013
Token big
Token ID1263
Feature activation+2.15e-01

Pos logit contributions
 brothers+0.015
 more+0.013
 chambers+0.013
 friends+0.012
 promises+0.012
Neg logit contributions
tha-0.032
flake-0.031
essa-0.030
la-0.030
iya-0.030
Token mess
Token ID2085
Feature activation+1.80e-01

Pos logit contributions
tha+0.015
flake+0.015
la+0.015
essa+0.015
iya+0.015
Neg logit contributions
 brothers-0.009
 more-0.009
 promises-0.008
 friends-0.008
 chambers-0.008
Token mom
Token ID1995
Feature activation-1.59e+00

Pos logit contributions
mun+0.056
 chambers+0.055
 brothers+0.051
ins+0.049
 goals+0.049
Neg logit contributions
tha-0.047
flake-0.044
icol-0.042
iya-0.042
essa-0.041
Token said
Token ID531
Feature activation-5.75e-01

Pos logit contributions
 brothers+0.063
mun+0.053
 chambers+0.051
 more+0.050
 promises+0.050
Neg logit contributions
icol-0.110
tha-0.109
flake-0.109
iya-0.107
 peac-0.106
Token,
Token ID11
Feature activation-6.51e-01

Pos logit contributions
 more+0.013
 brothers+0.013
 of+0.013
 friends+0.010
mun+0.010
Neg logit contributions
icol-0.048
iya-0.048
 peac-0.048
flake-0.047
AR-0.047
Token "
Token ID366
Feature activation-6.34e-01

Pos logit contributions
 brothers+0.015
 more+0.012
mun+0.011
 questions+0.010
 of+0.010
Neg logit contributions
icol-0.055
flake-0.055
tha-0.055
iya-0.054
 peac-0.054
TokenC
Token ID34
Feature activation-1.11e+00

Pos logit contributions
 brothers+0.025
mun+0.024
ins+0.023
 of+0.022
 more+0.022
Neg logit contributions
tha-0.043
icol-0.043
essa-0.039
iya-0.039
 peac-0.038
Tokenoc
Token ID420
Feature activation-4.21e+00

Pos logit contributions
 brothers+0.066
 chambers+0.064
mun+0.062
 promises+0.061
 more+0.058
Neg logit contributions
tha-0.054
flake-0.053
icol-0.051
 peac-0.050
iya-0.050
Tokenoa
Token ID12162
Feature activation-6.11e-01

Pos logit contributions
 brothers+0.248
ins+0.227
mun+0.227
 promises+0.221
 chambers+0.217
Neg logit contributions
iya-0.202
icol-0.201
 peac-0.199
tha-0.193
flake-0.191
Token is
Token ID318
Feature activation-2.47e-01

Pos logit contributions
 brothers+0.026
mun+0.021
 chambers+0.021
ins+0.020
 more+0.020
Neg logit contributions
icol-0.044
 peac-0.042
AR-0.042
tha-0.041
flake-0.041
Token a
Token ID257
Feature activation-7.50e-01

Pos logit contributions
 brothers+0.009
 more+0.008
 chambers+0.007
 friends+0.007
 y+0.007
Neg logit contributions
icol-0.018
flake-0.018
tha-0.018
 peac-0.018
iya-0.018
Token strong
Token ID1913
Feature activation-2.82e-01

Pos logit contributions
 y+0.020
 brothers+0.019
 more+0.018
 cookies+0.016
 sleepy+0.015
Neg logit contributions
tha-0.063
la-0.062
essa-0.061
oot-0.059
iya-0.059
Token drink
Token ID4144
Feature activation-5.06e-01

Pos logit contributions
 brothers+0.010
 more+0.009
 of+0.008
 promises+0.008
mun+0.008
Neg logit contributions
tha-0.021
la-0.021
AR-0.020
essa-0.020
icol-0.020
Token She
Token ID1375
Feature activation+1.49e-01

Pos logit contributions
tha+0.025
flake+0.024
iya+0.024
icol+0.024
 peac+0.023
Neg logit contributions
 brothers-0.009
 chambers-0.008
mun-0.007
 promises-0.007
 goals-0.007
Token loved
Token ID6151
Feature activation+4.81e-01

Pos logit contributions
tha+0.014
flake+0.014
AR+0.014
iya+0.013
icol+0.013
Neg logit contributions
 brothers-0.003
 friends-0.002
mun-0.002
 more-0.002
 happy-0.001
Token to
Token ID284
Feature activation+8.57e-01

Pos logit contributions
tha+0.030
flake+0.029
icol+0.027
iya+0.027
 peac+0.027
Neg logit contributions
 brothers-0.024
 chambers-0.022
mun-0.021
 more-0.020
 promises-0.020
Token eat
Token ID4483
Feature activation-4.72e-01

Pos logit contributions
tha+0.067
flake+0.066
icol+0.064
iya+0.064
la+0.063
Neg logit contributions
 brothers-0.027
 chambers-0.024
mun-0.022
 promises-0.022
 more-0.021
Token av
Token ID1196
Feature activation-1.26e+00

Pos logit contributions
 brothers+0.018
 chambers+0.017
mun+0.016
 promises+0.015
 goals+0.014
Neg logit contributions
flake-0.031
tha-0.030
essa-0.030
iya-0.030
 peac-0.030
Tokenoc
Token ID420
Feature activation-4.17e+00

Pos logit contributions
 brothers+0.050
 chambers+0.048
mun+0.044
 sisters+0.044
 questions+0.043
Neg logit contributions
flake-0.080
 peac-0.077
icol-0.076
OW-0.076
tha-0.076
Tokenados
Token ID22484
Feature activation+4.15e-01

Pos logit contributions
 brothers+0.201
 chambers+0.191
mun+0.185
 promises+0.179
 more+0.170
Neg logit contributions
flake-0.249
tha-0.248
icol-0.237
iya-0.234
 peac-0.233
Token.
Token ID13
Feature activation-1.60e-01

Pos logit contributions
flake+0.027
tha+0.027
iya+0.025
 peac+0.025
essa+0.025
Neg logit contributions
 brothers-0.017
 chambers-0.016
mun-0.016
 promises-0.015
 goals-0.014
Token One
Token ID1881
Feature activation-9.56e-02

Pos logit contributions
 brothers+0.006
 chambers+0.005
mun+0.005
 promises+0.005
 more+0.004
Neg logit contributions
tha-0.012
flake-0.012
icol-0.011
iya-0.011
 peac-0.011
Token day
Token ID1110
Feature activation-7.61e-01

Pos logit contributions
mun+0.006
 chambers+0.006
 goals+0.006
 brothers+0.006
 promises+0.006
Neg logit contributions
flake-0.004
tha-0.004
iya-0.004
storm-0.004
 peac-0.004
Token,
Token ID11
Feature activation-1.30e-01

Pos logit contributions
 brothers+0.030
 chambers+0.028
mun+0.027
 more+0.025
 promises+0.025
Neg logit contributions
flake-0.053
tha-0.053
icol-0.051
iya-0.050
 peac-0.050
Token't
Token ID470
Feature activation+1.82e-01

Pos logit contributions
 brothers+0.030
 of+0.028
mun+0.028
 chambers+0.028
 more+0.028
Neg logit contributions
icol-0.018
flake-0.018
tha-0.017
iya-0.017
 peac-0.017
Token touch
Token ID3638
Feature activation-1.79e-01

Pos logit contributions
icol+0.015
flake+0.015
tha+0.015
la+0.014
iya+0.014
Neg logit contributions
 friends-0.006
 of-0.006
 more-0.006
 brothers-0.006
 promises-0.005
Token the
Token ID262
Feature activation-1.86e-01

Pos logit contributions
 more+0.008
 brothers+0.008
 friends+0.007
 of+0.007
 ways+0.007
Neg logit contributions
icol-0.013
tha-0.012
flake-0.012
iya-0.012
 peac-0.011
Token rh
Token ID9529
Feature activation-3.12e-01

Pos logit contributions
 brothers+0.008
 more+0.007
 friends+0.007
 cookies+0.007
 chambers+0.007
Neg logit contributions
tha-0.013
icol-0.012
iya-0.012
enda-0.012
da-0.012
Tokenin
Token ID259
Feature activation+4.31e-01

Pos logit contributions
 brothers+0.012
 chambers+0.012
mun+0.011
 promises+0.011
 more+0.010
Neg logit contributions
tha-0.021
flake-0.021
icol-0.020
iya-0.020
 peac-0.020
Tokenoc
Token ID420
Feature activation-4.14e+00

Pos logit contributions
tha+0.040
icol+0.039
iya+0.038
essa+0.038
flake+0.038
Neg logit contributions
 brothers-0.008
 chambers-0.006
mun-0.005
 more-0.005
 promises-0.005
Tokeneros
Token ID27498
Feature activation+1.05e-01

Pos logit contributions
 brothers+0.278
mun+0.257
 promises+0.256
ins+0.244
 chambers+0.243
Neg logit contributions
flake-0.167
iya-0.167
icol-0.165
tha-0.162
 Gina-0.161
Token!
Token ID0
Feature activation+5.16e-01

Pos logit contributions
icol+0.005
tha+0.005
iya+0.005
essa+0.005
 peac+0.005
Neg logit contributions
 brothers-0.006
 more-0.006
 chambers-0.006
 promises-0.006
 of-0.006
Token It
Token ID632
Feature activation-2.68e-01

Pos logit contributions
tha+0.036
flake+0.035
icol+0.035
iya+0.034
 peac+0.034
Neg logit contributions
 brothers-0.021
 So-0.017
 of-0.017
 chambers-0.017
 promises-0.016
Token might
Token ID1244
Feature activation-5.98e-01

Pos logit contributions
 brothers+0.008
 chambers+0.007
mun+0.007
 promises+0.007
 more+0.007
Neg logit contributions
tha-0.021
flake-0.020
iya-0.020
icol-0.020
essa-0.020
Token bite
Token ID13197
Feature activation-5.44e-01

Pos logit contributions
 more+0.018
 of+0.016
 chew+0.014
 y+0.014
 other+0.014
Neg logit contributions
icol-0.053
iya-0.050
tha-0.050
essa-0.049
la-0.049
Token goodbye
Token ID24829
Feature activation+8.32e-01

Pos logit contributions
flake+0.027
tha+0.026
icol+0.026
iya+0.025
OW+0.025
Neg logit contributions
 brothers-0.013
 more-0.012
 friends-0.011
 questions-0.010
 of-0.010
Token to
Token ID284
Feature activation-4.44e-01

Pos logit contributions
tha+0.063
opter+0.062
flake+0.062
icol+0.062
iya+0.061
Neg logit contributions
 more-0.029
 brothers-0.026
 friends-0.025
 of-0.025
 promises-0.024
Token the
Token ID262
Feature activation-4.24e-01

Pos logit contributions
 brothers+0.015
 more+0.013
 promises+0.013
 chambers+0.013
 friends+0.012
Neg logit contributions
flake-0.035
icol-0.033
tha-0.033
iya-0.033
storm-0.032
Token rh
Token ID9529
Feature activation-5.95e-01

Pos logit contributions
 brothers+0.023
 friends+0.021
 chambers+0.020
 more+0.020
 promises+0.020
Neg logit contributions
tha-0.025
flake-0.025
icol-0.025
iya-0.024
la-0.024
Tokenin
Token ID259
Feature activation+1.68e-01

Pos logit contributions
 brothers+0.023
 chambers+0.021
mun+0.021
 promises+0.020
 more+0.018
Neg logit contributions
tha-0.041
flake-0.041
icol-0.040
iya-0.039
 peac-0.039
Tokenoc
Token ID420
Feature activation-4.12e+00

Pos logit contributions
flake+0.013
tha+0.013
 peac+0.013
iya+0.013
icol+0.013
Neg logit contributions
 brothers-0.005
 chambers-0.004
mun-0.004
 promises-0.004
 goals-0.004
Tokeneros
Token ID27498
Feature activation-4.63e-01

Pos logit contributions
 brothers+0.262
 promises+0.250
mun+0.237
 chambers+0.235
ins+0.225
Neg logit contributions
iya-0.172
icol-0.169
 Gina-0.167
flake-0.165
essa-0.165
Token.
Token ID13
Feature activation-1.83e-01

Pos logit contributions
 brothers+0.016
 chambers+0.015
mun+0.015
 promises+0.013
 goals+0.012
Neg logit contributions
flake-0.034
tha-0.033
 peac-0.032
iya-0.032
icol-0.032
Token They
Token ID1119
Feature activation+1.30e-01

Pos logit contributions
 brothers+0.004
 chambers+0.004
 So+0.003
 promises+0.003
 more+0.003
Neg logit contributions
flake-0.016
tha-0.016
iya-0.016
essa-0.015
ich-0.015
Token say
Token ID910
Feature activation+2.77e-01

Pos logit contributions
tha+0.009
flake+0.009
icol+0.008
 peac+0.008
iya+0.008
Neg logit contributions
 brothers-0.005
 chambers-0.005
mun-0.005
 promises-0.004
ins-0.004
Token they
Token ID484
Feature activation+3.99e-01

Pos logit contributions
flake+0.020
tha+0.020
icol+0.019
iya+0.019
OW+0.019
Neg logit contributions
 brothers-0.011
 more-0.010
 friends-0.009
 chambers-0.009
 questions-0.009
Token
Token ID26391
Feature activation-2.36e-01

Pos logit contributions
 peac+0.045
flake+0.043
icol+0.042
iya+0.042
tha+0.042
Neg logit contributions
 brothers-0.047
 promises-0.046
mun-0.045
 more-0.041
 chambers-0.041
Token replied
Token ID8712
Feature activation+4.24e-02

Pos logit contributions
 brothers+0.010
mun+0.009
 promises+0.009
 friends+0.008
 chambers+0.008
Neg logit contributions
flake-0.016
tha-0.015
essa-0.015
 peac-0.015
work-0.015
Token the
Token ID262
Feature activation-4.77e-01

Pos logit contributions
flake+0.004
tha+0.004
storm+0.004
 peac+0.003
iya+0.003
Neg logit contributions
 of-0.001
 brothers-0.001
 friends-0.001
 more-0.001
 his-0.001
Token rh
Token ID9529
Feature activation-4.05e-01

Pos logit contributions
 brothers+0.022
 friends+0.018
 more+0.018
 chambers+0.018
 goals+0.017
Neg logit contributions
tha-0.035
flake-0.034
icol-0.033
iya-0.032
essa-0.032
Tokenin
Token ID259
Feature activation+3.14e-01

Pos logit contributions
 brothers+0.015
 chambers+0.014
mun+0.013
 promises+0.012
 more+0.012
Neg logit contributions
tha-0.029
flake-0.029
icol-0.028
iya-0.028
 peac-0.027
Tokenoc
Token ID420
Feature activation-4.12e+00

Pos logit contributions
tha+0.030
icol+0.029
iya+0.029
essa+0.029
flake+0.028
Neg logit contributions
 brothers-0.005
 chambers-0.003
 more-0.003
mun-0.003
 promises-0.003
Tokeneros
Token ID27498
Feature activation-1.35e-01

Pos logit contributions
 brothers+0.268
 promises+0.249
ins+0.241
mun+0.241
 chambers+0.238
Neg logit contributions
iya-0.169
icol-0.165
tha-0.163
flake-0.163
storm-0.162
Token sadly
Token ID21098
Feature activation-4.68e-01

Pos logit contributions
 brothers+0.005
 more+0.004
 friends+0.004
 promises+0.004
 chambers+0.004
Neg logit contributions
icol-0.011
tha-0.010
iya-0.010
flake-0.010
essa-0.010
Token.
Token ID13
Feature activation-4.51e-01

Pos logit contributions
 brothers+0.012
 more+0.012
 promises+0.011
 friends+0.011
 of+0.010
Neg logit contributions
tha-0.039
iya-0.039
flake-0.038
 peac-0.037
AR-0.037
Token It
Token ID632
Feature activation-4.81e-01

Pos logit contributions
 brothers+0.014
 So+0.011
mun+0.010
 promises+0.010
 of+0.010
Neg logit contributions
flake-0.038
tha-0.036
 peac-0.035
iya-0.035
storm-0.035
Token had
Token ID550
Feature activation-7.13e-01

Pos logit contributions
 brothers+0.017
mun+0.015
 chambers+0.015
 promises+0.015
 more+0.014
Neg logit contributions
tha-0.035
flake-0.035
icol-0.034
iya-0.034
essa-0.034
Token it
Token ID340
Feature activation+5.22e-01

Pos logit contributions
 more+0.034
 brothers+0.031
 promises+0.030
 friends+0.029
 y+0.029
Neg logit contributions
flake-0.046
tha-0.045
iya-0.043
ich-0.042
 peac-0.042
Token,
Token ID11
Feature activation-4.48e-01

Pos logit contributions
icol+0.039
tha+0.039
iya+0.039
flake+0.039
 peac+0.039
Neg logit contributions
 brothers-0.018
 more-0.017
 promises-0.015
 chambers-0.015
mun-0.015
Token the
Token ID262
Feature activation-6.08e-01

Pos logit contributions
 brothers+0.015
 chambers+0.012
mun+0.012
 friends+0.012
 more+0.012
Neg logit contributions
flake-0.035
tha-0.035
icol-0.034
iya-0.034
OW-0.034
Token rh
Token ID9529
Feature activation-3.73e-01

Pos logit contributions
 brothers+0.033
 friends+0.029
 more+0.028
 chambers+0.027
 promises+0.026
Neg logit contributions
tha-0.037
flake-0.037
icol-0.036
iya-0.035
enda-0.035
Tokenin
Token ID259
Feature activation+2.66e-01

Pos logit contributions
 brothers+0.014
 chambers+0.013
mun+0.012
 promises+0.012
 more+0.011
Neg logit contributions
tha-0.027
flake-0.026
icol-0.026
iya-0.025
 peac-0.025
Tokenoc
Token ID420
Feature activation-4.11e+00

Pos logit contributions
tha+0.024
icol+0.024
flake+0.024
iya+0.024
essa+0.024
Neg logit contributions
 brothers-0.005
 chambers-0.003
mun-0.003
 promises-0.003
 more-0.003
Tokeneros
Token ID27498
Feature activation-1.20e-02

Pos logit contributions
 brothers+0.275
 promises+0.254
mun+0.247
 chambers+0.244
ins+0.237
Neg logit contributions
flake-0.170
iya-0.170
icol-0.163
essa-0.162
tha-0.161
Token smiled
Token ID13541
Feature activation-2.70e-01

Pos logit contributions
 brothers+0.000
 more+0.000
mun+0.000
 friends+0.000
 chambers+0.000
Neg logit contributions
icol-0.001
tha-0.001
flake-0.001
iya-0.001
essa-0.001
Token.
Token ID13
Feature activation-3.63e-02

Pos logit contributions
 brothers+0.009
 chambers+0.008
 more+0.008
 promises+0.008
mun+0.008
Neg logit contributions
tha-0.020
flake-0.020
iya-0.019
icol-0.019
 peac-0.019
Token He
Token ID679
Feature activation-1.64e-01

Pos logit contributions
 brothers+0.001
 chambers+0.001
 So+0.001
mun+0.001
 friends+0.001
Neg logit contributions
flake-0.003
tha-0.003
 peac-0.003
iya-0.003
storm-0.003
Token had
Token ID550
Feature activation-1.69e-01

Pos logit contributions
 brothers+0.005
 more+0.004
 friends+0.004
mun+0.003
 promises+0.003
Neg logit contributions
tha-0.014
flake-0.014
AR-0.013
storm-0.013
essa-0.013
TokenI
Token ID40
Feature activation-2.07e-02

Pos logit contributions
 brothers+0.009
mun+0.009
 chambers+0.008
 promises+0.008
 more+0.008
Neg logit contributions
tha-0.013
flake-0.013
icol-0.013
iya-0.012
 peac-0.012
Token will
Token ID481
Feature activation+1.05e+00

Pos logit contributions
 brothers+0.001
mun+0.001
 promises+0.001
 chambers+0.001
 more+0.001
Neg logit contributions
tha-0.001
flake-0.001
icol-0.001
iya-0.001
 peac-0.001
Token buy
Token ID2822
Feature activation-4.76e-01

Pos logit contributions
flake+0.095
icol+0.092
la+0.091
tha+0.090
ert+0.089
Neg logit contributions
 brothers-0.025
 of-0.023
 friends-0.022
 more-0.021
 promises-0.021
Token more
Token ID517
Feature activation-1.14e+00

Pos logit contributions
 more+0.023
 brothers+0.022
 friends+0.021
 promises+0.020
 cookies+0.020
Neg logit contributions
flake-0.034
storm-0.033
icol-0.032
tha-0.032
iya-0.031
Token av
Token ID1196
Feature activation-1.42e+00

Pos logit contributions
 brothers+0.037
 chambers+0.034
mun+0.033
 promises+0.030
 more+0.028
Neg logit contributions
tha-0.085
flake-0.084
icol-0.082
 peac-0.081
iya-0.081
Tokenoc
Token ID420
Feature activation-4.11e+00

Pos logit contributions
 brothers+0.061
 chambers+0.059
 sisters+0.055
 cabinets+0.053
mun+0.053
Neg logit contributions
flake-0.087
tha-0.085
 peac-0.085
OW-0.084
icol-0.082
Tokenados
Token ID22484
Feature activation+1.78e-01

Pos logit contributions
 brothers+0.187
 chambers+0.172
mun+0.169
 promises+0.165
ins+0.154
Neg logit contributions
flake-0.265
tha-0.258
icol-0.249
iya-0.248
 peac-0.245
Token tomorrow
Token ID9439
Feature activation-7.97e-01

Pos logit contributions
tha+0.013
icol+0.013
flake+0.013
 peac+0.012
iya+0.012
Neg logit contributions
 brothers-0.006
 chambers-0.006
 more-0.006
mun-0.005
 promises-0.005
Token.
Token ID13
Feature activation-2.04e-01

Pos logit contributions
 brothers+0.028
 more+0.026
 chambers+0.025
 of+0.024
 promises+0.024
Neg logit contributions
 peac-0.060
icol-0.058
tha-0.058
flake-0.058
iya-0.055
Token You
Token ID921
Feature activation-5.98e-01

Pos logit contributions
 brothers+0.010
 chambers+0.009
mun+0.009
 promises+0.009
 more+0.009
Neg logit contributions
flake-0.012
tha-0.012
iya-0.012
icol-0.011
 peac-0.011
Token can
Token ID460
Feature activation+8.93e-01

Pos logit contributions
 brothers+0.018
 chambers+0.016
 promises+0.015
 more+0.014
mun+0.014
Neg logit contributions
icol-0.049
tha-0.048
flake-0.048
iya-0.047
essa-0.046
Token book
Token ID1492
Feature activation+1.26e-02

Pos logit contributions
flake+0.004
tha+0.003
 peac+0.003
icol+0.003
iya+0.003
Neg logit contributions
 brothers-0.002
 chambers-0.002
mun-0.002
 promises-0.002
ins-0.002
Token.
Token ID13
Feature activation-1.99e-01

Pos logit contributions
flake+0.001
tha+0.001
icol+0.001
 peac+0.001
iya+0.001
Neg logit contributions
 brothers-0.000
 chambers-0.000
mun-0.000
 promises-0.000
 goals-0.000
Token The
Token ID383
Feature activation-6.17e-02

Pos logit contributions
 brothers+0.005
 chambers+0.004
 So+0.004
mun+0.004
 promises+0.004
Neg logit contributions
tha-0.017
flake-0.016
 peac-0.016
iya-0.016
essa-0.016
Token rh
Token ID9529
Feature activation-6.84e-01

Pos logit contributions
 brothers+0.003
 chambers+0.003
mun+0.003
 more+0.003
 promises+0.003
Neg logit contributions
flake-0.003
tha-0.003
icol-0.003
iya-0.003
essa-0.003
Tokenin
Token ID259
Feature activation+3.31e-02

Pos logit contributions
 brothers+0.028
 chambers+0.027
mun+0.025
 promises+0.025
 goals+0.023
Neg logit contributions
flake-0.045
tha-0.045
 peac-0.043
iya-0.042
essa-0.041
Tokenoc
Token ID420
Feature activation-4.10e+00

Pos logit contributions
tha+0.003
flake+0.003
icol+0.003
iya+0.003
 peac+0.003
Neg logit contributions
 brothers-0.001
 chambers-0.001
mun-0.001
 promises-0.001
 more-0.001
Tokeneros
Token ID27498
Feature activation-5.26e-01

Pos logit contributions
 brothers+0.279
 promises+0.262
 chambers+0.255
mun+0.254
ins+0.246
Neg logit contributions
iya-0.160
flake-0.154
icol-0.152
tha-0.150
storm-0.148
Token was
Token ID373
Feature activation-6.37e-02

Pos logit contributions
 brothers+0.019
 chambers+0.017
mun+0.016
 promises+0.016
 more+0.016
Neg logit contributions
tha-0.039
flake-0.038
icol-0.038
iya-0.037
essa-0.037
Token mesmer
Token ID46814
Feature activation+4.07e-01

Pos logit contributions
 brothers+0.002
 more+0.002
 chambers+0.002
 friends+0.002
 promises+0.002
Neg logit contributions
flake-0.005
tha-0.005
icol-0.005
iya-0.005
essa-0.005
Tokenized
Token ID1143
Feature activation+5.94e-02

Pos logit contributions
flake+0.023
tha+0.022
icol+0.022
 peac+0.022
storm+0.021
Neg logit contributions
 brothers-0.022
 chambers-0.020
 more-0.020
 promises-0.019
mun-0.019
Token by
Token ID416
Feature activation-4.02e-01

Pos logit contributions
flake+0.004
tha+0.004
icol+0.004
 peac+0.004
iya+0.004
Neg logit contributions
 brothers-0.002
 chambers-0.002
mun-0.002
 promises-0.002
 goals-0.002
Token Unicorn
Token ID39481
Feature activation-6.22e-02

Pos logit contributions
 brothers+0.024
 friends+0.021
 promises+0.020
 more+0.020
 chambers+0.019
Neg logit contributions
flake-0.034
tha-0.032
icol-0.032
iya-0.031
essa-0.031
Token!"
Token ID2474
Feature activation+6.79e-01

Pos logit contributions
 brothers+0.004
 friends+0.003
mun+0.003
 of+0.003
 more+0.003
Neg logit contributions
icol-0.003
tha-0.003
flake-0.003
AR-0.003
iya-0.003
Token The
Token ID383
Feature activation+3.13e-01

Pos logit contributions
flake+0.057
tha+0.055
ich+0.054
icol+0.054
OW+0.053
Neg logit contributions
 brothers-0.022
 friends-0.018
 chambers-0.017
 more-0.017
mun-0.016
Token rh
Token ID9529
Feature activation-2.41e-01

Pos logit contributions
tha+0.023
flake+0.023
icol+0.023
OW+0.022
storm+0.022
Neg logit contributions
 brothers-0.013
 friends-0.012
 more-0.010
 sisters-0.010
 other-0.010
Tokenin
Token ID259
Feature activation+4.09e-01

Pos logit contributions
 brothers+0.009
 chambers+0.008
mun+0.008
 promises+0.007
 more+0.007
Neg logit contributions
tha-0.017
icol-0.017
flake-0.017
iya-0.016
 peac-0.016
Tokenoc
Token ID420
Feature activation-4.09e+00

Pos logit contributions
tha+0.035
flake+0.035
icol+0.035
iya+0.034
essa+0.034
Neg logit contributions
 brothers-0.010
mun-0.007
 chambers-0.007
 promises-0.007
 friends-0.007
Tokeneros
Token ID27498
Feature activation-7.51e-02

Pos logit contributions
 brothers+0.267
 promises+0.249
mun+0.246
ins+0.240
 chambers+0.238
Neg logit contributions
iya-0.170
icol-0.168
flake-0.166
storm-0.164
 Gina-0.164
Token said
Token ID531
Feature activation-9.49e-02

Pos logit contributions
 brothers+0.003
 chambers+0.003
mun+0.002
 promises+0.002
 more+0.002
Neg logit contributions
tha-0.005
flake-0.005
icol-0.005
iya-0.005
essa-0.005
Token,
Token ID11
Feature activation-3.43e-01

Pos logit contributions
 brothers+0.002
 more+0.002
 friends+0.002
 of+0.002
mun+0.002
Neg logit contributions
tha-0.008
icol-0.008
flake-0.008
iya-0.008
 peac-0.008
Token feeling
Token ID4203
Feature activation-5.71e-01

Pos logit contributions
 brothers+0.012
 more+0.010
mun+0.010
 friends+0.009
 promises+0.009
Neg logit contributions
tha-0.025
flake-0.025
la-0.024
iya-0.024
essa-0.024
Token much
Token ID881
Feature activation-1.91e-01

Pos logit contributions
 chambers+0.020
 brothers+0.019
mun+0.019
 promises+0.016
ins+0.016
Neg logit contributions
flake-0.038
 peac-0.037
tha-0.037
icol-0.037
iya-0.036
Token fence
Token ID13990
Feature activation-8.04e-01

Pos logit contributions
 brothers+0.019
 chambers+0.017
 more+0.017
 friends+0.016
 promises+0.015
Neg logit contributions
tha-0.027
flake-0.027
iya-0.026
icol-0.026
essa-0.026
Token where
Token ID810
Feature activation-4.15e-01

Pos logit contributions
 brothers+0.023
 more+0.022
 of+0.021
 chambers+0.021
 promises+0.019
Neg logit contributions
tha-0.065
flake-0.064
icol-0.064
iya-0.064
OW-0.062
Token the
Token ID262
Feature activation-1.89e-01

Pos logit contributions
 brothers+0.016
 chambers+0.015
mun+0.014
 promises+0.013
 more+0.013
Neg logit contributions
flake-0.030
tha-0.029
icol-0.029
iya-0.028
 peac-0.028
Token rh
Token ID9529
Feature activation-2.20e-01

Pos logit contributions
 brothers+0.010
 friends+0.008
 chambers+0.008
 more+0.008
 other+0.008
Neg logit contributions
tha-0.012
icol-0.012
flake-0.012
enda-0.011
iya-0.011
Tokenin
Token ID259
Feature activation+4.78e-01

Pos logit contributions
 brothers+0.009
 chambers+0.008
mun+0.008
 promises+0.008
 more+0.007
Neg logit contributions
flake-0.015
tha-0.015
 peac-0.014
iya-0.014
icol-0.014
Tokenoc
Token ID420
Feature activation-4.08e+00

Pos logit contributions
flake+0.039
tha+0.039
icol+0.037
 peac+0.037
iya+0.037
Neg logit contributions
 brothers-0.012
 chambers-0.011
mun-0.011
 promises-0.010
 goals-0.009
Tokeneros
Token ID27498
Feature activation+8.77e-02

Pos logit contributions
 brothers+0.277
 promises+0.252
 chambers+0.250
mun+0.247
 more+0.239
Neg logit contributions
iya-0.167
flake-0.166
icol-0.162
essa-0.161
tha-0.159
Token was
Token ID373
Feature activation+2.30e-01

Pos logit contributions
tha+0.007
flake+0.007
icol+0.006
iya+0.006
essa+0.006
Neg logit contributions
 brothers-0.003
 chambers-0.003
mun-0.003
 promises-0.002
 more-0.002
Token.
Token ID13
Feature activation+5.38e-02

Pos logit contributions
tha+0.018
icol+0.018
flake+0.018
iya+0.018
essa+0.018
Neg logit contributions
 brothers-0.008
 more-0.007
 chambers-0.007
 friends-0.006
 of-0.006
Token She
Token ID1375
Feature activation-1.35e-01

Pos logit contributions
flake+0.004
tha+0.004
 peac+0.004
iya+0.004
icol+0.004
Neg logit contributions
 brothers-0.002
 chambers-0.002
mun-0.001
 promises-0.001
 more-0.001
Token saw
Token ID2497
Feature activation+6.74e-02

Pos logit contributions
 brothers+0.004
mun+0.004
 chambers+0.004
 more+0.004
 friends+0.004
Neg logit contributions
flake-0.011
icol-0.010
tha-0.010
essa-0.010
storm-0.010
Token Did
Token ID7731
Feature activation-1.30e+00

Pos logit contributions
flake+0.018
tha+0.017
iya+0.017
essa+0.016
icol+0.016
Neg logit contributions
 brothers-0.015
 chambers-0.013
 promises-0.013
mun-0.013
 friends-0.012
Token you
Token ID345
Feature activation-2.61e-01

Pos logit contributions
 brothers+0.069
 friends+0.062
 more+0.062
 chambers+0.062
 promises+0.062
Neg logit contributions
flake-0.078
icol-0.075
tha-0.075
iya-0.071
storm-0.070
Token know
Token ID760
Feature activation-7.79e-01

Pos logit contributions
 brothers+0.007
 of+0.007
 more+0.007
 friends+0.006
 promises+0.005
Neg logit contributions
icol-0.024
tha-0.024
iya-0.022
essa-0.022
flake-0.022
Token that
Token ID326
Feature activation+1.31e-01

Pos logit contributions
 brothers+0.022
 more+0.021
 chambers+0.019
 friends+0.018
 ways+0.017
Neg logit contributions
icol-0.066
flake-0.066
tha-0.065
iya-0.064
OW-0.062
Token av
Token ID1196
Feature activation-1.39e+00

Pos logit contributions
tha+0.008
icol+0.008
flake+0.008
iya+0.008
essa+0.008
Neg logit contributions
 brothers-0.007
 more-0.006
 chambers-0.006
 friends-0.006
 promises-0.006
Tokenoc
Token ID420
Feature activation-4.07e+00

Pos logit contributions
 brothers+0.046
 chambers+0.046
mun+0.041
 promises+0.038
 questions+0.037
Neg logit contributions
flake-0.102
tha-0.098
 peac-0.098
OW-0.096
icol-0.095
Tokenados
Token ID22484
Feature activation+3.48e-01

Pos logit contributions
 brothers+0.176
mun+0.154
 chambers+0.152
 promises+0.151
ins+0.144
Neg logit contributions
flake-0.277
tha-0.270
icol-0.265
iya-0.264
 peac-0.255
Token are
Token ID389
Feature activation+4.29e-02

Pos logit contributions
icol+0.030
tha+0.029
iya+0.028
flake+0.028
 peac+0.027
Neg logit contributions
 brothers-0.010
 chambers-0.008
 of-0.008
mun-0.008
 more-0.008
Token very
Token ID845
Feature activation-1.32e-01

Pos logit contributions
icol+0.003
flake+0.003
tha+0.003
iya+0.003
essa+0.003
Neg logit contributions
 brothers-0.002
 more-0.002
 chambers-0.002
 friends-0.002
 questions-0.002
Token healthy
Token ID5448
Feature activation-5.54e-01

Pos logit contributions
 brothers+0.005
 chambers+0.004
 more+0.004
 promises+0.004
mun+0.004
Neg logit contributions
flake-0.010
tha-0.010
icol-0.010
iya-0.009
 peac-0.009
Token for
Token ID329
Feature activation-5.03e-01

Pos logit contributions
 brothers+0.023
 chambers+0.021
 more+0.020
 promises+0.019
 friends+0.019
Neg logit contributions
tha-0.039
icol-0.038
flake-0.037
 peac-0.037
iya-0.037
Token net
Token ID2010
Feature activation+1.31e+00

Pos logit contributions
icol+0.046
tha+0.045
enda+0.044
iya+0.044
essa+0.043
Neg logit contributions
 brothers-0.034
 more-0.031
 friends-0.030
 promises-0.029
 chambers-0.029
Token on
Token ID319
Feature activation-3.35e-01

Pos logit contributions
tha+0.091
flake+0.090
icol+0.088
iya+0.087
 peac+0.086
Neg logit contributions
 brothers-0.050
 chambers-0.047
mun-0.044
 promises-0.043
 more-0.042
Token the
Token ID262
Feature activation-6.98e-02

Pos logit contributions
 more+0.007
 brothers+0.006
 other+0.005
 his+0.004
 chores+0.004
Neg logit contributions
icol-0.031
storm-0.031
flake-0.031
opter-0.030
 peac-0.030
Token rh
Token ID9529
Feature activation-1.47e-01

Pos logit contributions
 brothers+0.003
 more+0.003
 chambers+0.003
 other+0.003
 friends+0.002
Neg logit contributions
tha-0.005
la-0.005
enda-0.005
iya-0.005
flake-0.005
Tokenin
Token ID259
Feature activation+3.96e-01

Pos logit contributions
 brothers+0.006
 chambers+0.006
mun+0.006
 promises+0.005
 more+0.005
Neg logit contributions
flake-0.010
tha-0.009
iya-0.009
 peac-0.009
essa-0.009
Tokenoc
Token ID420
Feature activation-4.06e+00

Pos logit contributions
flake+0.031
tha+0.030
 peac+0.029
iya+0.029
icol+0.029
Neg logit contributions
 brothers-0.012
 chambers-0.011
mun-0.011
 promises-0.010
 goals-0.009
Tokeneros
Token ID27498
Feature activation+2.24e-02

Pos logit contributions
 brothers+0.274
 promises+0.257
 chambers+0.251
mun+0.241
 goals+0.239
Neg logit contributions
flake-0.162
iya-0.159
essa-0.156
la-0.155
tha-0.154
Token.
Token ID13
Feature activation+3.33e-02

Pos logit contributions
flake+0.002
tha+0.002
 peac+0.002
iya+0.002
icol+0.001
Neg logit contributions
 brothers-0.001
mun-0.001
 chambers-0.001
 promises-0.001
ins-0.001
Token They
Token ID1119
Feature activation+3.45e-01

Pos logit contributions
flake+0.003
tha+0.003
essa+0.003
iya+0.003
 peac+0.003
Neg logit contributions
 brothers-0.001
 chambers-0.001
 promises-0.001
 So-0.001
 of-0.001
Token put
Token ID1234
Feature activation+5.50e-01

Pos logit contributions
tha+0.024
flake+0.024
icol+0.023
iya+0.023
essa+0.023
Neg logit contributions
 brothers-0.013
 chambers-0.012
mun-0.012
 promises-0.011
 more-0.011
Token the
Token ID262
Feature activation+6.10e-01

Pos logit contributions
flake+0.037
tha+0.037
icol+0.037
iya+0.037
 peac+0.036
Neg logit contributions
 brothers-0.022
 chambers-0.020
 promises-0.020
 more-0.020
mun-0.019
Token She
Token ID1375
Feature activation+1.31e-01

Pos logit contributions
tha+0.029
flake+0.029
icol+0.028
iya+0.028
 peac+0.028
Neg logit contributions
 brothers-0.015
 chambers-0.014
mun-0.013
 promises-0.013
 more-0.012
Token loved
Token ID6151
Feature activation+4.72e-01

Pos logit contributions
tha+0.012
flake+0.012
AR+0.012
icol+0.012
chie+0.012
Neg logit contributions
 brothers-0.002
 friends-0.002
mun-0.002
 more-0.001
 happy-0.001
Token to
Token ID284
Feature activation+7.87e-01

Pos logit contributions
tha+0.027
flake+0.027
icol+0.025
iya+0.025
 peac+0.025
Neg logit contributions
 brothers-0.024
 chambers-0.023
mun-0.022
 promises-0.022
 more-0.021
Token eat
Token ID4483
Feature activation-4.75e-01

Pos logit contributions
tha+0.064
flake+0.062
icol+0.060
iya+0.060
la+0.060
Neg logit contributions
 brothers-0.023
 chambers-0.021
mun-0.018
 promises-0.018
 more-0.018
Token av
Token ID1196
Feature activation-1.14e+00

Pos logit contributions
 brothers+0.018
 chambers+0.018
mun+0.016
 promises+0.016
 goals+0.015
Neg logit contributions
flake-0.030
essa-0.029
tha-0.029
iya-0.029
 peac-0.029
Tokenoc
Token ID420
Feature activation-4.04e+00

Pos logit contributions
 brothers+0.046
 chambers+0.043
mun+0.041
 sisters+0.040
 questions+0.040
Neg logit contributions
flake-0.072
 peac-0.069
icol-0.069
tha-0.068
OW-0.068
Tokenados
Token ID22484
Feature activation+4.56e-01

Pos logit contributions
 brothers+0.196
 chambers+0.187
mun+0.181
 promises+0.175
 more+0.166
Neg logit contributions
flake-0.239
tha-0.239
icol-0.227
iya-0.225
 peac-0.224
Token because
Token ID780
Feature activation-6.28e-02

Pos logit contributions
flake+0.029
tha+0.029
essa+0.027
iya+0.027
 peac+0.027
Neg logit contributions
 brothers-0.020
 chambers-0.018
mun-0.018
 promises-0.018
 goals-0.016
Token they
Token ID484
Feature activation+5.30e-01

Pos logit contributions
 brothers+0.003
 chambers+0.003
mun+0.003
 promises+0.003
 goals+0.002
Neg logit contributions
tha-0.004
flake-0.004
 peac-0.004
iya-0.004
essa-0.004
Token were
Token ID547
Feature activation+2.46e-01

Pos logit contributions
tha+0.038
flake+0.038
 peac+0.036
iya+0.036
icol+0.036
Neg logit contributions
 brothers-0.019
 chambers-0.018
mun-0.017
 promises-0.016
 goals-0.015
Token y
Token ID331
Feature activation-9.19e-01

Pos logit contributions
tha+0.015
flake+0.015
 peac+0.015
iya+0.014
essa+0.014
Neg logit contributions
 chambers-0.010
mun-0.010
 brothers-0.010
 promises-0.010
 goals-0.009
Token.
Token ID13
Feature activation-3.08e-01

Pos logit contributions
 brothers+0.002
 chambers+0.002
mun+0.002
 more+0.002
 promises+0.002
Neg logit contributions
tha-0.006
flake-0.006
icol-0.006
iya-0.006
 peac-0.006
Token<|endoftext|>
Token ID50256
Feature activation-5.75e-02

Pos logit contributions
 brothers+0.011
 chambers+0.010
mun+0.009
 promises+0.009
 more+0.008
Neg logit contributions
flake-0.023
tha-0.023
 peac-0.022
iya-0.022
icol-0.022
TokenBen
Token ID11696
Feature activation-1.44e-02

Pos logit contributions
 brothers+0.003
 chambers+0.003
 promises+0.003
mun+0.003
 questions+0.002
Neg logit contributions
flake-0.003
tha-0.003
da-0.003
iya-0.003
icol-0.003
Token and
Token ID290
Feature activation-1.89e-01

Pos logit contributions
 brothers+0.000
 chambers+0.000
 promises+0.000
mun+0.000
 more+0.000
Neg logit contributions
tha-0.001
flake-0.001
 peac-0.001
icol-0.001
iya-0.001
Token Mia
Token ID32189
Feature activation+1.09e-01

Pos logit contributions
 brothers+0.006
 chambers+0.005
 friends+0.005
 promises+0.005
mun+0.005
Neg logit contributions
flake-0.015
tha-0.014
icol-0.014
storm-0.014
 peac-0.014
Token like
Token ID588
Feature activation+1.71e+00

Pos logit contributions
flake+0.010
tha+0.010
icol+0.009
 peac+0.009
ich+0.009
Neg logit contributions
 brothers-0.002
 chambers-0.002
mun-0.002
 promises-0.002
 more-0.002
Token to
Token ID284
Feature activation+5.79e-01

Pos logit contributions
tha+0.109
flake+0.106
icol+0.103
iya+0.099
la+0.098
Neg logit contributions
 brothers-0.081
 chambers-0.075
mun-0.070
 friends-0.070
 more-0.069
Token play
Token ID711
Feature activation-3.07e-01

Pos logit contributions
tha+0.045
flake+0.045
icol+0.043
iya+0.043
 peac+0.042
Neg logit contributions
 brothers-0.018
 chambers-0.017
mun-0.015
 promises-0.015
 more-0.014
Token with
Token ID351
Feature activation+2.39e-01

Pos logit contributions
 brothers+0.014
 chambers+0.013
mun+0.013
 promises+0.012
 questions+0.011
Neg logit contributions
flake-0.019
tha-0.018
icol-0.017
 peac-0.017
iya-0.017
Token trains
Token ID13404
Feature activation+7.36e-01

Pos logit contributions
tha+0.016
flake+0.016
iya+0.015
 peac+0.015
icol+0.015
Neg logit contributions
 brothers-0.009
 chambers-0.009
mun-0.009
 promises-0.008
 goals-0.007
Token.
Token ID13
Feature activation-4.50e-01

Pos logit contributions
flake+0.053
tha+0.052
 peac+0.051
icol+0.050
iya+0.050
Neg logit contributions
 brothers-0.024
 chambers-0.024
mun-0.022
 promises-0.022
 goals-0.019
Token rough
Token ID5210
Feature activation+4.60e-01

Pos logit contributions
tha+0.009
la+0.008
iya+0.008
icol+0.008
essa+0.008
Neg logit contributions
 brothers-0.004
 more-0.004
 friends-0.003
 chambers-0.003
 y-0.003
Token paper
Token ID3348
Feature activation+7.06e-01

Pos logit contributions
tha+0.037
la+0.035
iya+0.034
nes+0.032
icol+0.032
Neg logit contributions
 brothers-0.016
 more-0.015
 toys-0.014
 books-0.014
 chambers-0.013
Token and
Token ID290
Feature activation-1.08e-01

Pos logit contributions
tha+0.055
iya+0.053
icol+0.053
OW+0.053
flake+0.052
Neg logit contributions
 brothers-0.024
 chambers-0.022
 more-0.020
 friends-0.019
 promises-0.019
Token some
Token ID617
Feature activation-7.96e-02

Pos logit contributions
 brothers+0.005
 chambers+0.004
mun+0.004
 promises+0.004
 more+0.004
Neg logit contributions
tha-0.007
flake-0.007
icol-0.007
 peac-0.007
iya-0.007
Token cr
Token ID1067
Feature activation+1.48e-01

Pos logit contributions
 brothers+0.004
mun+0.003
 chambers+0.003
 promises+0.003
ins+0.003
Neg logit contributions
flake-0.005
tha-0.005
 peac-0.005
icol-0.005
iya-0.004
Tokenay
Token ID323
Feature activation+1.62e+00

Pos logit contributions
tha+0.009
flake+0.008
iya+0.008
 peac+0.008
icol+0.008
Neg logit contributions
 brothers-0.008
 chambers-0.007
 of-0.007
ins-0.006
 more-0.006
Tokenons
Token ID684
Feature activation+6.74e-01

Pos logit contributions
tha+0.122
flake+0.122
icol+0.118
iya+0.117
 peac+0.116
Neg logit contributions
 brothers-0.052
 chambers-0.049
mun-0.046
 promises-0.044
 more-0.041
Token.
Token ID13
Feature activation-2.48e-01

Pos logit contributions
tha+0.055
flake+0.054
icol+0.054
iya+0.053
 peac+0.052
Neg logit contributions
 brothers-0.019
 chambers-0.016
 more-0.015
 promises-0.015
mun-0.015
Token They
Token ID1119
Feature activation-9.08e-02

Pos logit contributions
 brothers+0.010
 chambers+0.010
mun+0.010
 promises+0.009
 more+0.009
Neg logit contributions
tha-0.016
flake-0.016
icol-0.016
iya-0.015
essa-0.015
Token sit
Token ID1650
Feature activation-1.16e+00

Pos logit contributions
 brothers+0.004
 chambers+0.004
mun+0.004
 promises+0.003
 more+0.003
Neg logit contributions
tha-0.006
flake-0.006
icol-0.006
iya-0.006
 peac-0.006
Token on
Token ID319
Feature activation-6.04e-01

Pos logit contributions
mun+0.050
 chambers+0.049
 brothers+0.048
 goals+0.044
 promises+0.044
Neg logit contributions
tha-0.078
flake-0.077
ich-0.071
iya-0.068
la-0.067
Token ride
Token ID6594
Feature activation+5.93e-02

Pos logit contributions
 brothers+0.005
 chambers+0.005
mun+0.004
 promises+0.004
ins+0.004
Neg logit contributions
flake-0.006
tha-0.006
 peac-0.006
icol-0.006
iya-0.006
Token the
Token ID262
Feature activation+5.56e-01

Pos logit contributions
flake+0.004
tha+0.004
icol+0.004
iya+0.004
 peac+0.004
Neg logit contributions
 brothers-0.002
 chambers-0.002
mun-0.002
 promises-0.002
ins-0.001
Token waves
Token ID9813
Feature activation+1.53e+00

Pos logit contributions
enda+0.045
tha+0.045
icol+0.042
flake+0.041
essa+0.041
Neg logit contributions
 brothers-0.020
 other-0.018
 friends-0.017
 more-0.016
 y-0.015
Token on
Token ID319
Feature activation-3.45e-01

Pos logit contributions
tha+0.129
flake+0.126
icol+0.125
iya+0.123
 peac+0.121
Neg logit contributions
 brothers-0.040
 chambers-0.033
 more-0.032
mun-0.032
 of-0.029
Token his
Token ID465
Feature activation-3.46e-01

Pos logit contributions
 brothers+0.012
 chambers+0.011
mun+0.011
 promises+0.010
 more+0.009
Neg logit contributions
tha-0.025
flake-0.025
icol-0.024
iya-0.024
 peac-0.024
Token surf
Token ID9053
Feature activation+1.57e+00

Pos logit contributions
 brothers+0.017
 chambers+0.015
 friends+0.015
 promises+0.014
 more+0.014
Neg logit contributions
flake-0.022
tha-0.021
icol-0.020
 peac-0.020
storm-0.020
Tokenboard
Token ID3526
Feature activation+9.60e-02

Pos logit contributions
tha+0.116
flake+0.114
icol+0.111
iya+0.110
 peac+0.109
Neg logit contributions
 brothers-0.055
 chambers-0.051
mun-0.049
 promises-0.046
 more-0.044
Token.
Token ID13
Feature activation-2.61e-01

Pos logit contributions
tha+0.007
flake+0.007
icol+0.007
iya+0.007
 peac+0.007
Neg logit contributions
 brothers-0.003
 chambers-0.003
mun-0.003
 promises-0.002
 more-0.002
Token One
Token ID1881
Feature activation+6.38e-02

Pos logit contributions
 chambers+0.012
 brothers+0.011
mun+0.011
 promises+0.011
ins+0.010
Neg logit contributions
flake-0.015
tha-0.015
icol-0.015
storm-0.014
 peac-0.014
Token day
Token ID1110
Feature activation-6.56e-01

Pos logit contributions
flake+0.003
tha+0.003
iya+0.003
 peac+0.003
bye+0.003
Neg logit contributions
 chambers-0.004
mun-0.004
ins-0.004
 promises-0.004
 brothers-0.004
Token,
Token ID11
Feature activation+1.04e-01

Pos logit contributions
 chambers+0.038
 brothers+0.037
 promises+0.037
mun+0.035
 goals+0.034
Neg logit contributions
tha-0.031
flake-0.030
icol-0.030
 peac-0.029
storm-0.028
Token some
Token ID617
Feature activation-5.22e-01

Pos logit contributions
flake+0.045
tha+0.045
iya+0.044
icol+0.043
storm+0.043
Neg logit contributions
 brothers-0.014
 more-0.014
 chambers-0.012
 promises-0.012
 friends-0.011
Token ac
Token ID936
Feature activation+3.48e-01

Pos logit contributions
 brothers+0.019
 chambers+0.018
mun+0.017
 promises+0.016
 goals+0.015
Neg logit contributions
flake-0.035
tha-0.035
 peac-0.035
icol-0.034
iya-0.033
Tokenorns
Token ID19942
Feature activation-1.73e-01

Pos logit contributions
flake+0.023
tha+0.023
 peac+0.022
icol+0.022
iya+0.021
Neg logit contributions
 brothers-0.014
 chambers-0.014
 promises-0.012
mun-0.012
 goals-0.012
Token and
Token ID290
Feature activation-1.71e-01

Pos logit contributions
 brothers+0.006
 more+0.006
 chambers+0.005
mun+0.005
 promises+0.005
Neg logit contributions
icol-0.013
tha-0.013
flake-0.012
iya-0.012
 peac-0.012
Token took
Token ID1718
Feature activation+3.66e-01

Pos logit contributions
 brothers+0.007
 chambers+0.007
mun+0.006
 promises+0.006
 goals+0.006
Neg logit contributions
tha-0.011
flake-0.011
icol-0.011
 peac-0.011
iya-0.011
Token them
Token ID606
Feature activation+1.48e+00

Pos logit contributions
flake+0.025
tha+0.025
ich+0.024
iya+0.023
storm+0.023
Neg logit contributions
 brothers-0.016
 more-0.015
 friends-0.014
 promises-0.014
 chambers-0.014
Token to
Token ID284
Feature activation-6.42e-02

Pos logit contributions
tha+0.092
flake+0.090
icol+0.090
iya+0.088
 peac+0.087
Neg logit contributions
 brothers-0.069
 chambers-0.066
 more-0.066
 promises-0.065
 friends-0.063
Token his
Token ID465
Feature activation-5.99e-01

Pos logit contributions
 brothers+0.002
 more+0.002
 chambers+0.002
 promises+0.002
 friends+0.002
Neg logit contributions
flake-0.005
tha-0.005
icol-0.005
iya-0.005
la-0.005
Token friends
Token ID2460
Feature activation+5.10e-02

Pos logit contributions
mun+0.028
 brothers+0.027
 chambers+0.026
ins+0.026
 promises+0.024
Neg logit contributions
tha-0.035
flake-0.034
icol-0.033
 peac-0.033
iya-0.033
Token.
Token ID13
Feature activation+5.95e-02

Pos logit contributions
tha+0.004
flake+0.004
icol+0.004
 peac+0.004
iya+0.004
Neg logit contributions
 brothers-0.002
 chambers-0.001
mun-0.001
 promises-0.001
 more-0.001
Token They
Token ID1119
Feature activation-1.35e-01

Pos logit contributions
tha+0.004
flake+0.004
icol+0.004
 peac+0.004
iya+0.004
Neg logit contributions
 brothers-0.002
 chambers-0.002
mun-0.002
 promises-0.002
 more-0.002
Token.
Token ID13
Feature activation+2.47e-02

Pos logit contributions
flake+0.082
tha+0.081
iya+0.078
 peac+0.078
icol+0.078
Neg logit contributions
 brothers-0.037
 chambers-0.035
mun-0.034
 promises-0.031
 goals-0.029
Token He
Token ID679
Feature activation+1.29e-01

Pos logit contributions
flake+0.001
icol+0.001
tha+0.001
storm+0.001
OW+0.001
Neg logit contributions
mun-0.001
 promises-0.001
 brothers-0.001
 chambers-0.001
ins-0.001
Token loved
Token ID6151
Feature activation+5.17e-01

Pos logit contributions
tha+0.010
flake+0.009
icol+0.009
iya+0.009
essa+0.009
Neg logit contributions
 brothers-0.005
 chambers-0.004
mun-0.004
 more-0.004
 promises-0.004
Token holding
Token ID4769
Feature activation-9.74e-02

Pos logit contributions
tha+0.026
flake+0.026
icol+0.025
 peac+0.025
iya+0.025
Neg logit contributions
 brothers-0.029
 chambers-0.028
mun-0.027
 promises-0.026
 goals-0.025
Token his
Token ID465
Feature activation+3.50e-01

Pos logit contributions
 chambers+0.003
mun+0.003
 brothers+0.003
 promises+0.002
 goals+0.002
Neg logit contributions
tha-0.007
flake-0.007
icol-0.007
iya-0.007
essa-0.007
Token treasure
Token ID14068
Feature activation+1.57e+00

Pos logit contributions
tha+0.025
flake+0.025
icol+0.024
iya+0.023
 peac+0.023
Neg logit contributions
 brothers-0.014
 chambers-0.012
 promises-0.012
mun-0.012
 friends-0.011
Token.
Token ID13
Feature activation+4.71e-02

Pos logit contributions
flake+0.098
tha+0.097
icol+0.092
 peac+0.092
essa+0.090
Neg logit contributions
 brothers-0.069
mun-0.069
 chambers-0.064
 promises-0.060
ins-0.059
Token One
Token ID1881
Feature activation+3.02e-01

Pos logit contributions
flake+0.003
tha+0.003
icol+0.003
iya+0.003
 peac+0.003
Neg logit contributions
 brothers-0.002
 chambers-0.002
mun-0.002
 promises-0.002
ins-0.002
Token day
Token ID1110
Feature activation-3.65e-01

Pos logit contributions
flake+0.015
tha+0.014
 peac+0.014
iya+0.014
storm+0.013
Neg logit contributions
 chambers-0.018
mun-0.018
ins-0.017
 brothers-0.017
 goals-0.017
Token,
Token ID11
Feature activation+3.50e-01

Pos logit contributions
 chambers+0.021
mun+0.021
 promises+0.021
 brothers+0.020
ins+0.020
Neg logit contributions
tha-0.016
icol-0.016
flake-0.016
OW-0.015
essa-0.015
Token while
Token ID981
Feature activation-7.49e-02

Pos logit contributions
tha+0.019
flake+0.019
icol+0.018
essa+0.018
 peac+0.017
Neg logit contributions
 chambers-0.018
mun-0.017
 brothers-0.017
 promises-0.016
ins-0.016
Token purple
Token ID14032
Feature activation+2.47e-01

Pos logit contributions
tha+0.046
la+0.045
OW+0.044
chie+0.043
flake+0.043
Neg logit contributions
 friends-0.020
 more-0.020
 cookies-0.018
 brothers-0.018
 toys-0.017
Token balloon
Token ID21190
Feature activation+4.40e-01

Pos logit contributions
tha+0.019
OW+0.017
la+0.017
enda+0.017
iya+0.017
Neg logit contributions
 more-0.008
 brothers-0.008
 friends-0.008
 chambers-0.008
 of-0.008
Token.
Token ID13
Feature activation-2.68e-03

Pos logit contributions
tha+0.034
icol+0.033
flake+0.033
iya+0.033
OW+0.033
Neg logit contributions
 brothers-0.013
 chambers-0.012
 more-0.012
 of-0.011
mun-0.011
Token
Token ID220
Feature activation-5.01e-01

Pos logit contributions
 brothers+0.000
 chambers+0.000
mun+0.000
 of+0.000
 friends+0.000
Neg logit contributions
flake-0.000
tha-0.000
iya-0.000
 peac-0.000
storm-0.000
Token
Token ID198
Feature activation+7.04e-02

Pos logit contributions
 brothers+0.021
 chambers+0.020
mun+0.019
 promises+0.018
 more+0.017
Neg logit contributions
tha-0.033
flake-0.033
iya-0.031
icol-0.031
essa-0.030
Token
Token ID198
Feature activation+2.89e-01

Pos logit contributions
tha+0.006
flake+0.006
icol+0.006
 peac+0.006
storm+0.006
Neg logit contributions
 brothers-0.002
 chambers-0.002
mun-0.002
 of-0.002
 more-0.001
TokenAs
Token ID1722
Feature activation+5.22e-01

Pos logit contributions
flake+0.020
tha+0.020
icol+0.019
iya+0.019
 peac+0.019
Neg logit contributions
 brothers-0.011
 chambers-0.011
mun-0.010
 more-0.010
 of-0.010
Token Sus
Token ID8932
Feature activation+1.10e+00

Pos logit contributions
flake+0.044
AR+0.041
icol+0.041
OW+0.040
rus+0.040
Neg logit contributions
 brothers-0.015
 more-0.015
 of-0.014
 friends-0.014
 chambers-0.012
Tokenie
Token ID494
Feature activation+8.81e-01

Pos logit contributions
tha+0.067
flake+0.067
iya+0.063
icol+0.063
 peac+0.062
Neg logit contributions
 brothers-0.051
 chambers-0.049
mun-0.047
 promises-0.045
 goals-0.044
Token and
Token ID290
Feature activation+4.38e-01

Pos logit contributions
tha+0.059
flake+0.057
iya+0.056
icol+0.055
la+0.054
Neg logit contributions
 brothers-0.035
 chambers-0.034
 goals-0.031
mun-0.030
 questions-0.030
Token her
Token ID607
Feature activation+4.02e-01

Pos logit contributions
tha+0.034
flake+0.034
icol+0.032
 peac+0.032
iya+0.032
Neg logit contributions
 brothers-0.014
 chambers-0.013
mun-0.012
 promises-0.011
 more-0.010
Token to
Token ID284
Feature activation-8.64e-01

Pos logit contributions
 brothers+0.020
 more+0.020
 promises+0.019
 friends+0.018
 chambers+0.018
Neg logit contributions
icol-0.033
tha-0.032
flake-0.032
iya-0.031
 peac-0.031
Token get
Token ID651
Feature activation-6.74e-01

Pos logit contributions
 more+0.027
 promises+0.025
 brothers+0.025
 friends+0.023
 chores+0.023
Neg logit contributions
flake-0.069
icol-0.068
la-0.068
tha-0.067
iya-0.066
Token better
Token ID1365
Feature activation+2.87e-01

Pos logit contributions
 more+0.030
 brothers+0.028
 promises+0.027
 friends+0.027
 of+0.025
Neg logit contributions
flake-0.049
icol-0.048
iya-0.048
tha-0.047
storm-0.047
Token."
Token ID526
Feature activation+4.03e-01

Pos logit contributions
tha+0.018
flake+0.017
icol+0.017
enda+0.017
 peac+0.017
Neg logit contributions
 more-0.014
 brothers-0.014
 promises-0.013
 friends-0.013
 chambers-0.013
Token Mia
Token ID32189
Feature activation-7.97e-01

Pos logit contributions
tha+0.025
flake+0.025
icol+0.024
iya+0.024
da+0.024
Neg logit contributions
 brothers-0.017
 chambers-0.016
mun-0.016
 promises-0.015
 chores-0.015
Token picked
Token ID6497
Feature activation-8.98e-01

Pos logit contributions
 brothers+0.028
 chambers+0.026
mun+0.025
 promises+0.024
 more+0.023
Neg logit contributions
tha-0.058
flake-0.058
icol-0.056
 peac-0.055
iya-0.055
Token up
Token ID510
Feature activation-1.51e+00

Pos logit contributions
 chambers+0.047
 brothers+0.046
mun+0.044
 goals+0.040
 promises+0.040
Neg logit contributions
tha-0.050
flake-0.049
icol-0.046
essa-0.046
iya-0.046
Token the
Token ID262
Feature activation-2.76e-01

Pos logit contributions
 chambers+0.077
 brothers+0.074
mun+0.074
ins+0.068
 goals+0.065
Neg logit contributions
tha-0.086
flake-0.082
 peac-0.079
iya-0.078
essa-0.076
Token arrow
Token ID15452
Feature activation+1.30e-02

Pos logit contributions
 brothers+0.018
 chambers+0.017
 promises+0.016
mun+0.016
 more+0.016
Neg logit contributions
tha-0.012
flake-0.012
icol-0.012
iya-0.012
essa-0.011
Token and
Token ID290
Feature activation-6.35e-01

Pos logit contributions
flake+0.001
tha+0.001
 peac+0.001
iya+0.001
icol+0.001
Neg logit contributions
 brothers-0.001
 chambers-0.001
mun-0.001
ins-0.001
 promises-0.001
Token put
Token ID1234
Feature activation+6.05e-01

Pos logit contributions
 brothers+0.027
 chambers+0.026
mun+0.025
 promises+0.024
 goals+0.023
Neg logit contributions
tha-0.041
flake-0.041
icol-0.039
iya-0.039
 peac-0.038
Token He
Token ID679
Feature activation+6.90e-02

Pos logit contributions
mun+0.006
ins+0.006
 promises+0.006
 brothers+0.005
 chambers+0.005
Neg logit contributions
flake-0.009
icol-0.009
tha-0.009
storm-0.009
 peac-0.009
Token was
Token ID373
Feature activation+3.57e-01

Pos logit contributions
tha+0.005
flake+0.005
icol+0.005
iya+0.005
 peac+0.005
Neg logit contributions
 brothers-0.003
 chambers-0.002
mun-0.002
 more-0.002
 promises-0.002
Token big
Token ID1263
Feature activation+5.64e-01

Pos logit contributions
tha+0.021
 peac+0.021
flake+0.020
ich+0.019
iya+0.019
Neg logit contributions
 chambers-0.016
mun-0.016
ins-0.015
 brothers-0.015
 promises-0.015
Token and
Token ID290
Feature activation+1.98e-01

Pos logit contributions
tha+0.032
flake+0.032
icol+0.031
 peac+0.031
iya+0.030
Neg logit contributions
 chambers-0.026
mun-0.026
 brothers-0.025
 promises-0.023
ins-0.023
Token strong
Token ID1913
Feature activation+5.03e-01

Pos logit contributions
tha+0.011
flake+0.011
 peac+0.010
storm+0.010
da+0.010
Neg logit contributions
mun-0.010
 chambers-0.010
ins-0.010
 promises-0.009
 ways-0.009
Token!
Token ID0
Feature activation+4.67e-01

Pos logit contributions
flake+0.032
tha+0.031
icol+0.031
 peac+0.031
essa+0.030
Neg logit contributions
mun-0.020
 chambers-0.019
 brothers-0.018
 promises-0.018
ins-0.017
Token He
Token ID679
Feature activation-1.81e-02

Pos logit contributions
flake+0.030
tha+0.030
icol+0.029
iya+0.029
 peac+0.029
Neg logit contributions
mun-0.017
 brothers-0.017
 promises-0.016
 chambers-0.016
ins-0.016
Token was
Token ID373
Feature activation+2.04e-01

Pos logit contributions
 brothers+0.001
 chambers+0.000
mun+0.000
 more+0.000
 friends+0.000
Neg logit contributions
tha-0.001
flake-0.001
icol-0.001
iya-0.001
essa-0.001
Token wearing
Token ID5762
Feature activation-5.63e-01

Pos logit contributions
tha+0.013
flake+0.013
 peac+0.013
iya+0.013
icol+0.013
Neg logit contributions
 chambers-0.008
 brothers-0.008
mun-0.008
 promises-0.007
 goals-0.007
Token an
Token ID281
Feature activation-1.49e-01

Pos logit contributions
 brothers+0.023
mun+0.023
 chambers+0.022
 promises+0.021
ins+0.020
Neg logit contributions
flake-0.036
tha-0.036
icol-0.035
 peac-0.035
iya-0.034
Token orange
Token ID10912
Feature activation-1.72e-01

Pos logit contributions
 brothers+0.006
 chambers+0.006
mun+0.006
 promises+0.006
 more+0.005
Neg logit contributions
flake-0.010
tha-0.010
icol-0.009
iya-0.009
 peac-0.009
Tokenase
Token ID589
Feature activation+1.64e-01

Pos logit contributions
tha+0.017
iya+0.016
icol+0.016
 Gab+0.016
 Gina+0.016
Neg logit contributions
 brothers-0.011
 of-0.010
ins-0.009
 chambers-0.009
mun-0.009
Token!"
Token ID2474
Feature activation+3.32e-01

Pos logit contributions
iya+0.008
icol+0.007
tha+0.007
essa+0.007
flake+0.007
Neg logit contributions
 of-0.011
 brothers-0.010
 more-0.010
 chambers-0.010
 friends-0.010
Token Anna
Token ID11735
Feature activation-1.22e-01

Pos logit contributions
tha+0.018
iya+0.018
essa+0.017
flake+0.017
la+0.017
Neg logit contributions
 brothers-0.016
 chambers-0.016
mun-0.015
 promises-0.014
ins-0.014
Token says
Token ID1139
Feature activation-2.40e-01

Pos logit contributions
 brothers+0.005
 chambers+0.005
mun+0.005
 promises+0.005
 chores+0.004
Neg logit contributions
tha-0.008
flake-0.008
iya-0.007
essa-0.007
icol-0.007
Token.
Token ID13
Feature activation-4.13e-01

Pos logit contributions
 chambers+0.011
mun+0.011
 brothers+0.011
 promises+0.010
 goals+0.009
Neg logit contributions
tha-0.015
flake-0.014
essa-0.014
work-0.013
icol-0.013
Token "
Token ID366
Feature activation-1.23e-01

Pos logit contributions
 brothers+0.016
 chambers+0.016
mun+0.015
 promises+0.014
 more+0.013
Neg logit contributions
tha-0.028
flake-0.028
icol-0.027
iya-0.027
essa-0.026
TokenCan
Token ID6090
Feature activation+3.44e-01

Pos logit contributions
 brothers+0.005
 chambers+0.005
 more+0.005
mun+0.005
 goals+0.005
Neg logit contributions
tha-0.008
icol-0.008
iya-0.007
flake-0.007
essa-0.007
Token we
Token ID356
Feature activation-5.17e-01

Pos logit contributions
icol+0.023
flake+0.022
iya+0.022
essa+0.022
tha+0.021
Neg logit contributions
 more-0.016
 brothers-0.016
 of-0.015
 friends-0.015
 chambers-0.014
Token play
Token ID711
Feature activation-1.11e+00

Pos logit contributions
 brothers+0.013
 of+0.013
 more+0.012
 friends+0.012
 chambers+0.011
Neg logit contributions
icol-0.044
flake-0.042
tha-0.042
essa-0.041
iya-0.041
Token with
Token ID351
Feature activation-3.98e-01

Pos logit contributions
 more+0.034
 brothers+0.032
 chambers+0.028
 friends+0.028
 of+0.026
Neg logit contributions
tha-0.095
iya-0.092
icol-0.091
essa-0.089
la-0.087
Token it
Token ID340
Feature activation+6.72e-01

Pos logit contributions
 more+0.016
 other+0.012
 friends+0.012
 things+0.012
 of+0.012
Neg logit contributions
icol-0.037
storm-0.034
flake-0.033
ote-0.032
sed-0.032
Token?"
Token ID1701
Feature activation+1.28e+00

Pos logit contributions
tha+0.025
flake+0.025
icol+0.024
 peac+0.024
AR+0.024
Neg logit contributions
 brothers-0.009
 promises-0.008
 chambers-0.008
 more-0.008
 friends-0.008
Token
Token ID198
Feature activation-3.25e-01

Pos logit contributions
flake+0.101
tha+0.098
icol+0.097
 peac+0.094
storm+0.092
Neg logit contributions
 brothers-0.044
mun-0.038
 chambers-0.036
 friends-0.035
 promises-0.035
Token
Token ID198
Feature activation-3.59e-02

Pos logit contributions
 brothers+0.010
 chambers+0.009
mun+0.009
 promises+0.008
 friends+0.008
Neg logit contributions
flake-0.025
tha-0.025
icol-0.024
 peac-0.024
storm-0.024
TokenThe
Token ID464
Feature activation+1.01e+00

Pos logit contributions
 brothers+0.001
 chambers+0.001
mun+0.001
 promises+0.001
 friends+0.001
Neg logit contributions
flake-0.002
tha-0.002
icol-0.002
 peac-0.002
storm-0.002
Token tree
Token ID5509
Feature activation-3.31e-01

Pos logit contributions
tha+0.070
flake+0.069
icol+0.068
iya+0.066
OW+0.065
Neg logit contributions
 brothers-0.042
 chambers-0.037
mun-0.035
 more-0.035
 friends-0.035
Token smiled
Token ID13541
Feature activation-3.11e-02

Pos logit contributions
 brothers+0.013
 chambers+0.012
mun+0.011
 promises+0.011
 more+0.011
Neg logit contributions
tha-0.023
icol-0.023
flake-0.023
iya-0.023
essa-0.022
Token and
Token ID290
Feature activation-3.91e-01

Pos logit contributions
 brothers+0.001
 chambers+0.001
 more+0.001
 promises+0.001
 friends+0.001
Neg logit contributions
tha-0.002
flake-0.002
iya-0.002
 peac-0.002
icol-0.002
Token said
Token ID531
Feature activation+7.31e-01

Pos logit contributions
 brothers+0.012
 more+0.011
 friends+0.010
 promises+0.010
mun+0.010
Neg logit contributions
flake-0.030
tha-0.030
AR-0.030
ich-0.029
iya-0.029
Token kindly
Token ID26820
Feature activation+3.16e-01

Pos logit contributions
tha+0.062
iya+0.061
flake+0.060
icol+0.060
ich+0.060
Neg logit contributions
 more-0.018
 of-0.017
 brothers-0.017
 friends-0.015
es-0.014
Token,
Token ID11
Feature activation-1.48e-01

Pos logit contributions
tha+0.026
flake+0.025
 peac+0.025
icol+0.025
iya+0.025
Neg logit contributions
 brothers-0.009
 chambers-0.007
 more-0.007
 questions-0.007
 promises-0.007
Token
Token ID198
Feature activation+3.86e-02

Pos logit contributions
 brothers+0.003
 more+0.002
 happy+0.002
 sleepy+0.002
 questions+0.002
Neg logit contributions
flake-0.013
tha-0.012
opter-0.012
iya-0.012
OW-0.012
Token a
Token ID257
Feature activation-1.48e-01

Pos logit contributions
 brothers+0.004
 more+0.004
 chambers+0.003
mun+0.003
 promises+0.003
Neg logit contributions
flake-0.010
tha-0.010
icol-0.010
iya-0.009
storm-0.009
Token sign
Token ID1051
Feature activation-1.67e-01

Pos logit contributions
 brothers+0.004
 more+0.004
 friends+0.004
 chambers+0.004
mun+0.004
Neg logit contributions
tha-0.012
flake-0.011
icol-0.011
essa-0.011
iya-0.011
Token that
Token ID326
Feature activation+1.49e-01

Pos logit contributions
 brothers+0.006
 more+0.006
 of+0.006
 chambers+0.005
 friends+0.005
Neg logit contributions
tha-0.012
flake-0.012
icol-0.012
iya-0.012
OW-0.012
Token said
Token ID531
Feature activation+1.91e-01

Pos logit contributions
icol+0.012
flake+0.012
iya+0.012
tha+0.012
OW+0.011
Neg logit contributions
 brothers-0.004
 chambers-0.004
 more-0.004
mun-0.004
 friends-0.004
Token "
Token ID366
Feature activation-2.36e-01

Pos logit contributions
icol+0.016
flake+0.015
iya+0.015
tha+0.015
OW+0.015
Neg logit contributions
 brothers-0.005
 of-0.005
 more-0.005
 questions-0.005
 friends-0.005
TokenSafety
Token ID45372
Feature activation-1.06e+00

Pos logit contributions
mun+0.009
 brothers+0.009
 of+0.009
 more+0.009
ins+0.008
Neg logit contributions
icol-0.016
tha-0.016
flake-0.014
iya-0.014
sed-0.014
Token First
Token ID3274
Feature activation-1.27e+00

Pos logit contributions
 brothers+0.051
 questions+0.050
 of+0.049
 more+0.046
 chores+0.045
Neg logit contributions
icol-0.071
 peac-0.062
iya-0.059
flake-0.058
storm-0.056
Token".
Token ID1911
Feature activation+9.34e-02

Pos logit contributions
 brothers+0.046
 of+0.043
 friends+0.039
 more+0.039
 ways+0.039
Neg logit contributions
icol-0.101
 peac-0.098
flake-0.095
AR-0.091
tha-0.088
Token Lily
Token ID20037
Feature activation-1.20e+00

Pos logit contributions
flake+0.006
tha+0.006
icol+0.006
essa+0.005
 peac+0.005
Neg logit contributions
 brothers-0.004
 chambers-0.004
mun-0.004
 promises-0.004
 goals-0.003
Token remembered
Token ID12086
Feature activation-6.69e-01

Pos logit contributions
 brothers+0.044
 chambers+0.040
mun+0.039
 promises+0.038
 more+0.035
Neg logit contributions
flake-0.086
tha-0.085
icol-0.083
 peac-0.082
iya-0.081
Token what
Token ID644
Feature activation-5.45e-01

Pos logit contributions
 more+0.019
 brothers+0.018
 questions+0.017
 friends+0.017
 promises+0.017
Neg logit contributions
flake-0.056
icol-0.055
tha-0.053
storm-0.053
OW-0.052
Token will
Token ID481
Feature activation+1.02e+00

Pos logit contributions
 brothers+0.004
 chambers+0.004
 promises+0.003
 friends+0.003
mun+0.003
Neg logit contributions
icol-0.015
tha-0.015
flake-0.014
ich-0.014
iya-0.014
Token have
Token ID423
Feature activation-5.23e-01

Pos logit contributions
icol+0.089
rus+0.087
flake+0.086
tha+0.085
ich+0.084
Neg logit contributions
 friends-0.027
 brothers-0.026
 more-0.026
 chores-0.023
 promises-0.021
Token dessert
Token ID23084
Feature activation-1.54e-01

Pos logit contributions
 more+0.018
 friends+0.014
 brothers+0.014
 cookies+0.013
 y+0.013
Neg logit contributions
flake-0.047
tha-0.046
icol-0.045
storm-0.044
AR-0.044
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
 brothers+0.006
 chambers+0.006
 more+0.006
 promises+0.006
 friends+0.005
Neg logit contributions
tha-0.010
icol-0.010
flake-0.010
 peac-0.010
iya-0.010
Token How
Token ID1374
Feature activation-3.46e-01

Pos logit contributions
 brothers+0.007
 chambers+0.007
mun+0.007
 promises+0.006
 more+0.006
Neg logit contributions
tha-0.008
flake-0.008
icol-0.008
iya-0.008
 peac-0.008
Token does
Token ID857
Feature activation-1.40e+00

Pos logit contributions
 brothers+0.012
mun+0.012
 chambers+0.011
 promises+0.011
ins+0.010
Neg logit contributions
flake-0.024
tha-0.024
iya-0.023
essa-0.023
 peac-0.023
Token that
Token ID326
Feature activation-7.95e-01

Pos logit contributions
 brothers+0.068
 more+0.067
 chores+0.063
 chambers+0.062
 of+0.061
Neg logit contributions
flake-0.088
icol-0.087
tha-0.084
OW-0.081
ert-0.079
Token sound
Token ID2128
Feature activation-7.10e-01

Pos logit contributions
 more+0.034
 brothers+0.033
 of+0.029
 friends+0.029
 promises+0.029
Neg logit contributions
icol-0.054
tha-0.054
flake-0.051
iya-0.051
la-0.050
Token?"
Token ID1701
Feature activation+7.02e-01

Pos logit contributions
 brothers+0.039
 more+0.037
 chambers+0.036
 of+0.035
 questions+0.035
Neg logit contributions
icol-0.040
tha-0.040
flake-0.038
iya-0.038
 peac-0.037
Token
Token ID198
Feature activation-8.49e-01

Pos logit contributions
tha+0.050
flake+0.050
icol+0.048
iya+0.048
 peac+0.048
Neg logit contributions
 brothers-0.026
 chambers-0.024
mun-0.023
 promises-0.022
 more-0.021
Token
Token ID198
Feature activation-4.71e-01

Pos logit contributions
 brothers+0.030
 chambers+0.028
mun+0.026
 promises+0.025
 more+0.024
Neg logit contributions
tha-0.062
flake-0.062
icol-0.060
 peac-0.059
iya-0.059
Token Everything
Token ID11391
Feature activation-6.03e-01

Pos logit contributions
 brothers+0.003
 chambers+0.003
 promises+0.003
mun+0.003
 more+0.002
Neg logit contributions
flake-0.003
tha-0.003
iya-0.003
icol-0.003
 peac-0.003
Token is
Token ID318
Feature activation+1.52e-01

Pos logit contributions
 more+0.018
 promises+0.017
 brothers+0.016
 chambers+0.016
 goals+0.015
Neg logit contributions
icol-0.049
iya-0.049
tha-0.049
 peac-0.048
essa-0.048
Token going
Token ID1016
Feature activation-7.20e-01

Pos logit contributions
iya+0.012
flake+0.012
icol+0.012
tha+0.012
essa+0.012
Neg logit contributions
 more-0.005
 brothers-0.005
 friends-0.004
 promises-0.004
 y-0.004
Token to
Token ID284
Feature activation-1.54e-01

Pos logit contributions
 more+0.023
 too+0.017
 questions+0.017
 brothers+0.017
 of+0.016
Neg logit contributions
iya-0.064
flake-0.063
icol-0.062
tha-0.062
essa-0.061
Token be
Token ID307
Feature activation-6.12e-01

Pos logit contributions
 more+0.006
 chores+0.005
 other+0.005
 brothers+0.005
 friends+0.004
Neg logit contributions
icol-0.013
la-0.012
tha-0.012
flake-0.012
iya-0.012
Token okay
Token ID8788
Feature activation-1.37e+00

Pos logit contributions
 more+0.021
 brothers+0.020
 friends+0.017
 promises+0.016
 chambers+0.016
Neg logit contributions
flake-0.051
tha-0.050
iya-0.050
icol-0.049
essa-0.049
Token."
Token ID526
Feature activation+3.55e-01

Pos logit contributions
 brothers+0.058
 of+0.053
 friends+0.053
 more+0.053
 chambers+0.049
Neg logit contributions
icol-0.109
tha-0.099
 peac-0.098
iya-0.096
flake-0.096
Token
Token ID220
Feature activation-1.38e+00

Pos logit contributions
flake+0.030
tha+0.029
 peac+0.029
icol+0.028
storm+0.028
Neg logit contributions
 brothers-0.010
mun-0.008
 chambers-0.008
 promises-0.008
 more-0.007
Token
Token ID198
Feature activation-5.51e-01

Pos logit contributions
 brothers+0.040
mun+0.031
 chambers+0.031
 promises+0.030
 friends+0.029
Neg logit contributions
flake-0.114
tha-0.112
 peac-0.112
icol-0.112
storm-0.109
Token
Token ID198
Feature activation-1.75e-01

Pos logit contributions
 brothers+0.011
mun+0.008
 friends+0.008
 more+0.007
 of+0.007
Neg logit contributions
icol-0.051
flake-0.051
storm-0.051
tha-0.051
 peac-0.049
TokenThe
Token ID464
Feature activation+4.63e-01

Pos logit contributions
 brothers+0.007
mun+0.006
 chambers+0.006
 more+0.006
 promises+0.006
Neg logit contributions
tha-0.012
flake-0.012
icol-0.012
storm-0.012
iya-0.012
Token "
Token ID366
Feature activation-1.04e-01

Pos logit contributions
 brothers+0.002
 more+0.001
 of+0.001
 questions+0.001
 friends+0.001
Neg logit contributions
tha-0.008
iya-0.008
flake-0.008
icol-0.008
AR-0.007
TokenI
Token ID40
Feature activation-2.67e-01

Pos logit contributions
mun+0.003
 brothers+0.003
 more+0.003
ins+0.003
 of+0.003
Neg logit contributions
tha-0.008
icol-0.007
sed-0.007
flake-0.007
iya-0.007
Token'm
Token ID1101
Feature activation+7.47e-01

Pos logit contributions
 brothers+0.009
 promises+0.008
 more+0.008
mun+0.008
 of+0.008
Neg logit contributions
tha-0.021
ich-0.020
icol-0.020
flake-0.019
iya-0.019
Token here
Token ID994
Feature activation+5.48e-01

Pos logit contributions
flake+0.066
icol+0.060
storm+0.060
tha+0.059
iya+0.058
Neg logit contributions
 brothers-0.024
 more-0.020
 friends-0.019
 sleepy-0.018
 of-0.018
Token to
Token ID284
Feature activation-3.80e-01

Pos logit contributions
flake+0.044
icol+0.044
tha+0.044
storm+0.043
iya+0.043
Neg logit contributions
 more-0.019
 of-0.019
 brothers-0.018
 friends-0.017
 questions-0.015
Token talk
Token ID1561
Feature activation-1.03e+00

Pos logit contributions
 brothers+0.010
 more+0.009
 friends+0.009
 of+0.009
 promises+0.008
Neg logit contributions
tha-0.033
flake-0.032
la-0.032
ich-0.032
icol-0.031
Token to
Token ID284
Feature activation-2.19e-01

Pos logit contributions
 more+0.038
 of+0.036
 questions+0.032
 brothers+0.030
 friends+0.028
Neg logit contributions
tha-0.090
icol-0.084
iya-0.083
flake-0.082
ich-0.081
Token you
Token ID345
Feature activation-2.20e-01

Pos logit contributions
 more+0.009
 brothers+0.009
 friends+0.009
 of+0.008
 questions+0.008
Neg logit contributions
icol-0.016
flake-0.016
tha-0.015
storm-0.015
ANG-0.015
Token about
Token ID546
Feature activation-8.08e-01

Pos logit contributions
 brothers+0.009
 more+0.008
 friends+0.008
 of+0.007
 chambers+0.007
Neg logit contributions
icol-0.017
tha-0.017
flake-0.016
iya-0.015
 peac-0.015
Token taking
Token ID2263
Feature activation-5.27e-01

Pos logit contributions
 brothers+0.033
 more+0.031
 friends+0.030
 promises+0.028
 ways+0.028
Neg logit contributions
tha-0.058
icol-0.057
flake-0.057
iya-0.056
 peac-0.055
Token a
Token ID257
Feature activation-5.51e-02

Pos logit contributions
 more+0.018
 brothers+0.018
 friends+0.017
 promises+0.017
 questions+0.016
Neg logit contributions
tha-0.044
flake-0.043
ich-0.041
storm-0.041
 peac-0.040
Token learning
Token ID4673
Feature activation+3.20e-01

Pos logit contributions
tha+0.018
flake+0.018
 peac+0.017
icol+0.017
iya+0.017
Neg logit contributions
 brothers-0.014
 chambers-0.014
mun-0.013
 promises-0.013
 goals-0.012
Token new
Token ID649
Feature activation+2.38e-01

Pos logit contributions
tha+0.021
flake+0.021
 peac+0.021
essa+0.021
icol+0.021
Neg logit contributions
 brothers-0.012
mun-0.011
 chambers-0.010
 promises-0.010
ins-0.009
Token things
Token ID1243
Feature activation+1.00e+00

Pos logit contributions
icol+0.017
 peac+0.017
flake+0.017
tha+0.017
essa+0.017
Neg logit contributions
 brothers-0.007
mun-0.007
 chambers-0.006
 promises-0.006
hes-0.005
Token.
Token ID13
Feature activation-4.46e-02

Pos logit contributions
flake+0.074
tha+0.074
icol+0.071
 peac+0.071
iya+0.071
Neg logit contributions
 brothers-0.033
 chambers-0.030
mun-0.029
 promises-0.027
 goals-0.024
Token One
Token ID1881
Feature activation+3.13e-01

Pos logit contributions
 brothers+0.001
 chambers+0.001
mun+0.001
 promises+0.001
 more+0.001
Neg logit contributions
flake-0.003
tha-0.003
icol-0.003
 peac-0.003
iya-0.003
Token sunny
Token ID27737
Feature activation-1.15e+00

Pos logit contributions
tha+0.020
flake+0.020
iya+0.019
 peac+0.019
icol+0.019
Neg logit contributions
 brothers-0.013
 chambers-0.013
mun-0.012
 promises-0.012
 goals-0.011
Token day
Token ID1110
Feature activation-3.83e-01

Pos logit contributions
 brothers+0.042
 chambers+0.039
mun+0.037
 promises+0.035
 more+0.034
Neg logit contributions
tha-0.083
flake-0.083
icol-0.080
iya-0.079
 peac-0.079
Token,
Token ID11
Feature activation+2.39e-01

Pos logit contributions
 brothers+0.012
 of+0.011
 more+0.011
 chambers+0.011
 friends+0.011
Neg logit contributions
flake-0.031
tha-0.030
icol-0.029
iya-0.028
ich-0.028
Token she
Token ID673
Feature activation-2.74e-01

Pos logit contributions
flake+0.016
tha+0.016
icol+0.015
iya+0.015
storm+0.015
Neg logit contributions
 brothers-0.010
 chambers-0.009
 more-0.009
 friends-0.009
mun-0.009
Token was
Token ID373
Feature activation+3.01e-01

Pos logit contributions
 brothers+0.008
 chambers+0.008
 friends+0.007
mun+0.007
 of+0.007
Neg logit contributions
tha-0.022
flake-0.022
icol-0.021
AR-0.021
ich-0.021
Token playing
Token ID2712
Feature activation-5.95e-01

Pos logit contributions
flake+0.024
tha+0.024
icol+0.023
 peac+0.023
iya+0.023
Neg logit contributions
 brothers-0.010
 chambers-0.008
 more-0.008
 friends-0.008
mun-0.008
Tokeneros
Token ID27498
Feature activation+2.39e-01

Pos logit contributions
 brothers+0.267
 chambers+0.249
mun+0.239
 friends+0.238
 promises+0.235
Neg logit contributions
flake-0.162
iya-0.156
tha-0.154
icol-0.153
essa-0.152
Token.
Token ID13
Feature activation+4.23e-01

Pos logit contributions
tha+0.019
icol+0.018
flake+0.018
iya+0.018
essa+0.018
Neg logit contributions
 brothers-0.008
 chambers-0.007
mun-0.007
 more-0.006
 friends-0.006
Token The
Token ID383
Feature activation+3.80e-01

Pos logit contributions
flake+0.033
tha+0.033
icol+0.031
iya+0.031
essa+0.031
Neg logit contributions
 brothers-0.015
 chambers-0.013
 of-0.011
mun-0.011
 friends-0.010
Token rh
Token ID9529
Feature activation-1.97e-01

Pos logit contributions
icol+0.022
flake+0.022
tha+0.021
iya+0.020
enda+0.020
Neg logit contributions
 brothers-0.022
 friends-0.020
 chambers-0.019
 more-0.019
 promises-0.018
Tokenin
Token ID259
Feature activation+4.11e-01

Pos logit contributions
 brothers+0.007
 chambers+0.007
mun+0.007
 promises+0.006
 more+0.006
Neg logit contributions
tha-0.014
flake-0.014
icol-0.013
iya-0.013
 peac-0.013
Tokenoc
Token ID420
Feature activation-4.03e+00

Pos logit contributions
tha+0.037
icol+0.037
flake+0.037
essa+0.036
iya+0.036
Neg logit contributions
 brothers-0.008
 chambers-0.006
mun-0.006
 promises-0.005
 friends-0.004
Tokeneros
Token ID27498
Feature activation-3.89e-03

Pos logit contributions
 brothers+0.272
 chambers+0.250
mun+0.246
 promises+0.243
 friends+0.240
Neg logit contributions
flake-0.166
iya-0.165
icol-0.163
tha-0.159
essa-0.159
Token was
Token ID373
Feature activation+1.42e-01

Pos logit contributions
 brothers+0.000
 chambers+0.000
mun+0.000
 friends+0.000
 more+0.000
Neg logit contributions
icol-0.000
tha-0.000
flake-0.000
iya-0.000
essa-0.000
Token very
Token ID845
Feature activation+4.09e-01

Pos logit contributions
flake+0.012
icol+0.012
tha+0.012
iya+0.011
essa+0.011
Neg logit contributions
 brothers-0.004
 more-0.003
 friends-0.003
 chambers-0.003
 promises-0.003
Token big
Token ID1263
Feature activation+6.42e-01

Pos logit contributions
flake+0.034
tha+0.033
icol+0.033
iya+0.032
essa+0.032
Neg logit contributions
 brothers-0.011
 chambers-0.010
mun-0.009
 promises-0.009
 more-0.008
Token and
Token ID290
Feature activation+1.77e-01

Pos logit contributions
flake+0.039
tha+0.038
icol+0.037
 peac+0.037
iya+0.036
Neg logit contributions
 brothers-0.028
mun-0.027
 chambers-0.027
 promises-0.025
ins-0.024
Token
Token ID198
Feature activation-7.60e-01

Pos logit contributions
 brothers+0.044
 chambers+0.037
mun+0.037
 promises+0.035
 friends+0.033
Neg logit contributions
flake-0.111
tha-0.110
icol-0.109
 peac-0.108
iya-0.106
Token
Token ID198
Feature activation-3.91e-01

Pos logit contributions
 brothers+0.017
mun+0.014
 of+0.012
 more+0.012
 friends+0.012
Neg logit contributions
tha-0.068
icol-0.067
flake-0.066
storm-0.066
 peac-0.065
TokenThe
Token ID464
Feature activation+3.23e-01

Pos logit contributions
 brothers+0.016
mun+0.015
 chambers+0.015
 more+0.014
 promises+0.014
Neg logit contributions
tha-0.027
flake-0.027
icol-0.026
essa-0.025
iya-0.025
Token rh
Token ID9529
Feature activation-3.13e-01

Pos logit contributions
tha+0.019
flake+0.018
icol+0.018
iya+0.018
essa+0.017
Neg logit contributions
 brothers-0.017
 chambers-0.016
mun-0.015
 promises-0.015
 more-0.014
Tokenin
Token ID259
Feature activation+3.42e-01

Pos logit contributions
 brothers+0.012
 chambers+0.012
mun+0.011
 promises+0.011
 more+0.010
Neg logit contributions
flake-0.021
tha-0.021
 peac-0.020
icol-0.020
iya-0.020
Tokenoc
Token ID420
Feature activation-3.53e+00

Pos logit contributions
tha+0.029
flake+0.028
icol+0.028
iya+0.027
 peac+0.027
Neg logit contributions
 brothers-0.008
 chambers-0.007
mun-0.007
 promises-0.006
 more-0.006
Tokeneros
Token ID27498
Feature activation-3.51e-01

Pos logit contributions
 brothers+0.240
 promises+0.224
mun+0.218
 chambers+0.217
 friends+0.211
Neg logit contributions
iya-0.141
icol-0.139
la-0.134
tha-0.132
flake-0.132
Token couldn
Token ID3521
Feature activation-4.17e-01

Pos logit contributions
 brothers+0.012
 more+0.010
 chambers+0.010
mun+0.010
 promises+0.010
Neg logit contributions
tha-0.027
icol-0.027
flake-0.026
iya-0.026
essa-0.026
Token't
Token ID470
Feature activation+1.34e-01

Pos logit contributions
 brothers+0.029
mun+0.027
 chambers+0.027
 more+0.027
 promises+0.027
Neg logit contributions
tha-0.016
icol-0.016
flake-0.015
 peac-0.015
iya-0.015
Token believe
Token ID1975
Feature activation+1.97e-01

Pos logit contributions
icol+0.009
tha+0.009
ich+0.009
flake+0.009
la+0.008
Neg logit contributions
 more-0.005
 brothers-0.005
 chambers-0.005
 of-0.005
 questions-0.005
Token his
Token ID465
Feature activation-1.88e-01

Pos logit contributions
flake+0.014
tha+0.014
icol+0.014
iya+0.014
 peac+0.014
Neg logit contributions
 brothers-0.007
 chambers-0.006
 promises-0.006
 more-0.006
mun-0.006
Token She
Token ID1375
Feature activation+1.31e-01

Pos logit contributions
tha+0.029
flake+0.029
icol+0.028
iya+0.028
 peac+0.028
Neg logit contributions
 brothers-0.015
 chambers-0.014
mun-0.013
 promises-0.013
 more-0.012
Token loved
Token ID6151
Feature activation+4.72e-01

Pos logit contributions
tha+0.012
flake+0.012
AR+0.012
icol+0.012
chie+0.012
Neg logit contributions
 brothers-0.002
 friends-0.002
mun-0.002
 more-0.001
 happy-0.001
Token to
Token ID284
Feature activation+7.87e-01

Pos logit contributions
tha+0.027
flake+0.027
icol+0.025
iya+0.025
 peac+0.025
Neg logit contributions
 brothers-0.024
 chambers-0.023
mun-0.022
 promises-0.022
 more-0.021
Token eat
Token ID4483
Feature activation-4.75e-01

Pos logit contributions
tha+0.064
flake+0.062
icol+0.060
iya+0.060
la+0.060
Neg logit contributions
 brothers-0.023
 chambers-0.021
mun-0.018
 promises-0.018
 more-0.018
Token av
Token ID1196
Feature activation-1.14e+00

Pos logit contributions
 brothers+0.018
 chambers+0.018
mun+0.016
 promises+0.016
 goals+0.015
Neg logit contributions
flake-0.030
essa-0.029
tha-0.029
iya-0.029
 peac-0.029
Tokenoc
Token ID420
Feature activation-4.04e+00

Pos logit contributions
 brothers+0.046
 chambers+0.043
mun+0.041
 sisters+0.040
 questions+0.040
Neg logit contributions
flake-0.072
 peac-0.069
icol-0.069
tha-0.068
OW-0.068
Tokenados
Token ID22484
Feature activation+4.56e-01

Pos logit contributions
 brothers+0.196
 chambers+0.187
mun+0.181
 promises+0.175
 more+0.166
Neg logit contributions
flake-0.239
tha-0.239
icol-0.227
iya-0.225
 peac-0.224
Token because
Token ID780
Feature activation-6.28e-02

Pos logit contributions
flake+0.029
tha+0.029
essa+0.027
iya+0.027
 peac+0.027
Neg logit contributions
 brothers-0.020
 chambers-0.018
mun-0.018
 promises-0.018
 goals-0.016
Token they
Token ID484
Feature activation+5.30e-01

Pos logit contributions
 brothers+0.003
 chambers+0.003
mun+0.003
 promises+0.003
 goals+0.002
Neg logit contributions
tha-0.004
flake-0.004
 peac-0.004
iya-0.004
essa-0.004
Token were
Token ID547
Feature activation+2.46e-01

Pos logit contributions
tha+0.038
flake+0.038
 peac+0.036
iya+0.036
icol+0.036
Neg logit contributions
 brothers-0.019
 chambers-0.018
mun-0.017
 promises-0.016
 goals-0.015
Token y
Token ID331
Feature activation-9.19e-01

Pos logit contributions
tha+0.015
flake+0.015
 peac+0.015
iya+0.014
essa+0.014
Neg logit contributions
 chambers-0.010
mun-0.010
 brothers-0.010
 promises-0.010
 goals-0.009
Token net
Token ID2010
Feature activation+1.31e+00

Pos logit contributions
icol+0.046
tha+0.045
enda+0.044
iya+0.044
essa+0.043
Neg logit contributions
 brothers-0.034
 more-0.031
 friends-0.030
 promises-0.029
 chambers-0.029
Token on
Token ID319
Feature activation-3.35e-01

Pos logit contributions
tha+0.091
flake+0.090
icol+0.088
iya+0.087
 peac+0.086
Neg logit contributions
 brothers-0.050
 chambers-0.047
mun-0.044
 promises-0.043
 more-0.042
Token the
Token ID262
Feature activation-6.98e-02

Pos logit contributions
 more+0.007
 brothers+0.006
 other+0.005
 his+0.004
 chores+0.004
Neg logit contributions
icol-0.031
storm-0.031
flake-0.031
opter-0.030
 peac-0.030
Token rh
Token ID9529
Feature activation-1.47e-01

Pos logit contributions
 brothers+0.003
 more+0.003
 chambers+0.003
 other+0.003
 friends+0.002
Neg logit contributions
tha-0.005
la-0.005
enda-0.005
iya-0.005
flake-0.005
Tokenin
Token ID259
Feature activation+3.96e-01

Pos logit contributions
 brothers+0.006
 chambers+0.006
mun+0.006
 promises+0.005
 more+0.005
Neg logit contributions
flake-0.010
tha-0.009
iya-0.009
 peac-0.009
essa-0.009
Tokenoc
Token ID420
Feature activation-4.06e+00

Pos logit contributions
flake+0.031
tha+0.030
 peac+0.029
iya+0.029
icol+0.029
Neg logit contributions
 brothers-0.012
 chambers-0.011
mun-0.011
 promises-0.010
 goals-0.009
Tokeneros
Token ID27498
Feature activation+2.24e-02

Pos logit contributions
 brothers+0.274
 promises+0.257
 chambers+0.251
mun+0.241
 goals+0.239
Neg logit contributions
flake-0.162
iya-0.159
essa-0.156
la-0.155
tha-0.154
Token.
Token ID13
Feature activation+3.33e-02

Pos logit contributions
flake+0.002
tha+0.002
 peac+0.002
iya+0.002
icol+0.001
Neg logit contributions
 brothers-0.001
mun-0.001
 chambers-0.001
 promises-0.001
ins-0.001
Token They
Token ID1119
Feature activation+3.45e-01

Pos logit contributions
flake+0.003
tha+0.003
essa+0.003
iya+0.003
 peac+0.003
Neg logit contributions
 brothers-0.001
 chambers-0.001
 promises-0.001
 So-0.001
 of-0.001
Token put
Token ID1234
Feature activation+5.50e-01

Pos logit contributions
tha+0.024
flake+0.024
icol+0.023
iya+0.023
essa+0.023
Neg logit contributions
 brothers-0.013
 chambers-0.012
mun-0.012
 promises-0.011
 more-0.011
Token the
Token ID262
Feature activation+6.10e-01

Pos logit contributions
flake+0.037
tha+0.037
icol+0.037
iya+0.037
 peac+0.036
Neg logit contributions
 brothers-0.022
 chambers-0.020
 promises-0.020
 more-0.020
mun-0.019
Token shaking
Token ID17275
Feature activation-1.12e+00

Pos logit contributions
 more+0.009
 brothers+0.008
 friends+0.007
 of+0.007
 ways+0.007
Neg logit contributions
tha-0.017
iya-0.017
flake-0.017
essa-0.017
 peac-0.016
Token.
Token ID13
Feature activation-9.45e-02

Pos logit contributions
 more+0.029
 brothers+0.026
 of+0.023
 ways+0.021
 goals+0.020
Neg logit contributions
tha-0.097
iya-0.097
flake-0.094
ich-0.093
essa-0.093
Token Mom
Token ID11254
Feature activation-1.27e+00

Pos logit contributions
 brothers+0.003
 chambers+0.002
mun+0.002
 promises+0.002
 more+0.002
Neg logit contributions
flake-0.008
tha-0.008
 peac-0.008
iya-0.007
ich-0.007
Token watched
Token ID7342
Feature activation-7.76e-01

Pos logit contributions
 brothers+0.045
mun+0.037
 more+0.035
 of+0.035
 friends+0.034
Neg logit contributions
icol-0.096
flake-0.094
tha-0.094
essa-0.093
iya-0.093
Token in
Token ID287
Feature activation-4.55e-01

Pos logit contributions
 of+0.022
 more+0.022
 brothers+0.022
 promises+0.018
 questions+0.018
Neg logit contributions
flake-0.063
 peac-0.061
tha-0.060
ich-0.060
iya-0.060
Token amaz
Token ID40642
Feature activation-3.44e+00

Pos logit contributions
 brothers+0.017
 chambers+0.016
mun+0.015
 promises+0.014
 more+0.013
Neg logit contributions
tha-0.032
flake-0.032
icol-0.031
iya-0.031
 peac-0.031
Tokenement
Token ID972
Feature activation-1.50e+00

Pos logit contributions
 brothers+0.122
 chambers+0.115
mun+0.108
 promises+0.106
 more+0.105
Neg logit contributions
flake-0.251
tha-0.244
 peac-0.241
icol-0.237
iya-0.234
Token from
Token ID422
Feature activation-1.14e+00

Pos logit contributions
 brothers+0.042
 more+0.038
 of+0.036
 friends+0.036
 chambers+0.034
Neg logit contributions
flake-0.122
tha-0.119
 peac-0.117
icol-0.116
iya-0.115
Token a
Token ID257
Feature activation-8.82e-01

Pos logit contributions
 more+0.029
 brothers+0.025
 ways+0.024
 promises+0.023
 chambers+0.022
Neg logit contributions
flake-0.099
opter-0.095
iya-0.095
enda-0.095
 peac-0.094
Token distance
Token ID5253
Feature activation-8.29e-01

Pos logit contributions
 brothers+0.034
 more+0.033
 chambers+0.031
mun+0.030
 promises+0.029
Neg logit contributions
tha-0.061
flake-0.061
essa-0.059
icol-0.058
iya-0.058
Token,
Token ID11
Feature activation-2.13e-01

Pos logit contributions
 more+0.024
 of+0.023
 brothers+0.021
 ways+0.020
 friends+0.019
Neg logit contributions
flake-0.070
icol-0.066
AR-0.066
 peac-0.065
tha-0.065