TOP ACTIVATIONS
MAX = 0.138

A ww , okay . â
!" " A ww !" Lily says . "
. " A ww , it is so cute
the ground . " E ww , what 's that ?"
and said , " E ww , Bruno . You are
be bitter , like e ww . Do you want to
at it said " ew ww !" One
and said , " A ww www , do I have
. " E ww !" she screamed .
She said , " E ww , disgusting !" She threw
. " E ww , this fish is sm
friends said , " A ww , okay . But come
s okay sweet heart . How about I give
He says , " A ww , this is from Anna
He said , " E ww , this is the worst
s wonderful , sweet heart ! Keep spring ing around
s wrong sweet heart ? â The little
wait in line , sweet heart . â She then
Yes , sweet heart , it â
No , sweet heart . That dress is too

MIN ACTIVATIONS
MIN = -0.155

Sally told him , Wh isk ers always wanted to help
on the cards . Wh isk ers was hesitant at first
a naughty cat named Wh isk ers . Wh isk ers
flew down and scared Wh isk ers away .
a smart cat named Wh isk ers . Wh isk ers
j olly cat named Wh isk ers . Wh isk ers
was a cat named Wh isk ers . Wh isk ers
that day on , Wh isk ers was no longer a
everyone 's surprise , Wh isk ers turned out to be
After Mr . Wh isk ers was done with his
a lazy cat named Wh isk ers . Wh isk ers
dream , she saw Wh isk ers walking and talking like
Wh isk ers . Wh isk ers loved to play with
, fat cat named Wh isk ers . Wh isk ers
that day on , Wh isk ers was no longer lazy
got back inside , Wh isk ers saw a teaspoon on
, Lucy !" said Wh isk ers , " Do you
From then on , Wh isk ers tried to be less
a long time . Wh isk ers learned that sometimes it
, fluffy cat named Wh isk ers , who liked to

INTERVAL 0.064 - 0.138
CONTAINS 0.053%

looks very nice , sweet heart ," she said .
says . " No , Sara ! This is
find it ?" The all igator said , " Yes ,
Then , a kind mail man came by . The mail
Andy 's picture ! Andy looked at the freshly printed

INTERVAL -0.009 - 0.064
CONTAINS 78.533%

believe it . He took the ring from Anna and looked
are successful . You are mean ." Max cannot
I wish I had some juice . â Tim thought
. You are making me happy . And you are making
for the fun ," Sam says . They hug

INTERVAL -0.082 - -0.009
CONTAINS 21.402%

will teach you some songs ." She lifts Anna and puts
girl named Av a . She was only three years old
. She looked at the mark on her knee and smiled
was going to meet a prince . She put on her
that she had a clean plate and a full tum my

INTERVAL -0.155 - -0.082
CONTAINS 0.012%

can hug and make grow l grow l sounds ," Lily
a bad tum my ac he and felt very sick .
Spot found Wh isk ers and said , "
book falls off the books he lf . It makes a
strange happened . The books he lf became restless . It
Token
Token ID95
Feature activation+2.73e-02

Pos logit contributions
ww+0.018
www+0.016
heart+0.014
?"+0.014
mber+0.014
Neg logit contributions
 bank-0.015
 banks-0.014
 allowance-0.013
isc-0.012
ro-0.012
Token
Token ID26391
Feature activation-2.92e-02

Pos logit contributions
ww+0.052
www+0.045
heart+0.041
ons+0.041
mber+0.040
Neg logit contributions
 bank-0.043
 banks-0.041
 allowance-0.038
ro-0.035
isc-0.035
Token
Token ID129
Feature activation-1.51e-02

Pos logit contributions
 bank+0.043
 banks+0.041
 allowance+0.039
isc+0.037
ro+0.036
Neg logit contributions
ww-0.055
www-0.048
heart-0.047
igator-0.045
loo-0.044
Token
Token ID241
Feature activation+2.58e-03

Pos logit contributions
 bank+0.024
 allowance+0.023
 banks+0.022
 usual+0.020
isc+0.019
Neg logit contributions
ww-0.028
www-0.026
?"-0.022
heart-0.022
mber-0.022
TokenA
Token ID32
Feature activation-2.32e-02

Pos logit contributions
ww+0.004
www+0.004
ons+0.003
heart+0.003
loo+0.003
Neg logit contributions
 bank-0.005
 banks-0.004
 allowance-0.004
ro-0.004
isc-0.004
Tokenww
Token ID1383
Feature activation+1.38e-01

Pos logit contributions
 bank+0.035
 banks+0.031
 allowance+0.030
ro+0.028
ork+0.028
Neg logit contributions
ww-0.041
ons-0.038
heart-0.036
www-0.035
loo-0.035
Token,
Token ID11
Feature activation+1.06e-02

Pos logit contributions
ww+0.259
ull+0.255
loo+0.243
igator+0.236
www+0.229
Neg logit contributions
 bank-0.167
 banks-0.157
 allowance-0.154
ro-0.138
isc-0.137
Token okay
Token ID8788
Feature activation-9.97e-03

Pos logit contributions
ww+0.018
www+0.016
ons+0.016
loo+0.015
heart+0.014
Neg logit contributions
 bank-0.017
 allowance-0.016
 banks-0.016
ro-0.015
isc-0.014
Token.
Token ID13
Feature activation-5.01e-03

Pos logit contributions
 anymore+0.017
 bank+0.017
ro+0.016
 yet+0.016
 allowance+0.016
Neg logit contributions
ons-0.013
ww-0.013
 course-0.011
loo-0.011
orn-0.011
Tokenâ
Token ID22940
Feature activation+3.70e-02

Pos logit contributions
 bank+0.008
 banks+0.008
 allowance+0.008
isc+0.007
ro+0.007
Neg logit contributions
ww-0.009
www-0.008
ons-0.007
heart-0.007
loo-0.007
Token
Token ID26391
Feature activation-3.06e-02

Pos logit contributions
ww+0.077
www+0.066
ons+0.065
heart+0.064
ins+0.063
Neg logit contributions
 bank-0.049
 banks-0.046
ro-0.040
 allowance-0.039
 symp-0.037
Token!"
Token ID2474
Feature activation+9.99e-03

Pos logit contributions
ww+0.019
www+0.017
mber+0.017
heart+0.017
very+0.016
Neg logit contributions
 bank-0.016
 find-0.015
 banks-0.014
ro-0.014
 anymore-0.014
Token
Token ID198
Feature activation+5.84e-03

Pos logit contributions
ww+0.024
www+0.021
heart+0.020
ons+0.019
loo+0.019
Neg logit contributions
 bank-0.012
 banks-0.011
 allowance-0.010
ro-0.010
 symp-0.009
Token
Token ID198
Feature activation+6.57e-03

Pos logit contributions
ww+0.014
www+0.012
heart+0.011
mber+0.011
ons+0.011
Neg logit contributions
 bank-0.007
 banks-0.006
 allowance-0.006
ro-0.005
 symp-0.005
Token"
Token ID1
Feature activation+4.57e-03

Pos logit contributions
ww+0.011
www+0.009
heart+0.009
ons+0.008
loo+0.008
Neg logit contributions
 bank-0.012
 banks-0.012
ro-0.011
 allowance-0.010
tted-0.010
TokenA
Token ID32
Feature activation-1.66e-02

Pos logit contributions
ww+0.008
www+0.007
heart+0.007
ons+0.007
loo+0.007
Neg logit contributions
 bank-0.007
 banks-0.007
ro-0.007
 allowance-0.006
 symp-0.006
Tokenww
Token ID1383
Feature activation+1.35e-01

Pos logit contributions
 bank+0.017
ro+0.015
 allowance+0.014
 banks+0.014
 long+0.014
Neg logit contributions
ons-0.035
ries-0.035
ins-0.032
loo-0.032
ions-0.031
Token!"
Token ID2474
Feature activation+1.24e-02

Pos logit contributions
ww+0.290
ull+0.288
igator+0.280
Charlie+0.275
John+0.275
Neg logit contributions
 bank-0.120
 banks-0.108
 allowance-0.102
isc-0.095
ro-0.091
Token Lily
Token ID20037
Feature activation+1.14e-02

Pos logit contributions
ww+0.024
www+0.021
heart+0.020
ons+0.019
loo+0.019
Neg logit contributions
 bank-0.019
 banks-0.018
 allowance-0.018
ro-0.016
 symp-0.015
Token says
Token ID1139
Feature activation+2.97e-03

Pos logit contributions
ww+0.019
www+0.016
loo+0.015
heart+0.014
ons+0.013
Neg logit contributions
 bank-0.022
 banks-0.022
 allowance-0.019
ro-0.019
 symp-0.018
Token.
Token ID13
Feature activation+5.00e-03

Pos logit contributions
ww+0.005
?"+0.004
www+0.004
?+0.004
heart+0.004
Neg logit contributions
 bank-0.005
 banks-0.005
 allowance-0.005
isc-0.004
uries-0.004
Token "
Token ID366
Feature activation-1.41e-02

Pos logit contributions
ww+0.010
www+0.009
heart+0.009
ons+0.008
mber+0.008
Neg logit contributions
 bank-0.007
 banks-0.007
 allowance-0.006
ro-0.006
 symp-0.006
Token.
Token ID13
Feature activation-2.34e-03

Pos logit contributions
ww+0.018
www+0.017
mber+0.016
heart+0.016
very+0.016
Neg logit contributions
 bank-0.007
 banks-0.006
ro-0.005
 allowance-0.005
 until-0.004
Token
Token ID198
Feature activation-5.14e-04

Pos logit contributions
 bank+0.003
 banks+0.002
 allowance+0.002
ro+0.002
isc+0.002
Neg logit contributions
ww-0.005
www-0.005
heart-0.005
ons-0.004
loo-0.004
Token
Token ID198
Feature activation+1.52e-04

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
ro+0.001
isc+0.001
Neg logit contributions
ww-0.001
www-0.001
heart-0.001
ons-0.001
mber-0.001
Token"
Token ID1
Feature activation-1.35e-03

Pos logit contributions
ww+0.000
heart+0.000
www+0.000
loo+0.000
mber+0.000
Neg logit contributions
 banks-0.000
 bank-0.000
 allowance-0.000
ro-0.000
side-0.000
TokenA
Token ID32
Feature activation-2.22e-02

Pos logit contributions
 bank+0.002
 banks+0.002
 allowance+0.002
ro+0.002
 symp+0.002
Neg logit contributions
ww-0.002
heart-0.002
www-0.002
ons-0.002
loo-0.002
Tokenww
Token ID1383
Feature activation+1.30e-01

Pos logit contributions
 bank+0.024
 banks+0.020
 allowance+0.020
ro+0.019
 long+0.019
Neg logit contributions
ons-0.045
ries-0.044
loo-0.043
ins-0.042
ined-0.041
Token,
Token ID11
Feature activation+6.42e-03

Pos logit contributions
ww+0.287
igator+0.278
ull+0.278
mber+0.275
www+0.273
Neg logit contributions
 bank-0.108
 banks-0.100
 allowance-0.090
isc-0.082
ro-0.080
Token it
Token ID340
Feature activation+4.65e-03

Pos logit contributions
ww+0.013
www+0.011
heart+0.011
ons+0.011
ins+0.010
Neg logit contributions
 bank-0.009
 allowance-0.008
 banks-0.008
 seem-0.007
 symp-0.007
Token is
Token ID318
Feature activation+1.82e-02

Pos logit contributions
ww+0.008
www+0.008
heart+0.007
mber+0.007
very+0.007
Neg logit contributions
 bank-0.008
 banks-0.007
 allowance-0.006
 seem-0.006
ro-0.006
Token so
Token ID523
Feature activation+6.09e-03

Pos logit contributions
ww+0.038
www+0.035
heart+0.034
loo+0.032
mber+0.032
Neg logit contributions
 bank-0.025
 banks-0.024
 allowance-0.022
 usual-0.020
isc-0.019
Token cute
Token ID13779
Feature activation+6.86e-03

Pos logit contributions
heart+0.014
ww+0.013
ons+0.013
www+0.013
 course+0.012
Neg logit contributions
 bank-0.006
 banks-0.005
 allowance-0.005
 usual-0.005
ro-0.005
Token the
Token ID262
Feature activation+1.29e-02

Pos logit contributions
ww+0.012
www+0.010
heart+0.009
ons+0.009
mber+0.009
Neg logit contributions
 bank-0.009
 banks-0.009
 allowance-0.009
ro-0.008
isc-0.008
Token ground
Token ID2323
Feature activation-5.10e-03

Pos logit contributions
ww+0.022
www+0.019
 onion+0.017
?"+0.017
 my+0.017
Neg logit contributions
 allowance-0.021
 bank-0.019
 banks-0.019
 symp-0.019
isc-0.019
Token.
Token ID13
Feature activation-5.64e-04

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.005
ro+0.005
 symp+0.005
Neg logit contributions
ww-0.012
www-0.010
heart-0.009
mber-0.009
ons-0.009
Token "
Token ID366
Feature activation-2.15e-02

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
ro+0.001
isc+0.001
Neg logit contributions
ww-0.001
www-0.001
ons-0.001
heart-0.001
loo-0.001
TokenE
Token ID36
Feature activation-1.40e-03

Pos logit contributions
 bank+0.036
 banks+0.034
 allowance+0.032
ro+0.031
 symp+0.030
Neg logit contributions
ww-0.037
www-0.032
loo-0.031
ons-0.030
?"-0.030
Tokenww
Token ID1383
Feature activation+1.29e-01

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.003
ro+0.003
 symp+0.003
Neg logit contributions
ww-0.001
www-0.001
heart-0.001
loo-0.001
?"-0.001
Token,
Token ID11
Feature activation+7.75e-03

Pos logit contributions
ww+0.255
ull+0.234
www+0.232
loo+0.224
mber+0.222
Neg logit contributions
 bank-0.162
 banks-0.153
 allowance-0.144
isc-0.125
ro-0.118
Token what
Token ID644
Feature activation+2.98e-02

Pos logit contributions
ww+0.014
www+0.012
ons+0.011
ins+0.011
heart+0.011
Neg logit contributions
 bank-0.012
 banks-0.011
 allowance-0.011
 symp-0.010
 buy-0.010
Token's
Token ID338
Feature activation-3.13e-03

Pos logit contributions
ww+0.068
www+0.063
loo+0.059
heart+0.058
very+0.058
Neg logit contributions
 seem-0.029
 allowance-0.028
 bank-0.028
 usual-0.024
 banks-0.023
Token that
Token ID326
Feature activation-1.09e-02

Pos logit contributions
 bank+0.004
 allowance+0.004
 banks+0.004
 usual+0.003
 any+0.003
Neg logit contributions
ww-0.006
www-0.006
mber-0.006
heart-0.005
loo-0.005
Token?"
Token ID1701
Feature activation+2.15e-02

Pos logit contributions
 bank+0.022
 banks+0.020
 allowance+0.018
 seem+0.018
isc+0.017
Neg logit contributions
ww-0.015
www-0.013
ons-0.013
loo-0.012
mber-0.012
Token and
Token ID290
Feature activation+2.43e-03

Pos logit contributions
 bank+0.005
 allowance+0.005
 banks+0.005
isc+0.005
urd+0.005
Neg logit contributions
ww-0.006
www-0.005
heart-0.004
?"-0.004
ons-0.004
Token said
Token ID531
Feature activation-2.54e-03

Pos logit contributions
ww+0.005
www+0.004
heart+0.004
loo+0.004
mber+0.004
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.004
ro-0.003
 symp-0.003
Token,
Token ID11
Feature activation+4.68e-03

Pos logit contributions
 bank+0.004
 banks+0.004
 allowance+0.003
ro+0.003
 symp+0.003
Neg logit contributions
ww-0.005
www-0.005
heart-0.004
mber-0.004
ons-0.004
Token "
Token ID366
Feature activation-2.05e-02

Pos logit contributions
ww+0.008
www+0.007
?"+0.006
heart+0.006
mber+0.006
Neg logit contributions
 bank-0.008
 banks-0.008
 allowance-0.007
isc-0.007
ro-0.007
TokenE
Token ID36
Feature activation-3.06e-03

Pos logit contributions
 bank+0.037
 banks+0.036
 allowance+0.035
isc+0.032
ro+0.031
Neg logit contributions
ww-0.035
www-0.030
heart-0.026
mber-0.025
ons-0.025
Tokenww
Token ID1383
Feature activation+1.28e-01

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.005
ro+0.005
isc+0.005
Neg logit contributions
ww-0.004
www-0.004
heart-0.004
mber-0.003
ons-0.003
Token,
Token ID11
Feature activation+3.52e-03

Pos logit contributions
ww+0.272
www+0.250
mber+0.237
heart+0.230
ull+0.229
Neg logit contributions
 bank-0.159
 banks-0.153
 allowance-0.145
isc-0.127
ro-0.124
Token Bruno
Token ID31045
Feature activation-1.77e-02

Pos logit contributions
ww+0.006
www+0.005
heart+0.005
ons+0.005
mber+0.005
Neg logit contributions
 bank-0.006
 banks-0.006
 allowance-0.006
ro-0.005
isc-0.005
Token.
Token ID13
Feature activation-7.82e-03

Pos logit contributions
 bank+0.022
 banks+0.020
 allowance+0.018
ro+0.016
isc+0.016
Neg logit contributions
ww-0.040
www-0.036
heart-0.034
mber-0.034
ons-0.033
Token You
Token ID921
Feature activation+8.09e-03

Pos logit contributions
 bank+0.014
 banks+0.013
 allowance+0.013
isc+0.012
ro+0.012
Neg logit contributions
ww-0.014
www-0.012
mber-0.011
heart-0.011
ons-0.011
Token are
Token ID389
Feature activation-1.30e-02

Pos logit contributions
ww+0.017
www+0.015
?"+0.014
ons+0.014
heart+0.014
Neg logit contributions
 bank-0.011
 banks-0.011
 allowance-0.010
 symp-0.009
ro-0.009
Token be
Token ID307
Feature activation-1.22e-02

Pos logit contributions
ww+0.073
www+0.065
?"+0.060
heart+0.059
ons+0.057
Neg logit contributions
 bank-0.047
 banks-0.045
 allowance-0.042
isc-0.039
 symp-0.038
Token bitter
Token ID12922
Feature activation-1.02e-02

Pos logit contributions
 bank+0.018
 banks+0.017
 allowance+0.017
ro+0.015
 usual+0.015
Neg logit contributions
ww-0.024
www-0.022
loo-0.019
mber-0.019
heart-0.019
Token,
Token ID11
Feature activation-1.25e-03

Pos logit contributions
 bank+0.014
 banks+0.013
 allowance+0.012
isc+0.011
 symp+0.011
Neg logit contributions
ww-0.022
www-0.019
?"-0.018
heart-0.018
ons-0.017
Token like
Token ID588
Feature activation-3.06e-02

Pos logit contributions
 bank+0.002
 banks+0.002
 allowance+0.001
isc+0.001
ro+0.001
Neg logit contributions
ww-0.003
www-0.002
heart-0.002
?"-0.002
ons-0.002
Token e
Token ID304
Feature activation-1.63e-02

Pos logit contributions
 bank+0.051
 allowance+0.049
 banks+0.048
 usual+0.045
ro+0.043
Neg logit contributions
ww-0.054
www-0.049
mber-0.044
heart-0.044
loo-0.042
Tokenww
Token ID1383
Feature activation+1.28e-01

Pos logit contributions
 bank+0.032
 banks+0.031
 allowance+0.029
 symp+0.028
ro+0.027
Neg logit contributions
ww-0.023
www-0.020
mber-0.018
loo-0.017
igator-0.015
Token.
Token ID13
Feature activation-2.79e-03

Pos logit contributions
ww+0.246
www+0.220
mber+0.199
heart+0.199
loo+0.194
Neg logit contributions
 bank-0.193
 banks-0.186
 allowance-0.177
ro-0.157
isc-0.152
Token Do
Token ID2141
Feature activation+3.00e-02

Pos logit contributions
 bank+0.005
 banks+0.004
 allowance+0.004
isc+0.004
ro+0.004
Neg logit contributions
ww-0.005
www-0.004
heart-0.004
ons-0.004
mber-0.004
Token you
Token ID345
Feature activation-5.51e-03

Pos logit contributions
ww+0.036
www+0.030
heart+0.027
loo+0.027
mber+0.025
Neg logit contributions
 bank-0.064
 allowance-0.062
 banks-0.061
 usual-0.057
 seem-0.057
Token want
Token ID765
Feature activation+1.00e-02

Pos logit contributions
 bank+0.007
 banks+0.007
 allowance+0.006
isc+0.005
ro+0.005
Neg logit contributions
ww-0.012
www-0.011
?"-0.010
heart-0.010
ons-0.010
Token to
Token ID284
Feature activation-6.18e-03

Pos logit contributions
ww+0.026
www+0.024
heart+0.023
mber+0.022
loo+0.022
Neg logit contributions
 bank-0.009
 banks-0.007
 allowance-0.007
 usual-0.006
ro-0.005
Token at
Token ID379
Feature activation+2.40e-02

Pos logit contributions
 bank+0.010
 banks+0.010
 allowance+0.009
ro+0.008
isc+0.008
Neg logit contributions
ww-0.019
www-0.017
heart-0.016
?"-0.016
ons-0.016
Token it
Token ID340
Feature activation+2.23e-03

Pos logit contributions
ww+0.052
www+0.046
mber+0.042
heart+0.041
ons+0.040
Neg logit contributions
 bank-0.034
 banks-0.032
 allowance-0.030
 usual-0.026
ro-0.025
Token said
Token ID531
Feature activation-1.20e-02

Pos logit contributions
ww+0.005
www+0.005
heart+0.004
mber+0.004
ons+0.004
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.002
ro-0.002
 usual-0.002
Token "
Token ID366
Feature activation-2.36e-02

Pos logit contributions
 bank+0.018
 banks+0.018
 allowance+0.017
ro+0.015
isc+0.015
Neg logit contributions
ww-0.023
www-0.021
heart-0.018
ons-0.018
mber-0.018
Tokenew
Token ID413
Feature activation+7.13e-03

Pos logit contributions
 bank+0.038
 banks+0.036
 allowance+0.034
ro+0.031
isc+0.031
Neg logit contributions
ww-0.044
www-0.039
heart-0.035
ons-0.034
mber-0.034
Tokenww
Token ID1383
Feature activation+1.28e-01

Pos logit contributions
ww+0.012
www+0.010
loo+0.010
mber+0.009
heart+0.009
Neg logit contributions
 bank-0.012
 banks-0.012
ro-0.010
 allowance-0.010
 symp-0.010
Token!"
Token ID2474
Feature activation+7.84e-03

Pos logit contributions
ww+0.203
www+0.180
loo+0.171
heart+0.166
ull+0.162
Neg logit contributions
 bank-0.220
 banks-0.216
 allowance-0.197
ro-0.184
isc-0.183
Token
Token ID220
Feature activation-2.02e-02

Pos logit contributions
ww+0.018
www+0.016
heart+0.015
ons+0.015
mber+0.015
Neg logit contributions
 bank-0.010
 banks-0.009
 allowance-0.008
ro-0.007
 symp-0.007
Token
Token ID198
Feature activation+1.37e-03

Pos logit contributions
 bank+0.031
 banks+0.030
 allowance+0.028
ro+0.025
isc+0.025
Neg logit contributions
ww-0.039
www-0.034
heart-0.031
ons-0.031
?"-0.031
Token
Token ID198
Feature activation+1.87e-03

Pos logit contributions
ww+0.003
www+0.003
heart+0.003
loo+0.002
ons+0.002
Neg logit contributions
 bank-0.002
 banks-0.002
 allowance-0.001
ro-0.001
 usual-0.001
TokenOne
Token ID3198
Feature activation+2.26e-03

Pos logit contributions
ww+0.004
www+0.004
heart+0.004
loo+0.004
ons+0.003
Neg logit contributions
 bank-0.002
 banks-0.002
 allowance-0.002
ro-0.002
side-0.002
Token and
Token ID290
Feature activation+6.97e-03

Pos logit contributions
 bank+0.012
 banks+0.011
 allowance+0.011
isc+0.009
ro+0.009
Neg logit contributions
ww-0.017
www-0.015
heart-0.014
ons-0.014
?"-0.014
Token said
Token ID531
Feature activation+2.74e-03

Pos logit contributions
ww+0.014
www+0.012
loo+0.011
ons+0.011
mber+0.010
Neg logit contributions
 bank-0.011
 banks-0.010
 allowance-0.010
 symp-0.009
 usual-0.009
Token,
Token ID11
Feature activation+1.06e-02

Pos logit contributions
ww+0.005
www+0.004
heart+0.004
?"+0.004
ons+0.004
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.004
isc-0.004
ro-0.004
Token "
Token ID366
Feature activation-1.40e-02

Pos logit contributions
ww+0.020
www+0.018
heart+0.016
ons+0.016
mber+0.015
Neg logit contributions
 bank-0.017
 banks-0.016
 allowance-0.015
ro-0.014
isc-0.014
TokenA
Token ID32
Feature activation-2.37e-02

Pos logit contributions
 bank+0.025
 banks+0.024
 allowance+0.023
ro+0.021
isc+0.021
Neg logit contributions
ww-0.023
www-0.020
ons-0.018
heart-0.018
loo-0.017
Tokenww
Token ID1383
Feature activation+1.27e-01

Pos logit contributions
 bank+0.033
 banks+0.032
 allowance+0.030
ro+0.027
isc+0.027
Neg logit contributions
ww-0.046
www-0.041
ons-0.040
heart-0.039
mber-0.038
Tokenwww
Token ID2503
Feature activation+6.03e-02

Pos logit contributions
ww+0.244
ull+0.232
igator+0.225
www+0.222
loo+0.218
Neg logit contributions
 bank-0.150
 banks-0.146
 allowance-0.139
ro-0.130
isc-0.130
Token,
Token ID11
Feature activation+8.85e-03

Pos logit contributions
ww+0.111
www+0.098
mber+0.091
loo+0.088
igator+0.087
Neg logit contributions
 bank-0.091
 banks-0.087
 allowance-0.083
isc-0.079
ro-0.078
Token do
Token ID466
Feature activation+1.96e-02

Pos logit contributions
ww+0.016
www+0.014
ons+0.013
ins+0.013
loo+0.013
Neg logit contributions
 bank-0.014
 banks-0.013
 allowance-0.012
isc-0.012
 symp-0.011
Token I
Token ID314
Feature activation+1.75e-02

Pos logit contributions
ww+0.029
www+0.025
heart+0.024
loo+0.024
mber+0.023
Neg logit contributions
 bank-0.036
 banks-0.035
 allowance-0.033
 seem-0.031
 usual-0.030
Token have
Token ID423
Feature activation+1.32e-02

Pos logit contributions
ww+0.037
www+0.033
heart+0.030
?"+0.030
ons+0.029
Neg logit contributions
 bank-0.024
 banks-0.023
 allowance-0.021
ro-0.019
isc-0.019
Token.
Token ID13
Feature activation+9.66e-04

Pos logit contributions
 bank+0.021
 banks+0.020
 allowance+0.019
isc+0.017
ro+0.017
Neg logit contributions
ww-0.031
www-0.027
heart-0.025
ons-0.025
?"-0.025
Token
Token ID198
Feature activation+4.49e-03

Pos logit contributions
ww+0.002
www+0.002
heart+0.001
ons+0.001
mber+0.001
Neg logit contributions
 bank-0.002
 banks-0.002
 allowance-0.001
ro-0.001
isc-0.001
Token
Token ID198
Feature activation+5.39e-03

Pos logit contributions
ww+0.009
www+0.008
ons+0.007
heart+0.007
?"+0.007
Neg logit contributions
 bank-0.007
 banks-0.007
 allowance-0.006
ro-0.006
isc-0.006
Token"
Token ID1
Feature activation-1.65e-03

Pos logit contributions
ww+0.010
www+0.008
heart+0.008
ons+0.007
loo+0.007
Neg logit contributions
 bank-0.009
 banks-0.009
 allowance-0.008
ro-0.007
 symp-0.007
TokenE
Token ID36
Feature activation-3.11e-03

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.002
ro+0.002
 symp+0.002
Neg logit contributions
ww-0.003
www-0.002
loo-0.002
?"-0.002
ons-0.002
Tokenww
Token ID1383
Feature activation+1.27e-01

Pos logit contributions
 bank+0.008
 banks+0.007
 allowance+0.007
ro+0.007
isc+0.007
Neg logit contributions
ww-0.003
www-0.002
heart-0.002
ons-0.002
loo-0.002
Token!"
Token ID2474
Feature activation+6.23e-03

Pos logit contributions
ww+0.246
ull+0.225
www+0.224
loo+0.222
igator+0.220
Neg logit contributions
 bank-0.162
 banks-0.155
 allowance-0.146
isc-0.130
ro-0.126
Token she
Token ID673
Feature activation-8.56e-03

Pos logit contributions
ww+0.010
www+0.009
heart+0.007
loo+0.007
ons+0.007
Neg logit contributions
 bank-0.012
 banks-0.011
 allowance-0.011
ro-0.010
isc-0.010
Token screamed
Token ID25421
Feature activation+1.68e-02

Pos logit contributions
 bank+0.017
 banks+0.016
 allowance+0.015
ro+0.014
isc+0.014
Neg logit contributions
ww-0.013
www-0.011
loo-0.010
heart-0.010
ons-0.010
Token.
Token ID13
Feature activation-2.57e-03

Pos logit contributions
ww+0.022
heart+0.021
?"+0.021
?+0.021
www+0.019
Neg logit contributions
 bank-0.030
 banks-0.030
 allowance-0.028
isc-0.027
tted-0.025
Token
Token ID198
Feature activation+1.86e-03

Pos logit contributions
 bank+0.004
 banks+0.004
 allowance+0.004
isc+0.003
ro+0.003
Neg logit contributions
ww-0.005
www-0.004
heart-0.004
mber-0.004
ons-0.004
Token She
Token ID1375
Feature activation+6.89e-03

Pos logit contributions
ww+0.005
www+0.004
heart+0.004
mber+0.004
ons+0.004
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.003
ro-0.003
isc-0.003
Token said
Token ID531
Feature activation-2.19e-03

Pos logit contributions
ww+0.014
www+0.013
loo+0.012
heart+0.012
ons+0.011
Neg logit contributions
 bank-0.010
 banks-0.009
 allowance-0.008
ro-0.008
 symp-0.008
Token,
Token ID11
Feature activation+5.62e-03

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.003
ro+0.002
 symp+0.002
Neg logit contributions
ww-0.005
www-0.004
heart-0.004
mber-0.004
ons-0.004
Token "
Token ID366
Feature activation-1.96e-02

Pos logit contributions
ww+0.011
www+0.010
heart+0.009
ons+0.008
mber+0.008
Neg logit contributions
 bank-0.009
 banks-0.008
 allowance-0.008
ro-0.007
isc-0.007
TokenE
Token ID36
Feature activation-1.27e-03

Pos logit contributions
 bank+0.036
 banks+0.034
 allowance+0.031
ro+0.031
 symp+0.030
Neg logit contributions
ww-0.031
www-0.027
loo-0.025
ons-0.025
heart-0.025
Tokenww
Token ID1383
Feature activation+1.26e-01

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.003
ro+0.003
isc+0.003
Neg logit contributions
ww-0.001
heart-0.001
www-0.001
mber-0.001
loo-0.001
Token,
Token ID11
Feature activation+4.78e-03

Pos logit contributions
ww+0.270
www+0.255
igator+0.250
ull+0.245
mber+0.245
Neg logit contributions
 bank-0.127
 allowance-0.123
 banks-0.119
isc-0.108
ro-0.103
Token disgusting
Token ID23374
Feature activation+5.00e-03

Pos logit contributions
ww+0.009
www+0.008
heart+0.007
mber+0.007
ons+0.007
Neg logit contributions
 bank-0.007
 banks-0.007
 allowance-0.007
 symp-0.006
isc-0.006
Token!"
Token ID2474
Feature activation+6.49e-03

Pos logit contributions
ww+0.008
www+0.007
mber+0.007
John+0.007
very+0.007
Neg logit contributions
 bank-0.008
 banks-0.008
ro-0.007
 bottom-0.007
 anymore-0.007
Token She
Token ID1375
Feature activation+1.01e-02

Pos logit contributions
ww+0.012
www+0.011
heart+0.010
ons+0.010
mber+0.009
Neg logit contributions
 bank-0.010
 banks-0.010
 allowance-0.009
ro-0.009
isc-0.008
Token threw
Token ID9617
Feature activation+3.97e-03

Pos logit contributions
ww+0.021
www+0.019
loo+0.018
heart+0.018
mber+0.016
Neg logit contributions
 bank-0.014
 banks-0.013
 allowance-0.012
ro-0.012
ked-0.011
Token.
Token ID13
Feature activation+5.65e-04

Pos logit contributions
ww+0.029
www+0.026
heart+0.023
mber+0.023
ons+0.023
Neg logit contributions
 bank-0.014
 banks-0.013
 allowance-0.011
ro-0.010
 usual-0.010
Token
Token ID198
Feature activation+7.57e-03

Pos logit contributions
ww+0.001
www+0.001
heart+0.001
ons+0.001
loo+0.001
Neg logit contributions
 bank-0.001
 banks-0.001
 allowance-0.001
ro-0.001
isc-0.001
Token
Token ID198
Feature activation+8.12e-03

Pos logit contributions
ww+0.016
www+0.014
heart+0.013
ons+0.013
mber+0.013
Neg logit contributions
 bank-0.010
 banks-0.010
 allowance-0.009
ro-0.008
isc-0.008
Token"
Token ID1
Feature activation-7.57e-04

Pos logit contributions
ww+0.015
www+0.013
loo+0.013
ons+0.013
heart+0.013
Neg logit contributions
 bank-0.012
 banks-0.011
 allowance-0.010
ro-0.010
 symp-0.010
TokenE
Token ID36
Feature activation-1.12e-03

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
ro+0.001
 symp+0.001
Neg logit contributions
ww-0.001
www-0.001
heart-0.001
ons-0.001
loo-0.001
Tokenww
Token ID1383
Feature activation+1.26e-01

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.003
ro+0.003
isc+0.002
Neg logit contributions
ww-0.001
www-0.001
heart-0.001
ons-0.001
mber-0.001
Token,
Token ID11
Feature activation+9.32e-03

Pos logit contributions
ww+0.270
www+0.247
ull+0.240
igator+0.234
loo+0.234
Neg logit contributions
 bank-0.141
 banks-0.135
 allowance-0.122
isc-0.108
ro-0.106
Token this
Token ID428
Feature activation-3.12e-02

Pos logit contributions
ww+0.018
www+0.016
ons+0.015
ins+0.015
heart+0.014
Neg logit contributions
 bank-0.013
 banks-0.012
 allowance-0.012
 buy-0.011
 seem-0.011
Token fish
Token ID5916
Feature activation-1.14e-02

Pos logit contributions
 bank+0.061
 banks+0.057
 allowance+0.048
 bottom+0.047
ro+0.045
Neg logit contributions
ww-0.051
www-0.046
heart-0.044
ons-0.043
imi-0.043
Token is
Token ID318
Feature activation+1.81e-02

Pos logit contributions
 bank+0.018
 banks+0.016
 find+0.014
 allowance+0.013
ro+0.013
Neg logit contributions
ww-0.022
www-0.019
mber-0.019
Charlie-0.019
John-0.018
Token sm
Token ID895
Feature activation-4.43e-03

Pos logit contributions
ww+0.039
www+0.036
heart+0.034
mber+0.033
ons+0.033
Neg logit contributions
 bank-0.024
 banks-0.023
 allowance-0.020
 usual-0.019
 properly-0.017
Token friends
Token ID2460
Feature activation+2.98e-02

Pos logit contributions
ww+0.028
www+0.025
heart+0.023
ons+0.023
loo+0.022
Neg logit contributions
 bank-0.014
 allowance-0.013
 banks-0.013
isc-0.011
 usual-0.011
Token said
Token ID531
Feature activation+5.89e-03

Pos logit contributions
ww+0.060
www+0.052
loo+0.046
ons+0.046
heart+0.045
Neg logit contributions
 bank-0.047
 banks-0.044
 allowance-0.039
 symp-0.037
ro-0.036
Token,
Token ID11
Feature activation+7.07e-03

Pos logit contributions
ww+0.011
www+0.010
heart+0.009
ons+0.009
?"+0.009
Neg logit contributions
 bank-0.009
 banks-0.009
 allowance-0.009
isc-0.008
ro-0.008
Token "
Token ID366
Feature activation-1.39e-02

Pos logit contributions
ww+0.016
www+0.014
loo+0.013
ons+0.013
heart+0.013
Neg logit contributions
 bank-0.009
 banks-0.008
 allowance-0.007
 symp-0.007
ro-0.007
TokenA
Token ID32
Feature activation-1.98e-02

Pos logit contributions
ro+0.017
 bank+0.017
side+0.016
 banks+0.015
tted+0.015
Neg logit contributions
ww-0.028
?"-0.026
loo-0.026
ons-0.025
www-0.025
Tokenww
Token ID1383
Feature activation+1.26e-01

Pos logit contributions
 bank+0.031
 allowance+0.027
ro+0.026
 banks+0.026
ork+0.025
Neg logit contributions
ons-0.034
ins-0.033
ries-0.033
heart-0.032
ww-0.031
Token,
Token ID11
Feature activation+4.03e-03

Pos logit contributions
ww+0.265
www+0.245
mber+0.238
ull+0.237
igator+0.232
Neg logit contributions
 bank-0.145
 banks-0.134
 allowance-0.130
ro-0.117
isc-0.114
Token okay
Token ID8788
Feature activation-1.59e-02

Pos logit contributions
ww+0.007
www+0.006
ons+0.006
ins+0.006
ined+0.006
Neg logit contributions
 bank-0.006
 allowance-0.005
 banks-0.005
 buy-0.005
ro-0.005
Token.
Token ID13
Feature activation-4.53e-03

Pos logit contributions
 anymore+0.016
 bank+0.014
 banks+0.013
 any+0.013
 properly+0.013
Neg logit contributions
ww-0.037
ons-0.034
www-0.034
mber-0.032
orn-0.031
Token But
Token ID887
Feature activation-1.86e-02

Pos logit contributions
 bank+0.007
 banks+0.007
 allowance+0.007
ro+0.007
isc+0.007
Neg logit contributions
ww-0.008
www-0.007
ons-0.006
heart-0.006
mber-0.006
Token come
Token ID1282
Feature activation-1.54e-02

Pos logit contributions
 bank+0.028
 banks+0.027
 allowance+0.026
 usual+0.024
ro+0.023
Neg logit contributions
ww-0.036
www-0.032
ons-0.029
mber-0.029
heart-0.028
Token
Token ID26391
Feature activation-3.20e-02

Pos logit contributions
ww+0.078
www+0.069
ons+0.064
heart+0.063
mber+0.063
Neg logit contributions
 bank-0.051
 banks-0.049
ro-0.043
 allowance-0.043
isc-0.041
Token
Token ID8151
Feature activation-4.22e-02

Pos logit contributions
 bank+0.047
 banks+0.045
 allowance+0.043
ro+0.042
isc+0.041
Neg logit contributions
ww-0.060
www-0.053
heart-0.052
loo-0.048
ons-0.048
Tokens
Token ID82
Feature activation+3.33e-03

Pos logit contributions
 bank+0.058
 banks+0.055
 allowance+0.052
ro+0.046
isc+0.045
Neg logit contributions
ww-0.089
www-0.079
heart-0.072
ons-0.071
mber-0.070
Token okay
Token ID8788
Feature activation-4.97e-03

Pos logit contributions
ww+0.007
www+0.006
ons+0.006
mber+0.006
loo+0.005
Neg logit contributions
 bank-0.005
 banks-0.005
 allowance-0.004
ro-0.004
isc-0.004
Token sweet
Token ID6029
Feature activation+3.90e-02

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.005
ro+0.005
 symp+0.005
Neg logit contributions
ww-0.011
www-0.010
ons-0.010
loo-0.009
 course-0.009
Tokenheart
Token ID11499
Feature activation+1.25e-01

Pos logit contributions
ww+0.037
www+0.029
ons+0.029
Charlie+0.027
loo+0.025
Neg logit contributions
 bank-0.089
ro-0.086
 banks-0.085
 allowance-0.082
isc-0.080
Token.
Token ID13
Feature activation-9.17e-03

Pos logit contributions
ww+0.269
www+0.236
loo+0.223
ons+0.220
mber+0.218
Neg logit contributions
 bank-0.163
 banks-0.146
 allowance-0.143
ro-0.134
 seem-0.125
Token How
Token ID1374
Feature activation-5.52e-03

Pos logit contributions
 bank+0.013
 banks+0.013
 allowance+0.012
ro+0.012
isc+0.011
Neg logit contributions
ww-0.018
www-0.016
ons-0.015
loo-0.014
w-0.014
Token about
Token ID546
Feature activation+3.11e-03

Pos logit contributions
 bank+0.009
 banks+0.009
 allowance+0.008
isc+0.008
ro+0.008
Neg logit contributions
ww-0.010
www-0.009
heart-0.008
?"-0.008
ons-0.008
Token I
Token ID314
Feature activation+1.67e-02

Pos logit contributions
ww+0.006
www+0.005
loo+0.005
mber+0.005
heart+0.005
Neg logit contributions
 bank-0.005
 banks-0.005
 allowance-0.005
 usual-0.004
 buy-0.004
Token give
Token ID1577
Feature activation-1.01e-02

Pos logit contributions
ww+0.038
www+0.034
ons+0.031
heart+0.031
mber+0.031
Neg logit contributions
 bank-0.021
 banks-0.019
 allowance-0.018
ro-0.016
isc-0.015
Token He
Token ID679
Feature activation+7.11e-03

Pos logit contributions
ww+0.002
www+0.002
heart+0.002
ons+0.001
loo+0.001
Neg logit contributions
 bank-0.001
 banks-0.001
 allowance-0.001
ro-0.001
isc-0.001
Token says
Token ID1139
Feature activation+7.07e-03

Pos logit contributions
ww+0.012
www+0.010
heart+0.009
loo+0.008
mber+0.008
Neg logit contributions
 bank-0.014
 banks-0.014
 allowance-0.013
ro-0.012
 symp-0.012
Token,
Token ID11
Feature activation+8.23e-03

Pos logit contributions
ww+0.016
www+0.014
heart+0.013
mber+0.013
loo+0.012
Neg logit contributions
 bank-0.008
 allowance-0.007
 banks-0.007
ro-0.006
 anymore-0.006
Token "
Token ID366
Feature activation-1.93e-02

Pos logit contributions
ww+0.016
www+0.014
heart+0.013
ons+0.013
mber+0.012
Neg logit contributions
 bank-0.013
 banks-0.012
 allowance-0.011
ro-0.010
isc-0.010
TokenA
Token ID32
Feature activation-2.36e-02

Pos logit contributions
 bank+0.034
 banks+0.032
 allowance+0.031
ro+0.029
isc+0.028
Neg logit contributions
ww-0.033
www-0.029
heart-0.027
ons-0.026
?"-0.025
Tokenww
Token ID1383
Feature activation+1.25e-01

Pos logit contributions
 bank+0.038
 allowance+0.036
ork+0.033
 banks+0.032
 loudspe+0.031
Neg logit contributions
heart-0.038
ww-0.037
www-0.034
loo-0.034
imi-0.034
Token,
Token ID11
Feature activation+6.61e-03

Pos logit contributions
ww+0.256
igator+0.248
ull+0.247
mber+0.246
www+0.242
Neg logit contributions
 bank-0.125
 allowance-0.116
 banks-0.111
isc-0.103
ro-0.101
Token this
Token ID428
Feature activation-2.90e-02

Pos logit contributions
ww+0.012
www+0.011
heart+0.010
mber+0.009
ons+0.009
Neg logit contributions
 bank-0.010
 allowance-0.010
 banks-0.009
ro-0.009
 symp-0.009
Token is
Token ID318
Feature activation+2.04e-02

Pos logit contributions
 bank+0.049
 allowance+0.045
 banks+0.043
ork+0.040
isc+0.037
Neg logit contributions
ww-0.049
heart-0.047
www-0.045
mber-0.043
Andy-0.041
Token from
Token ID422
Feature activation-3.74e-02

Pos logit contributions
ww+0.036
www+0.033
heart+0.032
mber+0.030
loo+0.029
Neg logit contributions
 bank-0.033
 allowance-0.033
 banks-0.030
 usual-0.030
isc-0.028
Token Anna
Token ID11735
Feature activation+5.49e-03

Pos logit contributions
 bank+0.077
 allowance+0.073
 banks+0.071
 usual+0.068
ro+0.065
Neg logit contributions
ww-0.053
www-0.045
heart-0.041
mber-0.040
loo-0.037
Token He
Token ID679
Feature activation+4.26e-04

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
ro+0.001
isc+0.001
Neg logit contributions
ww-0.002
www-0.002
heart-0.002
ons-0.002
w-0.002
Token said
Token ID531
Feature activation-9.22e-03

Pos logit contributions
ww+0.001
www+0.001
loo+0.001
heart+0.001
ons+0.001
Neg logit contributions
 bank-0.001
 banks-0.001
 allowance-0.001
 widened-0.001
ro-0.001
Token,
Token ID11
Feature activation-3.61e-03

Pos logit contributions
 bank+0.011
 banks+0.010
 allowance+0.010
 symp+0.009
ro+0.009
Neg logit contributions
ww-0.020
www-0.018
heart-0.017
mber-0.016
ons-0.016
Token "
Token ID366
Feature activation-2.66e-02

Pos logit contributions
 bank+0.005
 banks+0.005
 allowance+0.005
ro+0.004
 symp+0.004
Neg logit contributions
ww-0.007
www-0.007
heart-0.006
ons-0.006
mber-0.006
TokenE
Token ID36
Feature activation-7.98e-03

Pos logit contributions
 bank+0.042
 banks+0.040
ro+0.038
 allowance+0.037
side+0.036
Neg logit contributions
ww-0.044
www-0.039
loo-0.039
heart-0.037
ons-0.037
Tokenww
Token ID1383
Feature activation+1.24e-01

Pos logit contributions
 bank+0.017
 banks+0.016
 allowance+0.016
ro+0.015
isc+0.015
Neg logit contributions
ww-0.008
heart-0.007
www-0.007
mber-0.006
?"-0.006
Token,
Token ID11
Feature activation-4.02e-03

Pos logit contributions
ww+0.269
www+0.251
igator+0.248
ull+0.244
heart+0.240
Neg logit contributions
 bank-0.126
 allowance-0.120
 banks-0.115
isc-0.102
ro-0.096
Token this
Token ID428
Feature activation-3.53e-02

Pos logit contributions
 bank+0.006
 allowance+0.005
 buy+0.005
 seem+0.005
 banks+0.005
Neg logit contributions
ww-0.007
www-0.007
heart-0.006
ins-0.006
ined-0.006
Token is
Token ID318
Feature activation+1.03e-02

Pos logit contributions
 bank+0.051
 bottom+0.043
 allowance+0.042
 banks+0.041
 anymore+0.040
Neg logit contributions
ww-0.065
www-0.059
heart-0.058
Andy-0.057
imi-0.056
Token the
Token ID262
Feature activation+7.21e-03

Pos logit contributions
ww+0.022
www+0.020
loo+0.019
heart+0.019
mber+0.018
Neg logit contributions
 bank-0.012
 allowance-0.012
 banks-0.011
 usual-0.011
 anymore-0.011
Token worst
Token ID5290
Feature activation+2.08e-03

Pos logit contributions
ww+0.013
www+0.011
heart+0.010
mber+0.010
ons+0.010
Neg logit contributions
 bank-0.013
 banks-0.011
 allowance-0.011
 usual-0.011
 bottom-0.010
Token
Token ID8151
Feature activation-3.48e-02

Pos logit contributions
 bank+0.043
 banks+0.041
 allowance+0.040
isc+0.039
ro+0.038
Neg logit contributions
ww-0.053
www-0.047
heart-0.046
igator-0.043
loo-0.043
Tokens
Token ID82
Feature activation+2.69e-03

Pos logit contributions
 bank+0.051
 banks+0.049
 allowance+0.046
isc+0.043
ro+0.042
Neg logit contributions
ww-0.067
www-0.059
heart-0.053
mber-0.052
loo-0.052
Token wonderful
Token ID7932
Feature activation+1.33e-02

Pos logit contributions
ww+0.005
www+0.005
ons+0.004
loo+0.004
mber+0.004
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.003
 seem-0.003
isc-0.003
Token,
Token ID11
Feature activation+1.13e-02

Pos logit contributions
ww+0.026
ons+0.024
loo+0.023
www+0.023
ined+0.023
Neg logit contributions
 bank-0.016
 allowance-0.015
ro-0.015
 banks-0.014
isc-0.013
Token sweet
Token ID6029
Feature activation+2.93e-02

Pos logit contributions
ww+0.021
www+0.018
ons+0.018
loo+0.018
rooms+0.017
Neg logit contributions
 bank-0.016
 allowance-0.015
 banks-0.015
ro-0.014
isc-0.014
Tokenheart
Token ID11499
Feature activation+1.21e-01

Pos logit contributions
ww+0.025
ons+0.019
www+0.018
loo+0.018
Charlie+0.017
Neg logit contributions
 bank-0.066
ro-0.064
 banks-0.064
isc-0.064
 allowance-0.061
Token!
Token ID0
Feature activation+1.36e-02

Pos logit contributions
ww+0.260
www+0.224
loo+0.214
imi+0.214
ons+0.210
Neg logit contributions
 bank-0.147
 banks-0.134
ro-0.124
 allowance-0.122
 until-0.116
Token Keep
Token ID9175
Feature activation+3.49e-02

Pos logit contributions
ww+0.027
www+0.024
ons+0.023
loo+0.023
heart+0.021
Neg logit contributions
 bank-0.018
 banks-0.017
 allowance-0.017
isc-0.017
ro-0.016
Token spring
Token ID6076
Feature activation-2.14e-02

Pos logit contributions
ww+0.070
www+0.059
loo+0.057
heart+0.054
mber+0.054
Neg logit contributions
 bank-0.054
 banks-0.051
 allowance-0.048
 find-0.045
 until-0.044
Tokening
Token ID278
Feature activation+2.20e-02

Pos logit contributions
 bank+0.031
 banks+0.030
 allowance+0.027
ro+0.027
side+0.024
Neg logit contributions
ww-0.043
www-0.038
mber-0.034
ons-0.034
loo-0.034
Token around
Token ID1088
Feature activation-6.15e-03

Pos logit contributions
ww+0.047
www+0.043
mber+0.039
loo+0.039
ons+0.038
Neg logit contributions
 bank-0.029
 banks-0.028
 allowance-0.025
ro-0.024
 symp-0.022
Token
Token ID26391
Feature activation-3.18e-02

Pos logit contributions
ww+0.077
ins+0.066
www+0.066
heart+0.064
ons+0.063
Neg logit contributions
 bank-0.049
 banks-0.045
ro-0.044
tted-0.039
 allowance-0.039
Token
Token ID8151
Feature activation-3.80e-02

Pos logit contributions
 bank+0.045
 banks+0.043
 allowance+0.043
isc+0.041
ro+0.039
Neg logit contributions
ww-0.060
www-0.053
heart-0.052
igator-0.049
 course-0.048
Tokens
Token ID82
Feature activation+1.88e-03

Pos logit contributions
 bank+0.056
 banks+0.053
 allowance+0.050
isc+0.045
 symp+0.045
Neg logit contributions
ww-0.075
www-0.066
heart-0.060
mber-0.058
ons-0.057
Token wrong
Token ID2642
Feature activation+6.40e-03

Pos logit contributions
ww+0.004
heart+0.003
www+0.003
mber+0.003
ins+0.003
Neg logit contributions
 allowance-0.002
 bank-0.002
 banks-0.002
 seem-0.002
 usual-0.002
Token sweet
Token ID6029
Feature activation+2.75e-02

Pos logit contributions
ww+0.007
ons+0.006
 course+0.006
www+0.006
loo+0.005
Neg logit contributions
 bank-0.014
 allowance-0.014
 banks-0.013
ro-0.013
isc-0.013
Tokenheart
Token ID11499
Feature activation+1.20e-01

Pos logit contributions
ww+0.041
Charlie+0.038
Steve+0.035
www+0.035
Andy+0.035
Neg logit contributions
ro-0.043
 bank-0.042
isc-0.042
 allowance-0.041
 seem-0.038
Token?
Token ID30
Feature activation+3.73e-02

Pos logit contributions
ww+0.155
www+0.115
mber+0.105
imi+0.102
ins+0.102
Neg logit contributions
 bank-0.244
 find-0.229
 allowance-0.229
 seem-0.227
 banks-0.223
Tokenâ
Token ID22940
Feature activation+3.94e-02

Pos logit contributions
ww+0.075
www+0.066
loo+0.061
ons+0.061
heart+0.060
Neg logit contributions
 bank-0.051
 allowance-0.049
 banks-0.048
isc-0.047
ro-0.045
Token
Token ID26391
Feature activation-3.03e-02

Pos logit contributions
ww+0.087
www+0.075
ins+0.075
ons+0.073
heart+0.072
Neg logit contributions
 bank-0.046
 banks-0.043
ro-0.039
isc-0.035
 symp-0.035
Token The
Token ID383
Feature activation-5.94e-03

Pos logit contributions
 bank+0.043
 banks+0.041
 allowance+0.039
isc+0.036
ro+0.035
Neg logit contributions
ww-0.061
www-0.054
heart-0.051
loo-0.048
mber-0.048
Token little
Token ID1310
Feature activation+9.33e-03

Pos logit contributions
 bank+0.010
 banks+0.009
 allowance+0.009
 usual+0.008
 bottom+0.008
Neg logit contributions
ww-0.011
www-0.010
heart-0.009
ons-0.009
mber-0.009
Token wait
Token ID4043
Feature activation-7.85e-03

Pos logit contributions
 bank+0.002
 banks+0.002
 allowance+0.002
ro+0.001
isc+0.001
Neg logit contributions
ww-0.004
www-0.004
mber-0.004
heart-0.004
ons-0.004
Token in
Token ID287
Feature activation-4.25e-03

Pos logit contributions
 bank+0.009
 banks+0.009
 allowance+0.008
ro+0.007
 usual+0.007
Neg logit contributions
ww-0.018
www-0.016
ons-0.015
heart-0.015
mber-0.015
Token line
Token ID1627
Feature activation-1.27e-02

Pos logit contributions
 bank+0.007
 banks+0.006
 allowance+0.006
ro+0.005
isc+0.005
Neg logit contributions
ww-0.008
www-0.007
heart-0.007
ons-0.006
mber-0.006
Token,
Token ID11
Feature activation+7.10e-03

Pos logit contributions
 bank+0.020
 banks+0.019
 allowance+0.018
ro+0.017
 usual+0.016
Neg logit contributions
ww-0.024
www-0.021
heart-0.019
mber-0.019
ons-0.019
Token sweet
Token ID6029
Feature activation+2.54e-02

Pos logit contributions
ww+0.015
www+0.013
ons+0.012
heart+0.012
loo+0.012
Neg logit contributions
 bank-0.010
 banks-0.009
 allowance-0.009
ro-0.008
isc-0.008
Tokenheart
Token ID11499
Feature activation+1.18e-01

Pos logit contributions
ww+0.026
www+0.020
loo+0.019
ons+0.018
igator+0.018
Neg logit contributions
 bank-0.057
 banks-0.056
 allowance-0.052
ro-0.050
isc-0.050
Token.
Token ID13
Feature activation-3.54e-03

Pos logit contributions
ww+0.236
www+0.202
loo+0.189
ons+0.188
mber+0.188
Neg logit contributions
 bank-0.171
 banks-0.158
 allowance-0.152
ro-0.145
 anymore-0.138
Tokenâ
Token ID22940
Feature activation+3.63e-02

Pos logit contributions
 bank+0.005
 banks+0.005
 allowance+0.005
ro+0.005
isc+0.005
Neg logit contributions
ww-0.007
www-0.006
ons-0.006
heart-0.005
loo-0.005
Token
Token ID26391
Feature activation-2.98e-02

Pos logit contributions
ww+0.077
www+0.067
heart+0.063
ons+0.063
loo+0.061
Neg logit contributions
 bank-0.048
 banks-0.046
 allowance-0.040
ro-0.039
isc-0.037
Token She
Token ID1375
Feature activation+1.02e-02

Pos logit contributions
 bank+0.046
 banks+0.044
 allowance+0.041
ro+0.037
isc+0.036
Neg logit contributions
ww-0.058
www-0.052
ons-0.046
heart-0.046
?"-0.046
Token then
Token ID788
Feature activation-5.70e-02

Pos logit contributions
ww+0.021
www+0.018
loo+0.018
heart+0.017
ons+0.017
Neg logit contributions
 bank-0.014
 banks-0.013
 allowance-0.013
isc-0.011
ro-0.011
Token
Token ID129
Feature activation-1.61e-02

Pos logit contributions
 bank+0.044
 banks+0.042
 allowance+0.040
isc+0.038
ro+0.036
Neg logit contributions
ww-0.055
www-0.048
heart-0.047
igator-0.043
mber-0.043
Token
Token ID241
Feature activation+4.19e-03

Pos logit contributions
 bank+0.025
 allowance+0.024
 banks+0.023
 usual+0.021
isc+0.020
Neg logit contributions
ww-0.030
www-0.028
?"-0.024
heart-0.023
mber-0.023
TokenYes
Token ID5297
Feature activation+4.02e-02

Pos logit contributions
ww+0.007
www+0.006
ons+0.006
heart+0.005
loo+0.005
Neg logit contributions
 bank-0.007
 banks-0.007
 allowance-0.007
ro-0.007
 usual-0.006
Token,
Token ID11
Feature activation+9.31e-03

Pos logit contributions
ww+0.073
www+0.063
ons+0.061
loo+0.059
mber+0.058
Neg logit contributions
 bank-0.062
 banks-0.058
 allowance-0.056
isc-0.051
ro-0.051
Token sweet
Token ID6029
Feature activation+2.87e-02

Pos logit contributions
ww+0.016
www+0.013
ons+0.013
loo+0.013
heart+0.012
Neg logit contributions
 bank-0.015
 allowance-0.015
 banks-0.014
ro-0.014
isc-0.013
Tokenheart
Token ID11499
Feature activation+1.18e-01

Pos logit contributions
ww+0.030
ons+0.027
web+0.026
Charlie+0.026
loo+0.025
Neg logit contributions
 bank-0.055
isc-0.054
ro-0.054
 banks-0.052
 allowance-0.049
Token,
Token ID11
Feature activation+7.92e-03

Pos logit contributions
ww+0.265
www+0.231
mber+0.228
ons+0.225
loo+0.223
Neg logit contributions
 bank-0.125
 banks-0.108
ro-0.104
 allowance-0.103
 anymore-0.100
Token it
Token ID340
Feature activation+9.62e-03

Pos logit contributions
ww+0.013
www+0.012
loo+0.011
ons+0.011
heart+0.011
Neg logit contributions
 bank-0.013
 allowance-0.012
 banks-0.012
ro-0.011
isc-0.011
Tokenâ
Token ID22940
Feature activation+3.66e-02

Pos logit contributions
ww+0.022
www+0.019
loo+0.019
mber+0.018
ull+0.018
Neg logit contributions
 bank-0.011
 banks-0.010
 seem-0.009
chy-0.009
 allowance-0.008
Token
Token ID26391
Feature activation-3.08e-02

Pos logit contributions
ww+0.076
ins+0.067
www+0.067
ons+0.066
heart+0.066
Neg logit contributions
 bank-0.045
 banks-0.040
ro-0.039
tted-0.037
isc-0.035
Token
Token ID8151
Feature activation-3.77e-02

Pos logit contributions
 bank+0.043
 banks+0.041
 allowance+0.039
isc+0.036
ro+0.035
Neg logit contributions
ww-0.062
www-0.055
heart-0.054
mber-0.050
igator-0.050
Token
Token ID129
Feature activation-1.64e-02

Pos logit contributions
 bank+0.046
 banks+0.044
 allowance+0.042
ro+0.038
isc+0.037
Neg logit contributions
ww-0.052
www-0.045
ons-0.040
?"-0.040
heart-0.040
Token
Token ID241
Feature activation+4.36e-03

Pos logit contributions
 allowance+0.026
 bank+0.025
 banks+0.024
 usual+0.023
 injuries+0.023
Neg logit contributions
ww-0.030
www-0.028
?"-0.024
 my-0.023
mber-0.022
TokenNo
Token ID2949
Feature activation+6.33e-02

Pos logit contributions
ww+0.007
www+0.006
ons+0.006
heart+0.006
loo+0.005
Neg logit contributions
 bank-0.008
 banks-0.007
 allowance-0.007
ro-0.007
isc-0.007
Token,
Token ID11
Feature activation+6.55e-03

Pos logit contributions
ww+0.130
www+0.114
loo+0.114
ull+0.110
ons+0.109
Neg logit contributions
 bank-0.080
 allowance-0.073
 banks-0.072
isc-0.064
ro-0.063
Token sweet
Token ID6029
Feature activation+2.48e-02

Pos logit contributions
ww+0.011
loo+0.010
ins+0.010
www+0.009
orn+0.009
Neg logit contributions
 bank-0.010
 allowance-0.010
 banks-0.009
 buy-0.009
 seem-0.009
Tokenheart
Token ID11499
Feature activation+1.17e-01

Pos logit contributions
ww+0.023
ons+0.020
Charlie+0.019
loo+0.018
igator+0.018
Neg logit contributions
isc-0.051
ro-0.050
 bank-0.050
 banks-0.046
 allowance-0.046
Token.
Token ID13
Feature activation+2.55e-03

Pos logit contributions
ww+0.253
www+0.222
mber+0.208
ons+0.206
loo+0.205
Neg logit contributions
 bank-0.149
 banks-0.135
 allowance-0.130
ro-0.118
isc-0.114
Token That
Token ID1320
Feature activation+1.33e-02

Pos logit contributions
ww+0.004
www+0.004
ons+0.003
heart+0.003
loo+0.003
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.004
isc-0.004
ro-0.004
Token dress
Token ID6576
Feature activation+2.97e-03

Pos logit contributions
ww+0.029
www+0.026
loo+0.025
heart+0.024
ons+0.024
Neg logit contributions
 bank-0.017
 banks-0.015
 allowance-0.014
isc-0.012
ro-0.012
Token is
Token ID318
Feature activation+1.62e-02

Pos logit contributions
ww+0.005
www+0.004
mber+0.004
loo+0.004
ull+0.004
Neg logit contributions
 bank-0.005
 banks-0.005
 allowance-0.005
ro-0.005
isc-0.005
Token too
Token ID1165
Feature activation+2.96e-02

Pos logit contributions
ww+0.035
www+0.031
loo+0.030
ons+0.030
heart+0.029
Neg logit contributions
 bank-0.020
 allowance-0.019
 banks-0.018
 usual-0.017
 properly-0.016
Token Sally
Token ID25737
Feature activation-2.82e-02

Pos logit contributions
 bank+0.044
 banks+0.042
 allowance+0.040
ro+0.037
 seem+0.036
Neg logit contributions
ww-0.055
www-0.048
mber-0.043
heart-0.042
loo-0.040
Token told
Token ID1297
Feature activation-6.82e-03

Pos logit contributions
 bank+0.040
 banks+0.038
 allowance+0.036
ro+0.032
isc+0.031
Neg logit contributions
ww-0.059
www-0.052
heart-0.047
mber-0.046
loo-0.046
Token him
Token ID683
Feature activation-2.68e-02

Pos logit contributions
 bank+0.011
 banks+0.011
 allowance+0.010
ro+0.009
isc+0.009
Neg logit contributions
ww-0.012
www-0.011
heart-0.010
ons-0.010
mber-0.009
Token,
Token ID11
Feature activation-1.20e-02

Pos logit contributions
 bank+0.037
 banks+0.035
 allowance+0.034
ro+0.030
 usual+0.029
Neg logit contributions
ww-0.057
www-0.050
heart-0.045
mber-0.045
ons-0.044
Token Wh
Token ID854
Feature activation-8.23e-02

Pos logit contributions
 bank+0.019
 banks+0.018
 allowance+0.017
 usual+0.016
ro+0.016
Neg logit contributions
ww-0.023
www-0.021
loo-0.018
mber-0.018
heart-0.018
Tokenisk
Token ID1984
Feature activation-1.55e-01

Pos logit contributions
 bank+0.075
 banks+0.070
 allowance+0.063
ro+0.050
isc+0.049
Neg logit contributions
ww-0.212
www-0.193
heart-0.180
ons-0.177
?"-0.176
Tokeners
Token ID364
Feature activation-2.91e-02

Pos logit contributions
 bank+0.280
 banks+0.268
 allowance+0.253
ro+0.239
isc+0.230
Neg logit contributions
ww-0.261
www-0.225
heart-0.200
mber-0.191
?"-0.191
Token always
Token ID1464
Feature activation+2.30e-02

Pos logit contributions
 bank+0.044
 banks+0.041
 allowance+0.038
ro+0.035
isc+0.034
Neg logit contributions
ww-0.059
www-0.052
heart-0.047
ons-0.046
mber-0.046
Token wanted
Token ID2227
Feature activation+4.45e-03

Pos logit contributions
ww+0.047
www+0.040
loo+0.040
mber+0.037
ull+0.037
Neg logit contributions
 bank-0.033
 banks-0.030
 allowance-0.029
 usual-0.027
 seem-0.027
Token to
Token ID284
Feature activation-2.02e-02

Pos logit contributions
ww+0.011
www+0.009
heart+0.009
ons+0.009
mber+0.009
Neg logit contributions
 bank-0.005
 banks-0.005
 allowance-0.004
ro-0.004
isc-0.004
Token help
Token ID1037
Feature activation-2.48e-02

Pos logit contributions
 bank+0.024
 banks+0.022
 allowance+0.020
ro+0.017
 buy+0.017
Neg logit contributions
ww-0.049
www-0.044
mber-0.041
heart-0.040
loo-0.040
Token on
Token ID319
Feature activation-1.55e-02

Pos logit contributions
 bank+0.022
 banks+0.020
 anymore+0.019
 allowance+0.018
 properly+0.018
Neg logit contributions
ww-0.049
www-0.044
mber-0.042
heart-0.041
imi-0.039
Token the
Token ID262
Feature activation-4.59e-03

Pos logit contributions
 bank+0.021
 banks+0.020
 allowance+0.019
 usual+0.017
ro+0.017
Neg logit contributions
ww-0.034
www-0.030
heart-0.027
mber-0.027
loo-0.026
Token cards
Token ID4116
Feature activation-3.54e-02

Pos logit contributions
 bank+0.007
 banks+0.007
 allowance+0.007
ro+0.006
isc+0.006
Neg logit contributions
ww-0.009
www-0.008
heart-0.007
ons-0.007
mber-0.007
Token.
Token ID13
Feature activation-1.20e-02

Pos logit contributions
 bank+0.044
 banks+0.040
 allowance+0.035
ro+0.031
 anymore+0.030
Neg logit contributions
ww-0.085
www-0.076
heart-0.071
mber-0.070
imi-0.068
Token Wh
Token ID854
Feature activation-7.34e-02

Pos logit contributions
 bank+0.013
 banks+0.013
 allowance+0.012
ro+0.011
isc+0.011
Neg logit contributions
ww-0.028
www-0.025
heart-0.024
ons-0.023
w-0.022
Tokenisk
Token ID1984
Feature activation-1.49e-01

Pos logit contributions
 bank+0.073
 banks+0.068
 allowance+0.062
 symp+0.049
 usual+0.049
Neg logit contributions
ww-0.183
www-0.166
heart-0.156
ons-0.154
?"-0.153
Tokeners
Token ID364
Feature activation-2.00e-02

Pos logit contributions
 bank+0.280
 banks+0.270
 allowance+0.255
ro+0.237
isc+0.233
Neg logit contributions
ww-0.240
www-0.206
heart-0.182
mber-0.174
?"-0.173
Token was
Token ID373
Feature activation+9.04e-05

Pos logit contributions
 bank+0.030
 banks+0.028
 allowance+0.026
ro+0.024
 symp+0.023
Neg logit contributions
ww-0.041
www-0.036
heart-0.033
mber-0.032
loo-0.031
Token hesitant
Token ID32848
Feature activation+2.48e-02

Pos logit contributions
ww+0.000
www+0.000
heart+0.000
loo+0.000
mber+0.000
Neg logit contributions
 bank-0.000
 banks-0.000
 allowance-0.000
 usual-0.000
ro-0.000
Token at
Token ID379
Feature activation+2.02e-02

Pos logit contributions
ww+0.049
www+0.043
heart+0.040
?"+0.038
mber+0.038
Neg logit contributions
 bank-0.038
 banks-0.037
 allowance-0.035
ro-0.031
isc-0.031
Token first
Token ID717
Feature activation-6.59e-02

Pos logit contributions
ww+0.053
www+0.048
heart+0.044
mber+0.043
ons+0.043
Neg logit contributions
 bank-0.020
 banks-0.018
 allowance-0.017
 usual-0.016
ro-0.014
Token a
Token ID257
Feature activation-9.42e-03

Pos logit contributions
 bank+0.010
 banks+0.010
 allowance+0.009
ro+0.008
isc+0.008
Neg logit contributions
ww-0.014
www-0.013
heart-0.012
mber-0.011
ons-0.011
Token naughty
Token ID45128
Feature activation-1.82e-02

Pos logit contributions
 bank+0.013
 banks+0.013
 allowance+0.012
ro+0.011
isc+0.011
Neg logit contributions
ww-0.019
www-0.017
heart-0.016
ons-0.015
mber-0.015
Token cat
Token ID3797
Feature activation-2.10e-02

Pos logit contributions
 bank+0.029
 banks+0.026
 allowance+0.025
ro+0.025
isc+0.024
Neg logit contributions
ww-0.033
www-0.029
ons-0.029
heart-0.026
ins-0.025
Token named
Token ID3706
Feature activation+4.60e-03

Pos logit contributions
 bank+0.033
 banks+0.029
ro+0.026
 allowance+0.026
 anymore+0.025
Neg logit contributions
ww-0.043
www-0.038
mber-0.034
heart-0.034
very-0.031
Token Wh
Token ID854
Feature activation-7.34e-02

Pos logit contributions
ww+0.007
www+0.006
?"+0.005
heart+0.005
ons+0.005
Neg logit contributions
 bank-0.009
 banks-0.009
 allowance-0.008
ro-0.007
 symp-0.007
Tokenisk
Token ID1984
Feature activation-1.49e-01

Pos logit contributions
 bank+0.087
 banks+0.081
 allowance+0.079
 contain+0.065
 symp+0.063
Neg logit contributions
ww-0.163
www-0.146
ons-0.143
?"-0.142
imi-0.141
Tokeners
Token ID364
Feature activation-1.93e-02

Pos logit contributions
 bank+0.271
 banks+0.259
 allowance+0.244
ro+0.229
isc+0.223
Neg logit contributions
ww-0.250
www-0.216
heart-0.194
mber-0.184
?"-0.181
Token.
Token ID13
Feature activation-1.04e-02

Pos logit contributions
 allowance+0.036
 banks+0.035
 bank+0.035
urd+0.033
ro+0.032
Neg logit contributions
?"-0.026
?-0.026
ww-0.025
ons-0.023
 course-0.022
Token Wh
Token ID854
Feature activation-6.82e-02

Pos logit contributions
 bank+0.016
 banks+0.016
 allowance+0.015
 contain+0.014
ately+0.014
Neg logit contributions
ww-0.020
www-0.017
?"-0.015
 my-0.015
imi-0.015
Tokenisk
Token ID1984
Feature activation-1.45e-01

Pos logit contributions
 bank+0.078
 banks+0.074
 allowance+0.071
 contain+0.062
 usual+0.059
Neg logit contributions
ww-0.155
www-0.138
ons-0.134
?"-0.133
imi-0.131
Tokeners
Token ID364
Feature activation-1.65e-02

Pos logit contributions
 bank+0.258
 banks+0.247
 allowance+0.231
ro+0.218
isc+0.210
Neg logit contributions
ww-0.247
www-0.214
heart-0.192
mber-0.183
?"-0.178
Token flew
Token ID13112
Feature activation-8.76e-03

Pos logit contributions
ww+0.002
www+0.001
heart+0.001
ons+0.001
mber+0.001
Neg logit contributions
 bank-0.001
 banks-0.001
 allowance-0.001
ro-0.001
isc-0.001
Token down
Token ID866
Feature activation-1.93e-02

Pos logit contributions
 bank+0.010
 banks+0.009
ro+0.008
 allowance+0.008
 usual+0.007
Neg logit contributions
ww-0.021
www-0.019
ons-0.018
mber-0.017
heart-0.017
Token and
Token ID290
Feature activation+2.17e-03

Pos logit contributions
 bank+0.025
 banks+0.024
 allowance+0.022
isc+0.019
ro+0.019
Neg logit contributions
ww-0.042
www-0.037
heart-0.034
ons-0.034
?"-0.034
Token scared
Token ID12008
Feature activation+1.64e-02

Pos logit contributions
ww+0.004
www+0.004
loo+0.004
heart+0.004
ons+0.004
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.003
ro-0.003
 usual-0.002
Token Wh
Token ID854
Feature activation-7.25e-02

Pos logit contributions
ww+0.033
www+0.029
heart+0.026
ons+0.026
mber+0.026
Neg logit contributions
 bank-0.024
 banks-0.023
 allowance-0.022
ro-0.020
isc-0.019
Tokenisk
Token ID1984
Feature activation-1.48e-01

Pos logit contributions
 bank+0.084
 allowance+0.080
 banks+0.078
 symp+0.062
 usual+0.061
Neg logit contributions
ww-0.165
www-0.148
heart-0.142
imi-0.137
ons-0.137
Tokeners
Token ID364
Feature activation-1.99e-02

Pos logit contributions
 bank+0.292
 banks+0.283
 allowance+0.272
 symp+0.249
isc+0.248
Neg logit contributions
ww-0.222
www-0.188
ons-0.163
heart-0.162
mber-0.157
Token away
Token ID1497
Feature activation-6.42e-03

Pos logit contributions
 bank+0.029
 allowance+0.029
 banks+0.029
isc+0.028
 symp+0.026
Neg logit contributions
ww-0.033
www-0.029
?"-0.028
?-0.028
ons-0.027
Token.
Token ID13
Feature activation-7.44e-03

Pos logit contributions
 bank+0.009
 banks+0.008
 allowance+0.008
isc+0.007
ro+0.007
Neg logit contributions
ww-0.014
www-0.012
heart-0.011
?"-0.011
ons-0.011
Token
Token ID198
Feature activation+4.95e-03

Pos logit contributions
 bank+0.011
 banks+0.011
 allowance+0.010
ro+0.009
isc+0.009
Neg logit contributions
ww-0.015
www-0.013
heart-0.012
ons-0.012
mber-0.011
Token
Token ID198
Feature activation+5.99e-03

Pos logit contributions
ww+0.011
www+0.010
heart+0.009
ons+0.009
loo+0.009
Neg logit contributions
 bank-0.006
 banks-0.006
 allowance-0.006
ro-0.005
isc-0.005
Token a
Token ID257
Feature activation-7.39e-03

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.005
 usual+0.005
isc+0.005
Neg logit contributions
ww-0.009
www-0.008
heart-0.007
mber-0.007
loo-0.007
Token smart
Token ID4451
Feature activation-2.97e-02

Pos logit contributions
 bank+0.010
 banks+0.010
 allowance+0.009
ro+0.008
 symp+0.008
Neg logit contributions
ww-0.015
www-0.014
heart-0.013
ons-0.013
mber-0.012
Token cat
Token ID3797
Feature activation-1.87e-02

Pos logit contributions
 bank+0.045
 banks+0.040
ro+0.039
 allowance+0.038
isc+0.035
Neg logit contributions
ww-0.056
ons-0.050
www-0.050
heart-0.046
w-0.043
Token named
Token ID3706
Feature activation+6.34e-03

Pos logit contributions
 bank+0.027
 banks+0.024
ro+0.021
 anymore+0.020
 allowance+0.020
Neg logit contributions
ww-0.039
www-0.035
mber-0.032
heart-0.032
ins-0.029
Token Wh
Token ID854
Feature activation-7.11e-02

Pos logit contributions
ww+0.010
www+0.008
heart+0.007
ons+0.007
?"+0.007
Neg logit contributions
 bank-0.012
 banks-0.012
 allowance-0.011
ro-0.011
isc-0.010
Tokenisk
Token ID1984
Feature activation-1.47e-01

Pos logit contributions
 bank+0.083
 banks+0.078
 allowance+0.075
 symp+0.060
ro+0.059
Neg logit contributions
ww-0.161
www-0.145
ons-0.138
?"-0.137
heart-0.136
Tokeners
Token ID364
Feature activation-1.52e-02

Pos logit contributions
 bank+0.262
 banks+0.251
 allowance+0.235
ro+0.222
isc+0.215
Neg logit contributions
ww-0.250
www-0.216
heart-0.195
mber-0.185
?"-0.182
Token.
Token ID13
Feature activation-7.51e-03

Pos logit contributions
 allowance+0.027
 bank+0.027
 banks+0.027
urd+0.025
ro+0.024
Neg logit contributions
ww-0.022
?"-0.021
?-0.021
ons-0.019
 course-0.019
Token Wh
Token ID854
Feature activation-6.73e-02

Pos logit contributions
 bank+0.012
 banks+0.011
 allowance+0.010
 contain+0.010
 symp+0.010
Neg logit contributions
ww-0.014
www-0.012
?"-0.011
 my-0.011
ons-0.011
Tokenisk
Token ID1984
Feature activation-1.43e-01

Pos logit contributions
 bank+0.069
 banks+0.064
 allowance+0.061
 symp+0.048
 usual+0.048
Neg logit contributions
ww-0.164
www-0.148
ons-0.140
?"-0.138
heart-0.138
Tokeners
Token ID364
Feature activation-1.33e-02

Pos logit contributions
 bank+0.251
 banks+0.240
 allowance+0.222
ro+0.212
tted+0.203
Neg logit contributions
ww-0.249
www-0.216
heart-0.195
mber-0.185
?"-0.181
Token j
Token ID474
Feature activation-1.23e-02

Pos logit contributions
 bank+0.010
 banks+0.009
 allowance+0.008
ro+0.008
isc+0.007
Neg logit contributions
ww-0.014
www-0.013
heart-0.012
ons-0.011
mber-0.011
Tokenolly
Token ID5098
Feature activation+6.71e-03

Pos logit contributions
 bank+0.024
 banks+0.023
 allowance+0.022
ro+0.021
isc+0.021
Neg logit contributions
ww-0.018
www-0.015
heart-0.013
ons-0.013
mber-0.013
Token cat
Token ID3797
Feature activation-1.65e-02

Pos logit contributions
ww+0.013
www+0.011
ons+0.011
heart+0.011
loo+0.010
Neg logit contributions
 bank-0.010
 banks-0.009
 allowance-0.009
ro-0.009
isc-0.008
Token named
Token ID3706
Feature activation+8.28e-03

Pos logit contributions
 bank+0.026
 banks+0.023
ro+0.020
 allowance+0.020
 symp+0.019
Neg logit contributions
ww-0.033
www-0.030
mber-0.027
heart-0.026
loo-0.024
Token Wh
Token ID854
Feature activation-7.03e-02

Pos logit contributions
ww+0.013
www+0.011
?"+0.010
heart+0.010
ons+0.010
Neg logit contributions
 bank-0.016
 banks-0.015
 allowance-0.015
ro-0.014
isc-0.013
Tokenisk
Token ID1984
Feature activation-1.47e-01

Pos logit contributions
 bank+0.083
 banks+0.078
 allowance+0.075
 contain+0.061
 symp+0.058
Neg logit contributions
ww-0.159
www-0.142
ons-0.138
imi-0.137
?"-0.135
Tokeners
Token ID364
Feature activation-1.47e-02

Pos logit contributions
 bank+0.263
 banks+0.252
 allowance+0.236
ro+0.223
isc+0.217
Neg logit contributions
ww-0.248
www-0.214
heart-0.193
mber-0.183
?"-0.182
Token.
Token ID13
Feature activation-7.89e-03

Pos logit contributions
 allowance+0.029
 banks+0.028
 bank+0.028
urd+0.026
asy+0.026
Neg logit contributions
?-0.019
?"-0.019
ww-0.018
 course-0.016
ons-0.016
Token Wh
Token ID854
Feature activation-6.68e-02

Pos logit contributions
 bank+0.012
 banks+0.012
 allowance+0.011
 contain+0.011
ately+0.010
Neg logit contributions
ww-0.015
www-0.013
?"-0.012
imi-0.011
 my-0.011
Tokenisk
Token ID1984
Feature activation-1.44e-01

Pos logit contributions
 bank+0.075
 banks+0.070
 allowance+0.067
 contain+0.055
 usual+0.055
Neg logit contributions
ww-0.156
www-0.140
ons-0.134
?"-0.131
heart-0.131
Tokeners
Token ID364
Feature activation-1.31e-02

Pos logit contributions
 bank+0.249
 banks+0.238
 allowance+0.220
ro+0.211
tted+0.202
Neg logit contributions
ww-0.251
www-0.219
heart-0.198
mber-0.187
?"-0.185
Token was
Token ID373
Feature activation-8.06e-03

Pos logit contributions
 bank+0.037
 banks+0.036
 allowance+0.034
isc+0.031
ro+0.031
Neg logit contributions
ww-0.036
www-0.031
?"-0.029
ons-0.028
heart-0.028
Token a
Token ID257
Feature activation-9.05e-03

Pos logit contributions
 bank+0.012
 banks+0.011
 allowance+0.011
 usual+0.009
isc+0.009
Neg logit contributions
ww-0.016
www-0.015
heart-0.013
mber-0.013
ons-0.013
Token cat
Token ID3797
Feature activation-1.80e-02

Pos logit contributions
 bank+0.012
 banks+0.011
 allowance+0.011
ro+0.010
 symp+0.010
Neg logit contributions
ww-0.019
www-0.017
heart-0.016
ons-0.016
mber-0.015
Token named
Token ID3706
Feature activation+6.27e-03

Pos logit contributions
 bank+0.029
 banks+0.026
 allowance+0.023
ro+0.023
 symp+0.022
Neg logit contributions
ww-0.035
www-0.031
heart-0.028
mber-0.028
loo-0.026
Token Wh
Token ID854
Feature activation-6.84e-02

Pos logit contributions
ww+0.010
www+0.009
heart+0.007
ons+0.007
?"+0.007
Neg logit contributions
 bank-0.012
 banks-0.012
 allowance-0.011
ro-0.010
 symp-0.010
Tokenisk
Token ID1984
Feature activation-1.46e-01

Pos logit contributions
 bank+0.086
 banks+0.082
 allowance+0.079
 contain+0.067
 symp+0.062
Neg logit contributions
ww-0.146
www-0.130
ons-0.129
imi-0.127
?"-0.125
Tokeners
Token ID364
Feature activation-1.17e-02

Pos logit contributions
 bank+0.280
 banks+0.271
 allowance+0.258
ro+0.237
isc+0.236
Neg logit contributions
ww-0.228
www-0.195
heart-0.171
ons-0.166
mber-0.164
Token.
Token ID13
Feature activation-3.22e-03

Pos logit contributions
 allowance+0.022
 banks+0.022
 bank+0.021
isc+0.020
urd+0.020
Neg logit contributions
?"-0.015
?-0.015
ww-0.015
ons-0.013
 course-0.013
Token Wh
Token ID854
Feature activation-6.73e-02

Pos logit contributions
 bank+0.005
 banks+0.005
 allowance+0.005
ately+0.005
 contain+0.005
Neg logit contributions
ww-0.006
www-0.005
?"-0.005
ons-0.004
 my-0.004
Tokenisk
Token ID1984
Feature activation-1.45e-01

Pos logit contributions
 bank+0.077
 banks+0.073
 allowance+0.070
 contain+0.061
 usual+0.059
Neg logit contributions
ww-0.153
www-0.137
ons-0.133
?"-0.129
heart-0.128
Tokeners
Token ID364
Feature activation-1.11e-02

Pos logit contributions
 bank+0.260
 banks+0.249
 allowance+0.232
ro+0.219
isc+0.213
Neg logit contributions
ww-0.246
www-0.213
heart-0.190
mber-0.182
?"-0.179
Token that
Token ID326
Feature activation-8.36e-03

Pos logit contributions
 bank+0.017
 banks+0.016
 allowance+0.014
 usual+0.013
 until+0.013
Neg logit contributions
ww-0.031
www-0.028
ins-0.027
heart-0.027
ons-0.026
Token day
Token ID1110
Feature activation-4.93e-03

Pos logit contributions
 bank+0.015
 allowance+0.014
 banks+0.014
 usual+0.013
ro+0.012
Neg logit contributions
ww-0.013
www-0.012
heart-0.011
ins-0.011
mber-0.010
Token on
Token ID319
Feature activation+1.81e-03

Pos logit contributions
 bank+0.010
 banks+0.010
 allowance+0.009
ro+0.008
isc+0.008
Neg logit contributions
ww-0.008
www-0.007
ons-0.006
?"-0.005
heart-0.005
Token,
Token ID11
Feature activation+5.89e-03

Pos logit contributions
ww+0.004
www+0.003
heart+0.003
mber+0.003
ons+0.003
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.002
ro-0.002
isc-0.002
Token Wh
Token ID854
Feature activation-6.85e-02

Pos logit contributions
ww+0.012
www+0.010
ons+0.009
 course+0.009
 my+0.009
Neg logit contributions
 banks-0.009
 bank-0.008
 symp-0.008
 allowance-0.007
 spine-0.007
Tokenisk
Token ID1984
Feature activation-1.46e-01

Pos logit contributions
 bank+0.085
 banks+0.083
 allowance+0.077
 contain+0.074
 usual+0.071
Neg logit contributions
ww-0.150
www-0.132
ons-0.125
heart-0.123
imi-0.121
Tokeners
Token ID364
Feature activation-1.08e-02

Pos logit contributions
 bank+0.274
 banks+0.265
 allowance+0.251
ro+0.232
isc+0.229
Neg logit contributions
ww-0.231
www-0.198
heart-0.175
mber-0.168
ons-0.168
Token was
Token ID373
Feature activation+2.67e-03

Pos logit contributions
 bank+0.016
 banks+0.015
 allowance+0.014
isc+0.013
ro+0.013
Neg logit contributions
ww-0.022
www-0.019
ons-0.017
heart-0.017
?"-0.017
Token no
Token ID645
Feature activation+2.03e-02

Pos logit contributions
ww+0.006
www+0.005
heart+0.005
loo+0.005
ons+0.005
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.003
 usual-0.003
 symp-0.002
Token longer
Token ID2392
Feature activation+3.18e-04

Pos logit contributions
ww+0.046
www+0.042
heart+0.040
?"+0.037
 course+0.037
Neg logit contributions
 bank-0.025
 banks-0.025
 allowance-0.020
isc-0.020
 symp-0.019
Token a
Token ID257
Feature activation-7.48e-03

Pos logit contributions
ww+0.001
www+0.001
heart+0.001
ons+0.001
mber+0.001
Neg logit contributions
 bank-0.000
 banks-0.000
 allowance-0.000
ro-0.000
isc-0.000
Token everyone
Token ID2506
Feature activation+2.60e-03

Pos logit contributions
ww+0.075
www+0.067
?"+0.060
heart+0.059
ons+0.059
Neg logit contributions
 bank-0.061
 banks-0.059
 allowance-0.055
 symp-0.049
ro-0.048
Token's
Token ID338
Feature activation-1.70e-03

Pos logit contributions
ww+0.006
www+0.005
heart+0.005
mber+0.005
loo+0.005
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.003
ro-0.002
 usual-0.002
Token surprise
Token ID5975
Feature activation+2.58e-02

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.003
ro+0.002
isc+0.002
Neg logit contributions
ww-0.003
www-0.003
heart-0.002
mber-0.002
ons-0.002
Token,
Token ID11
Feature activation+6.02e-03

Pos logit contributions
ww+0.052
www+0.046
heart+0.041
mber+0.041
ons+0.040
Neg logit contributions
 bank-0.038
 banks-0.036
 allowance-0.034
isc-0.031
ro-0.030
Token Wh
Token ID854
Feature activation-6.86e-02

Pos logit contributions
ww+0.011
www+0.010
heart+0.009
ons+0.009
mber+0.009
Neg logit contributions
 bank-0.010
 banks-0.009
 allowance-0.009
ro-0.008
isc-0.008
Tokenisk
Token ID1984
Feature activation-1.46e-01

Pos logit contributions
 bank+0.080
 banks+0.077
 allowance+0.073
 contain+0.065
 usual+0.062
Neg logit contributions
ww-0.155
www-0.138
heart-0.131
ons-0.131
imi-0.128
Tokeners
Token ID364
Feature activation-1.20e-02

Pos logit contributions
 bank+0.252
 banks+0.240
 allowance+0.223
ro+0.213
tted+0.206
Neg logit contributions
ww-0.254
www-0.220
heart-0.198
?"-0.190
mber-0.187
Token turned
Token ID2900
Feature activation-1.57e-02

Pos logit contributions
 bank+0.019
 banks+0.018
 allowance+0.017
ro+0.016
isc+0.016
Neg logit contributions
ww-0.022
www-0.020
heart-0.018
ons-0.018
?"-0.017
Token out
Token ID503
Feature activation-4.23e-02

Pos logit contributions
 bank+0.022
 banks+0.021
 allowance+0.019
isc+0.017
ro+0.017
Neg logit contributions
ww-0.033
www-0.029
heart-0.027
ons-0.027
?"-0.026
Token to
Token ID284
Feature activation-6.96e-03

Pos logit contributions
 bank+0.069
 banks+0.067
 allowance+0.063
isc+0.057
ro+0.057
Neg logit contributions
ww-0.078
www-0.068
heart-0.062
ons-0.061
?"-0.059
Token be
Token ID307
Feature activation-1.42e-02

Pos logit contributions
 bank+0.010
 banks+0.010
 allowance+0.010
 symp+0.009
isc+0.009
Neg logit contributions
ww-0.013
www-0.012
heart-0.011
?"-0.011
ons-0.010
Token
Token ID198
Feature activation-4.17e-03

Pos logit contributions
 bank+0.008
 banks+0.008
 allowance+0.007
ro+0.006
isc+0.006
Neg logit contributions
ww-0.016
www-0.014
heart-0.013
ons-0.012
loo-0.012
TokenAfter
Token ID3260
Feature activation+4.48e-03

Pos logit contributions
 bank+0.006
 banks+0.005
 allowance+0.005
tted+0.005
ro+0.005
Neg logit contributions
ww-0.008
www-0.007
heart-0.007
loo-0.007
ons-0.007
Token Mr
Token ID1770
Feature activation-4.17e-02

Pos logit contributions
ww+0.009
www+0.008
heart+0.008
mber+0.007
ins+0.007
Neg logit contributions
 bank-0.007
 banks-0.006
 allowance-0.006
 usual-0.005
 until-0.005
Token.
Token ID13
Feature activation-7.91e-03

Pos logit contributions
 bank+0.059
 banks+0.057
 allowance+0.053
ro+0.046
 symp+0.046
Neg logit contributions
ww-0.086
www-0.075
heart-0.069
?"-0.068
mber-0.067
Token Wh
Token ID854
Feature activation-7.03e-02

Pos logit contributions
 bank+0.012
 banks+0.011
 allowance+0.010
ro+0.010
isc+0.010
Neg logit contributions
ww-0.016
www-0.015
heart-0.013
ons-0.013
mber-0.013
Tokenisk
Token ID1984
Feature activation-1.45e-01

Pos logit contributions
 bank+0.075
 banks+0.071
 allowance+0.066
 usual+0.051
 contain+0.051
Neg logit contributions
ww-0.169
www-0.153
heart-0.145
ons-0.141
?"-0.139
Tokeners
Token ID364
Feature activation-1.33e-02

Pos logit contributions
 bank+0.263
 banks+0.252
 allowance+0.237
ro+0.223
isc+0.216
Neg logit contributions
ww-0.241
www-0.208
heart-0.186
?"-0.180
mber-0.177
Token was
Token ID373
Feature activation+2.79e-03

Pos logit contributions
 bank+0.020
 banks+0.020
 allowance+0.019
isc+0.017
ro+0.017
Neg logit contributions
ww-0.025
www-0.022
heart-0.020
ons-0.020
mber-0.020
Token done
Token ID1760
Feature activation-1.31e-02

Pos logit contributions
ww+0.006
www+0.006
heart+0.005
mber+0.005
ons+0.005
Neg logit contributions
 bank-0.004
 banks-0.003
 allowance-0.003
 usual-0.003
 symp-0.003
Token with
Token ID351
Feature activation+7.63e-03

Pos logit contributions
 bank+0.020
 banks+0.018
 allowance+0.018
ro+0.016
 symp+0.016
Neg logit contributions
ww-0.027
www-0.024
heart-0.021
mber-0.021
ons-0.020
Token his
Token ID465
Feature activation-3.54e-04

Pos logit contributions
ww+0.010
www+0.008
 my+0.008
 course+0.008
heart+0.008
Neg logit contributions
 banks-0.015
 bank-0.015
ro-0.014
 allowance-0.014
tted-0.013
Token a
Token ID257
Feature activation-6.98e-03

Pos logit contributions
 bank+0.007
 banks+0.006
 allowance+0.006
 usual+0.005
isc+0.005
Neg logit contributions
ww-0.009
www-0.008
heart-0.008
mber-0.007
ons-0.007
Token lazy
Token ID16931
Feature activation-1.34e-02

Pos logit contributions
 bank+0.010
 banks+0.009
 allowance+0.009
ro+0.008
isc+0.008
Neg logit contributions
ww-0.014
www-0.013
heart-0.012
ons-0.012
mber-0.011
Token cat
Token ID3797
Feature activation-1.58e-02

Pos logit contributions
 bank+0.019
 banks+0.017
ro+0.017
 allowance+0.015
isc+0.015
Neg logit contributions
ww-0.026
ons-0.024
www-0.023
ins-0.022
heart-0.022
Token named
Token ID3706
Feature activation+8.08e-03

Pos logit contributions
 bank+0.024
 banks+0.021
ro+0.019
 anymore+0.018
 allowance+0.018
Neg logit contributions
ww-0.033
www-0.030
mber-0.027
heart-0.026
ins-0.024
Token Wh
Token ID854
Feature activation-6.92e-02

Pos logit contributions
ww+0.013
www+0.011
?"+0.009
heart+0.009
 my+0.009
Neg logit contributions
 bank-0.016
 banks-0.015
 allowance-0.015
ro-0.013
 symp-0.013
Tokenisk
Token ID1984
Feature activation-1.45e-01

Pos logit contributions
 bank+0.083
 banks+0.077
 allowance+0.075
 contain+0.060
 symp+0.058
Neg logit contributions
ww-0.154
www-0.139
ons-0.135
imi-0.133
?"-0.131
Tokeners
Token ID364
Feature activation-1.03e-02

Pos logit contributions
 bank+0.264
 banks+0.253
 allowance+0.238
ro+0.223
isc+0.219
Neg logit contributions
ww-0.242
www-0.209
heart-0.187
mber-0.178
?"-0.177
Token.
Token ID13
Feature activation-5.27e-03

Pos logit contributions
 allowance+0.019
 banks+0.019
 bank+0.019
urd+0.018
ro+0.017
Neg logit contributions
?-0.014
?"-0.014
ww-0.013
 course-0.012
ons-0.012
Token Wh
Token ID854
Feature activation-6.66e-02

Pos logit contributions
 bank+0.008
 banks+0.008
 allowance+0.008
 contain+0.007
ately+0.007
Neg logit contributions
ww-0.010
www-0.008
?"-0.008
 my-0.007
imi-0.007
Tokenisk
Token ID1984
Feature activation-1.43e-01

Pos logit contributions
 bank+0.072
 banks+0.067
 allowance+0.064
 usual+0.051
 contain+0.051
Neg logit contributions
ww-0.158
www-0.143
ons-0.136
heart-0.134
?"-0.133
Tokeners
Token ID364
Feature activation-8.99e-03

Pos logit contributions
 bank+0.248
 banks+0.238
 allowance+0.219
ro+0.209
tted+0.202
Neg logit contributions
ww-0.249
www-0.217
heart-0.195
mber-0.186
?"-0.183
Token dream
Token ID4320
Feature activation-1.40e-02

Pos logit contributions
ww+0.004
 my+0.003
www+0.003
imi+0.003
?+0.002
Neg logit contributions
 banks-0.004
 bank-0.004
ked-0.004
 contain-0.004
ured-0.004
Token,
Token ID11
Feature activation+4.72e-04

Pos logit contributions
 bank+0.026
 banks+0.026
 allowance+0.024
 symp+0.022
isc+0.021
Neg logit contributions
ww-0.024
www-0.020
heart-0.018
mber-0.018
?"-0.018
Token she
Token ID673
Feature activation-1.28e-02

Pos logit contributions
ww+0.001
www+0.001
heart+0.000
ons+0.000
?"+0.000
Neg logit contributions
 bank-0.001
 banks-0.001
 allowance-0.001
ro-0.001
 symp-0.001
Token saw
Token ID2497
Feature activation-3.29e-03

Pos logit contributions
 bank+0.019
 banks+0.019
 allowance+0.017
isc+0.015
ro+0.015
Neg logit contributions
ww-0.025
www-0.022
heart-0.020
?"-0.020
ons-0.020
Token Wh
Token ID854
Feature activation-6.75e-02

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.005
ro+0.005
 symp+0.005
Neg logit contributions
ww-0.006
www-0.005
ons-0.004
heart-0.004
?"-0.004
Tokenisk
Token ID1984
Feature activation-1.45e-01

Pos logit contributions
 bank+0.085
 banks+0.079
 allowance+0.077
 contain+0.060
 symp+0.060
Neg logit contributions
ww-0.152
www-0.137
heart-0.130
imi-0.128
ons-0.126
Tokeners
Token ID364
Feature activation-1.04e-02

Pos logit contributions
 bank+0.284
 banks+0.275
 allowance+0.263
isc+0.240
ro+0.240
Neg logit contributions
ww-0.220
www-0.187
heart-0.163
ons-0.162
mber-0.157
Token walking
Token ID6155
Feature activation+4.42e-03

Pos logit contributions
 bank+0.018
 banks+0.017
 allowance+0.017
isc+0.015
ro+0.015
Neg logit contributions
ww-0.017
www-0.015
ons-0.014
heart-0.014
?"-0.014
Token and
Token ID290
Feature activation-2.24e-03

Pos logit contributions
ww+0.009
www+0.008
heart+0.007
ons+0.007
mber+0.007
Neg logit contributions
 bank-0.006
 banks-0.006
 allowance-0.006
ro-0.005
isc-0.005
Token talking
Token ID3375
Feature activation-1.03e-03

Pos logit contributions
 bank+0.004
 banks+0.003
 allowance+0.003
 usual+0.003
ro+0.003
Neg logit contributions
ww-0.005
www-0.004
heart-0.004
loo-0.003
ons-0.003
Token like
Token ID588
Feature activation-3.34e-02

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
ro+0.001
isc+0.001
Neg logit contributions
ww-0.002
www-0.002
heart-0.002
ons-0.002
mber-0.002
Token Wh
Token ID854
Feature activation-7.34e-02

Pos logit contributions
ww+0.007
www+0.006
?"+0.005
heart+0.005
ons+0.005
Neg logit contributions
 bank-0.009
 banks-0.009
 allowance-0.008
ro-0.007
 symp-0.007
Tokenisk
Token ID1984
Feature activation-1.49e-01

Pos logit contributions
 bank+0.087
 banks+0.081
 allowance+0.079
 contain+0.065
 symp+0.063
Neg logit contributions
ww-0.163
www-0.146
ons-0.143
?"-0.142
imi-0.141
Tokeners
Token ID364
Feature activation-1.93e-02

Pos logit contributions
 bank+0.271
 banks+0.259
 allowance+0.244
ro+0.229
isc+0.223
Neg logit contributions
ww-0.250
www-0.216
heart-0.194
mber-0.184
?"-0.181
Token.
Token ID13
Feature activation-1.04e-02

Pos logit contributions
 allowance+0.036
 banks+0.035
 bank+0.035
urd+0.033
ro+0.032
Neg logit contributions
?"-0.026
?-0.026
ww-0.025
ons-0.023
 course-0.022
Token Wh
Token ID854
Feature activation-6.82e-02

Pos logit contributions
 bank+0.016
 banks+0.016
 allowance+0.015
 contain+0.014
ately+0.014
Neg logit contributions
ww-0.020
www-0.017
?"-0.015
 my-0.015
imi-0.015
Tokenisk
Token ID1984
Feature activation-1.45e-01

Pos logit contributions
 bank+0.078
 banks+0.074
 allowance+0.071
 contain+0.062
 usual+0.059
Neg logit contributions
ww-0.155
www-0.138
ons-0.134
?"-0.133
imi-0.131
Tokeners
Token ID364
Feature activation-1.65e-02

Pos logit contributions
 bank+0.258
 banks+0.247
 allowance+0.231
ro+0.218
isc+0.210
Neg logit contributions
ww-0.247
www-0.214
heart-0.192
mber-0.183
?"-0.178
Token loved
Token ID6151
Feature activation+6.40e-03

Pos logit contributions
 bank+0.028
 banks+0.027
 allowance+0.026
isc+0.024
ro+0.024
Neg logit contributions
ww-0.029
www-0.025
?"-0.022
ons-0.022
heart-0.022
Token to
Token ID284
Feature activation-1.34e-02

Pos logit contributions
ww+0.018
www+0.017
heart+0.016
mber+0.016
loo+0.015
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.003
 usual-0.003
ro-0.002
Token play
Token ID711
Feature activation+6.91e-03

Pos logit contributions
 bank+0.016
 banks+0.014
 allowance+0.012
ro+0.011
 usual+0.010
Neg logit contributions
ww-0.033
www-0.030
mber-0.028
heart-0.028
ins-0.027
Token with
Token ID351
Feature activation+5.18e-03

Pos logit contributions
ww+0.013
www+0.011
ons+0.010
heart+0.010
?"+0.010
Neg logit contributions
 bank-0.011
 banks-0.011
 allowance-0.010
isc-0.009
ro-0.009
Token,
Token ID11
Feature activation-4.61e-03

Pos logit contributions
ww+0.001
www+0.001
ins+0.001
heart+0.001
ons+0.001
Neg logit contributions
 bank-0.001
 banks-0.001
 allowance-0.001
 bottom-0.001
 symp-0.001
Token fat
Token ID3735
Feature activation-2.65e-02

Pos logit contributions
 bank+0.006
 banks+0.005
 allowance+0.005
 symp+0.005
isc+0.004
Neg logit contributions
ww-0.010
www-0.009
heart-0.009
ons-0.008
ins-0.008
Token cat
Token ID3797
Feature activation-1.74e-02

Pos logit contributions
 bank+0.038
 banks+0.033
ro+0.032
 allowance+0.029
isc+0.028
Neg logit contributions
ww-0.054
www-0.048
heart-0.045
ons-0.045
ins-0.043
Token named
Token ID3706
Feature activation+4.88e-03

Pos logit contributions
 bank+0.027
 banks+0.024
ro+0.022
 allowance+0.021
 symp+0.020
Neg logit contributions
ww-0.035
www-0.031
heart-0.028
mber-0.028
loo-0.025
Token Wh
Token ID854
Feature activation-6.94e-02

Pos logit contributions
ww+0.008
www+0.007
?"+0.006
ons+0.006
heart+0.005
Neg logit contributions
 bank-0.010
 banks-0.009
 allowance-0.009
 symp-0.008
ro-0.008
Tokenisk
Token ID1984
Feature activation-1.44e-01

Pos logit contributions
 bank+0.084
 banks+0.078
 allowance+0.076
 contain+0.061
 symp+0.058
Neg logit contributions
ww-0.154
www-0.138
ons-0.135
imi-0.133
?"-0.132
Tokeners
Token ID364
Feature activation-1.26e-02

Pos logit contributions
 bank+0.269
 banks+0.259
 allowance+0.245
ro+0.228
isc+0.225
Neg logit contributions
ww-0.234
www-0.201
heart-0.178
mber-0.171
?"-0.169
Token.
Token ID13
Feature activation-5.54e-03

Pos logit contributions
 allowance+0.023
 banks+0.023
 bank+0.023
isc+0.021
urd+0.021
Neg logit contributions
?"-0.017
ww-0.017
?-0.017
ons-0.015
 course-0.015
Token Wh
Token ID854
Feature activation-6.79e-02

Pos logit contributions
 bank+0.009
 banks+0.009
 allowance+0.008
ately+0.008
 contain+0.008
Neg logit contributions
ww-0.010
www-0.008
?"-0.008
 my-0.007
ons-0.007
Tokenisk
Token ID1984
Feature activation-1.44e-01

Pos logit contributions
 bank+0.079
 banks+0.075
 allowance+0.072
 contain+0.063
 usual+0.061
Neg logit contributions
ww-0.154
www-0.137
ons-0.133
?"-0.130
imi-0.128
Tokeners
Token ID364
Feature activation-1.17e-02

Pos logit contributions
 bank+0.256
 banks+0.245
 allowance+0.228
ro+0.216
isc+0.209
Neg logit contributions
ww-0.244
www-0.212
heart-0.190
mber-0.182
?"-0.179
Token that
Token ID326
Feature activation-8.69e-03

Pos logit contributions
ww+0.009
www+0.008
heart+0.008
ins+0.008
ons+0.008
Neg logit contributions
 bank-0.005
 banks-0.005
 allowance-0.004
 usual-0.004
 symp-0.004
Token day
Token ID1110
Feature activation-1.03e-02

Pos logit contributions
 bank+0.015
 banks+0.014
 allowance+0.014
 usual+0.013
 symp+0.013
Neg logit contributions
ww-0.014
www-0.012
heart-0.012
ins-0.012
mber-0.011
Token on
Token ID319
Feature activation-1.06e-03

Pos logit contributions
 bank+0.020
 banks+0.020
 allowance+0.018
ro+0.017
isc+0.017
Neg logit contributions
ww-0.016
www-0.014
ons-0.012
?"-0.012
heart-0.011
Token,
Token ID11
Feature activation+5.75e-03

Pos logit contributions
 bank+0.002
 banks+0.002
 allowance+0.002
ro+0.001
isc+0.001
Neg logit contributions
ww-0.002
www-0.002
heart-0.002
ons-0.002
mber-0.002
Token Wh
Token ID854
Feature activation-6.83e-02

Pos logit contributions
ww+0.010
ons+0.008
www+0.008
 course+0.008
 my+0.008
Neg logit contributions
 banks-0.010
 bank-0.009
 spine-0.009
 contain-0.009
 symp-0.008
Tokenisk
Token ID1984
Feature activation-1.44e-01

Pos logit contributions
 bank+0.081
 banks+0.078
 allowance+0.070
 contain+0.063
 usual+0.063
Neg logit contributions
ww-0.158
www-0.139
heart-0.132
ons-0.132
imi-0.128
Tokeners
Token ID364
Feature activation-1.44e-02

Pos logit contributions
 bank+0.285
 banks+0.276
 allowance+0.265
isc+0.242
ro+0.241
Neg logit contributions
ww-0.218
www-0.185
heart-0.160
ons-0.160
mber-0.155
Token was
Token ID373
Feature activation-1.06e-03

Pos logit contributions
 bank+0.020
 banks+0.019
 allowance+0.018
ro+0.016
isc+0.015
Neg logit contributions
ww-0.030
www-0.027
heart-0.025
ons-0.024
mber-0.024
Token no
Token ID645
Feature activation+1.96e-02

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
 usual+0.001
 symp+0.001
Neg logit contributions
ww-0.002
www-0.002
heart-0.002
mber-0.002
ons-0.002
Token longer
Token ID2392
Feature activation-1.32e-03

Pos logit contributions
ww+0.045
www+0.040
heart+0.038
 course+0.037
?"+0.036
Neg logit contributions
 bank-0.024
 banks-0.024
 allowance-0.020
isc-0.020
 symp-0.018
Token lazy
Token ID16931
Feature activation-1.69e-02

Pos logit contributions
 bank+0.002
 banks+0.002
 allowance+0.002
ro+0.002
isc+0.001
Neg logit contributions
ww-0.003
www-0.002
heart-0.002
ons-0.002
mber-0.002
Token got
Token ID1392
Feature activation+1.00e-03

Pos logit contributions
 banks+0.022
 bank+0.021
 allowance+0.020
ro+0.020
uries+0.019
Neg logit contributions
ww-0.019
ons-0.016
www-0.016
?"-0.015
 course-0.015
Token back
Token ID736
Feature activation-1.47e-02

Pos logit contributions
ww+0.002
www+0.002
ons+0.002
?"+0.001
heart+0.001
Neg logit contributions
 bank-0.002
 banks-0.002
 allowance-0.001
ro-0.001
isc-0.001
Token inside
Token ID2641
Feature activation-2.25e-02

Pos logit contributions
 bank+0.020
 banks+0.019
 allowance+0.018
ro+0.015
isc+0.015
Neg logit contributions
ww-0.032
www-0.028
heart-0.026
mber-0.026
ons-0.025
Token,
Token ID11
Feature activation+1.03e-03

Pos logit contributions
 bank+0.040
 banks+0.039
 allowance+0.036
isc+0.033
ro+0.033
Neg logit contributions
ww-0.037
www-0.032
heart-0.030
ons-0.030
?"-0.029
Token Wh
Token ID854
Feature activation-6.62e-02

Pos logit contributions
ww+0.002
www+0.001
ons+0.001
 my+0.001
?"+0.001
Neg logit contributions
 banks-0.002
 bank-0.002
 allowance-0.002
ro-0.002
tted-0.002
Tokenisk
Token ID1984
Feature activation-1.44e-01

Pos logit contributions
 bank+0.088
 banks+0.087
 contain+0.083
 allowance+0.079
 usual+0.074
Neg logit contributions
ww-0.138
www-0.118
ons-0.116
imi-0.114
ins-0.113
Tokeners
Token ID364
Feature activation-1.24e-02

Pos logit contributions
 bank+0.266
 banks+0.255
 allowance+0.241
ro+0.225
isc+0.221
Neg logit contributions
ww-0.236
www-0.203
heart-0.180
?"-0.172
mber-0.172
Token saw
Token ID2497
Feature activation-6.89e-04

Pos logit contributions
 banks+0.021
 allowance+0.021
 bank+0.021
ro+0.020
isc+0.020
Neg logit contributions
ww-0.018
ons-0.017
www-0.016
?"-0.016
 course-0.015
Token a
Token ID257
Feature activation-8.63e-03

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
isc+0.001
ro+0.001
Neg logit contributions
ww-0.001
www-0.001
heart-0.001
mber-0.001
?"-0.001
Token teaspoon
Token ID22326
Feature activation+1.32e-02

Pos logit contributions
 bank+0.013
 banks+0.012
 allowance+0.012
ro+0.010
 usual+0.010
Neg logit contributions
ww-0.017
www-0.015
heart-0.014
ons-0.013
loo-0.013
Token on
Token ID319
Feature activation+5.53e-04

Pos logit contributions
ww+0.029
www+0.026
mber+0.024
heart+0.023
ons+0.022
Neg logit contributions
 bank-0.018
 banks-0.017
 allowance-0.015
ro-0.014
 symp-0.014
Token,
Token ID11
Feature activation+2.15e-03

Pos logit contributions
ww+0.055
www+0.051
ons+0.047
loo+0.047
heart+0.046
Neg logit contributions
 bank-0.033
 allowance-0.031
 banks-0.030
isc-0.027
 anymore-0.026
Token Lucy
Token ID22162
Feature activation+2.78e-03

Pos logit contributions
ww+0.004
www+0.004
ons+0.003
heart+0.003
loo+0.003
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.003
isc-0.003
 usual-0.002
Token!"
Token ID2474
Feature activation-1.16e-02

Pos logit contributions
ww+0.004
www+0.004
ons+0.003
loo+0.003
mber+0.003
Neg logit contributions
 bank-0.005
 banks-0.005
 allowance-0.004
isc-0.004
ro-0.004
Token said
Token ID531
Feature activation-1.28e-02

Pos logit contributions
 bank+0.017
 banks+0.016
 allowance+0.016
isc+0.015
 loudspe+0.014
Neg logit contributions
ww-0.023
www-0.020
loo-0.019
heart-0.018
ins-0.018
Token Wh
Token ID854
Feature activation-6.70e-02

Pos logit contributions
 banks+0.025
 bank+0.025
 allowance+0.022
ro+0.021
 symp+0.020
Neg logit contributions
ww-0.021
www-0.017
?"-0.016
heart-0.015
ons-0.015
Tokenisk
Token ID1984
Feature activation-1.44e-01

Pos logit contributions
 bank+0.081
 banks+0.077
 allowance+0.071
ro+0.061
isc+0.061
Neg logit contributions
ww-0.153
www-0.137
heart-0.126
ons-0.124
mber-0.123
Tokeners
Token ID364
Feature activation-1.08e-02

Pos logit contributions
 bank+0.245
 banks+0.233
 allowance+0.215
ro+0.211
tted+0.203
Neg logit contributions
ww-0.250
www-0.216
heart-0.194
?"-0.189
mber-0.184
Token,
Token ID11
Feature activation+2.24e-03

Pos logit contributions
 allowance+0.020
 banks+0.019
 bank+0.019
isc+0.017
ro+0.017
Neg logit contributions
ww-0.015
?"-0.013
ons-0.013
?-0.013
www-0.013
Token "
Token ID366
Feature activation-2.69e-02

Pos logit contributions
ww+0.005
www+0.004
heart+0.004
ons+0.004
loo+0.004
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.002
 symp-0.002
ro-0.002
TokenDo
Token ID5211
Feature activation-8.58e-03

Pos logit contributions
 bank+0.040
 banks+0.037
ro+0.037
 allowance+0.034
side+0.034
Neg logit contributions
ww-0.051
www-0.046
ons-0.043
loo-0.041
heart-0.041
Token you
Token ID345
Feature activation-1.14e-02

Pos logit contributions
 bank+0.020
 banks+0.020
 allowance+0.019
 usual+0.018
isc+0.018
Neg logit contributions
ww-0.009
www-0.007
heart-0.006
ons-0.006
loo-0.006
Token From
Token ID3574
Feature activation+4.64e-03

Pos logit contributions
 bank+0.012
 banks+0.011
 allowance+0.011
 usual+0.010
 contain+0.010
Neg logit contributions
ww-0.013
www-0.011
ons-0.010
?"-0.010
mber-0.010
Token then
Token ID788
Feature activation-6.01e-02

Pos logit contributions
ww+0.010
www+0.009
heart+0.009
ins+0.008
mber+0.008
Neg logit contributions
 bank-0.005
 banks-0.005
 allowance-0.005
 usual-0.004
late-0.004
Token on
Token ID319
Feature activation+1.93e-03

Pos logit contributions
 bank+0.109
 banks+0.105
 allowance+0.100
ro+0.091
isc+0.091
Neg logit contributions
ww-0.100
www-0.087
heart-0.077
ons-0.075
mber-0.074
Token,
Token ID11
Feature activation+4.30e-03

Pos logit contributions
ww+0.003
www+0.003
ons+0.002
?"+0.002
 my+0.002
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.003
isc-0.003
ro-0.003
Token Wh
Token ID854
Feature activation-6.54e-02

Pos logit contributions
ww+0.007
ons+0.006
www+0.005
 my+0.005
 course+0.005
Neg logit contributions
 banks-0.008
 bank-0.007
 contain-0.007
 spine-0.007
ured-0.007
Tokenisk
Token ID1984
Feature activation-1.44e-01

Pos logit contributions
 banks+0.085
 bank+0.085
 contain+0.077
 allowance+0.074
 usual+0.071
Neg logit contributions
ww-0.142
www-0.122
ons-0.118
heart-0.115
ins-0.114
Tokeners
Token ID364
Feature activation-1.23e-02

Pos logit contributions
 bank+0.277
 banks+0.267
 allowance+0.255
ro+0.234
isc+0.233
Neg logit contributions
ww-0.225
www-0.192
heart-0.168
ons-0.164
mber-0.162
Token tried
Token ID3088
Feature activation+1.82e-02

Pos logit contributions
 banks+0.019
 bank+0.019
 allowance+0.018
isc+0.016
 spine+0.016
Neg logit contributions
ww-0.022
ons-0.019
www-0.019
?"-0.018
 course-0.018
Token to
Token ID284
Feature activation-5.82e-03

Pos logit contributions
ww+0.038
www+0.034
ons+0.032
heart+0.032
?"+0.031
Neg logit contributions
 bank-0.023
 banks-0.023
 allowance-0.021
isc-0.020
ro-0.018
Token be
Token ID307
Feature activation-1.48e-02

Pos logit contributions
 bank+0.007
 banks+0.007
 allowance+0.006
isc+0.005
ro+0.005
Neg logit contributions
ww-0.013
www-0.012
heart-0.011
ons-0.011
?"-0.011
Token less
Token ID1342
Feature activation+2.31e-02

Pos logit contributions
 bank+0.021
 banks+0.020
 allowance+0.019
 injuries+0.016
 usual+0.016
Neg logit contributions
ww-0.031
www-0.028
heart-0.025
mber-0.025
loo-0.025
Token a
Token ID257
Feature activation-8.15e-03

Pos logit contributions
ww+0.015
www+0.013
heart+0.012
ons+0.012
?"+0.012
Neg logit contributions
 bank-0.014
 banks-0.013
 allowance-0.013
ro-0.011
isc-0.011
Token long
Token ID890
Feature activation-1.75e-02

Pos logit contributions
 banks+0.012
 bank+0.011
 allowance+0.010
isc+0.010
 symp+0.010
Neg logit contributions
ww-0.017
www-0.014
mber-0.013
heart-0.012
?"-0.012
Token time
Token ID640
Feature activation-1.15e-02

Pos logit contributions
 bank+0.028
 banks+0.026
 allowance+0.025
ro+0.023
isc+0.022
Neg logit contributions
ww-0.034
www-0.030
heart-0.027
mber-0.026
ons-0.026
Token.
Token ID13
Feature activation-5.04e-03

Pos logit contributions
 bank+0.014
 banks+0.014
 allowance+0.013
ro+0.011
isc+0.011
Neg logit contributions
ww-0.026
www-0.023
heart-0.021
mber-0.021
ons-0.021
Token Wh
Token ID854
Feature activation-6.68e-02

Pos logit contributions
 banks+0.008
 bank+0.008
 allowance+0.008
 usual+0.007
 contain+0.007
Neg logit contributions
ww-0.009
www-0.008
?"-0.007
ons-0.007
 my-0.006
Tokenisk
Token ID1984
Feature activation-1.44e-01

Pos logit contributions
 bank+0.080
 banks+0.078
 allowance+0.073
 contain+0.069
 usual+0.069
Neg logit contributions
ww-0.149
www-0.131
ons-0.124
heart-0.124
ins-0.120
Tokeners
Token ID364
Feature activation-1.19e-02

Pos logit contributions
 bank+0.279
 banks+0.270
 allowance+0.258
ro+0.236
isc+0.236
Neg logit contributions
ww-0.222
www-0.189
heart-0.165
ons-0.162
mber-0.159
Token learned
Token ID4499
Feature activation-3.71e-02

Pos logit contributions
 banks+0.019
 bank+0.018
 allowance+0.018
isc+0.017
ro+0.017
Neg logit contributions
ww-0.020
www-0.018
ons-0.017
?"-0.017
heart-0.016
Token that
Token ID326
Feature activation-1.20e-02

Pos logit contributions
 bank+0.068
 banks+0.067
 allowance+0.063
ro+0.058
isc+0.058
Neg logit contributions
ww-0.061
www-0.052
heart-0.046
?"-0.045
ons-0.045
Token sometimes
Token ID3360
Feature activation+2.01e-02

Pos logit contributions
 bank+0.018
 banks+0.017
 allowance+0.017
 usual+0.015
ro+0.015
Neg logit contributions
ww-0.023
www-0.021
heart-0.019
mber-0.019
ons-0.018
Token it
Token ID340
Feature activation+3.86e-03

Pos logit contributions
ww+0.035
www+0.031
mber+0.028
heart+0.027
loo+0.027
Neg logit contributions
 bank-0.035
 banks-0.033
 allowance-0.033
 seem-0.029
 usual-0.028
Token,
Token ID11
Feature activation-6.70e-04

Pos logit contributions
ww+0.007
www+0.007
ins+0.007
heart+0.006
mber+0.006
Neg logit contributions
 bank-0.005
 allowance-0.005
 banks-0.005
isc-0.004
 symp-0.004
Token fluffy
Token ID39145
Feature activation+1.42e-02

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
ro+0.001
isc+0.001
Neg logit contributions
ww-0.001
www-0.001
heart-0.001
ons-0.001
mber-0.001
Token cat
Token ID3797
Feature activation-1.60e-02

Pos logit contributions
ww+0.031
www+0.028
ons+0.026
ins+0.026
heart+0.026
Neg logit contributions
 bank-0.019
 banks-0.017
 allowance-0.016
ro-0.015
isc-0.014
Token named
Token ID3706
Feature activation+9.01e-03

Pos logit contributions
 bank+0.027
 banks+0.025
 allowance+0.023
ro+0.022
isc+0.021
Neg logit contributions
ww-0.029
www-0.026
heart-0.024
mber-0.023
loo-0.022
Token Wh
Token ID854
Feature activation-6.63e-02

Pos logit contributions
ww+0.016
www+0.014
heart+0.012
?"+0.012
mber+0.012
Neg logit contributions
 bank-0.016
 banks-0.015
 allowance-0.014
 symp-0.013
ro-0.012
Tokenisk
Token ID1984
Feature activation-1.44e-01

Pos logit contributions
 bank+0.083
 banks+0.077
 allowance+0.076
 contain+0.059
urd+0.058
Neg logit contributions
ww-0.146
www-0.132
heart-0.127
imi-0.124
?"-0.123
Tokeners
Token ID364
Feature activation-9.23e-03

Pos logit contributions
 bank+0.277
 banks+0.268
 allowance+0.255
ro+0.234
isc+0.234
Neg logit contributions
ww-0.224
www-0.191
heart-0.167
ons-0.163
mber-0.161
Token,
Token ID11
Feature activation-1.28e-03

Pos logit contributions
 banks+0.015
 bank+0.015
 allowance+0.014
urd+0.013
isc+0.013
Neg logit contributions
ww-0.014
?"-0.013
?-0.013
www-0.012
ons-0.012
Token who
Token ID508
Feature activation+9.25e-03

Pos logit contributions
 bank+0.002
 banks+0.002
 allowance+0.002
ro+0.002
isc+0.002
Neg logit contributions
ww-0.003
www-0.002
heart-0.002
ons-0.002
mber-0.002
Token liked
Token ID8288
Feature activation-1.39e-02

Pos logit contributions
ww+0.019
www+0.017
heart+0.016
mber+0.015
loo+0.015
Neg logit contributions
 bank-0.013
 banks-0.012
 allowance-0.012
isc-0.010
ro-0.010
Token to
Token ID284
Feature activation-8.18e-03

Pos logit contributions
 bank+0.015
 banks+0.015
 allowance+0.013
ro+0.011
isc+0.011
Neg logit contributions
ww-0.033
www-0.030
heart-0.027
ons-0.027
?"-0.027
Token looks
Token ID3073
Feature activation+1.59e-02

Pos logit contributions
 bank+0.004
 banks+0.003
 seem+0.003
 allowance+0.002
 find+0.002
Neg logit contributions
ww-0.018
loo-0.017
www-0.017
ull-0.016
mber-0.016
Token very
Token ID845
Feature activation+3.94e-03

Pos logit contributions
ww+0.034
www+0.030
heart+0.027
?"+0.027
ons+0.027
Neg logit contributions
 bank-0.022
 banks-0.021
 allowance-0.019
ro-0.017
isc-0.017
Token nice
Token ID3621
Feature activation+3.18e-03

Pos logit contributions
ww+0.007
www+0.007
ons+0.006
heart+0.006
loo+0.006
Neg logit contributions
 bank-0.006
 banks-0.006
 allowance-0.006
 usual-0.005
ro-0.005
Token,
Token ID11
Feature activation+6.12e-03

Pos logit contributions
ww+0.007
www+0.006
loo+0.006
imi+0.006
Charlie+0.006
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.003
ro-0.003
 until-0.003
Token sweet
Token ID6029
Feature activation+2.30e-02

Pos logit contributions
ww+0.011
www+0.010
loo+0.010
ons+0.010
P+0.009
Neg logit contributions
 bank-0.009
 banks-0.008
 allowance-0.008
ro-0.008
 symp-0.007
Tokenheart
Token ID11499
Feature activation+1.11e-01

Pos logit contributions
ww+0.025
www+0.020
loo+0.020
ined+0.019
Charlie+0.019
Neg logit contributions
 bank-0.046
 banks-0.044
ro-0.043
isc-0.041
 anymore-0.041
Token,"
Token ID553
Feature activation-1.16e-04

Pos logit contributions
ww+0.245
www+0.216
mber+0.203
ons+0.202
loo+0.201
Neg logit contributions
 bank-0.132
 banks-0.117
 allowance-0.115
 anymore-0.103
ro-0.102
Token she
Token ID673
Feature activation-7.82e-03

Pos logit contributions
 allowance+0.000
 bank+0.000
 buy+0.000
 tum+0.000
 until+0.000
Neg logit contributions
ww-0.000
loo-0.000
ile-0.000
asc-0.000
www-0.000
Token said
Token ID531
Feature activation-4.23e-03

Pos logit contributions
 bank+0.013
 banks+0.013
 allowance+0.012
isc+0.012
 symp+0.011
Neg logit contributions
ww-0.014
www-0.011
loo-0.011
ons-0.010
 course-0.010
Token.
Token ID13
Feature activation+1.97e-03

Pos logit contributions
 banks+0.008
 bank+0.008
 allowance+0.007
isc+0.006
ro+0.006
Neg logit contributions
ww-0.006
heart-0.006
?"-0.006
www-0.006
?-0.005
Token
Token ID198
Feature activation+5.54e-03

Pos logit contributions
ww+0.004
www+0.004
loo+0.004
heart+0.004
ons+0.004
Neg logit contributions
 bank-0.002
 banks-0.002
 allowance-0.002
ro-0.002
isc-0.002
Token says
Token ID1139
Feature activation-2.39e-03

Pos logit contributions
 bank+0.020
 banks+0.020
 allowance+0.019
ro+0.018
 symp+0.017
Neg logit contributions
ww-0.013
www-0.010
heart-0.008
loo-0.008
mber-0.008
Token.
Token ID13
Feature activation+2.20e-03

Pos logit contributions
 bank+0.005
 banks+0.005
isc+0.004
 allowance+0.004
urd+0.004
Neg logit contributions
ww-0.003
?-0.003
?"-0.003
ons-0.003
heart-0.002
Token
Token ID198
Feature activation+5.63e-03

Pos logit contributions
ww+0.004
www+0.003
heart+0.003
ons+0.003
mber+0.003
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.003
ro-0.003
isc-0.003
Token
Token ID198
Feature activation+5.97e-03

Pos logit contributions
ww+0.010
www+0.009
?"+0.008
ons+0.008
mber+0.008
Neg logit contributions
 bank-0.009
 banks-0.009
 allowance-0.008
isc-0.007
ro-0.007
Token"
Token ID1
Feature activation-3.68e-03

Pos logit contributions
ww+0.008
www+0.007
heart+0.006
ons+0.006
loo+0.006
Neg logit contributions
 bank-0.013
 banks-0.012
 allowance-0.012
ro-0.011
isc-0.011
TokenNo
Token ID2949
Feature activation+6.54e-02

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.006
ro+0.006
 symp+0.005
Neg logit contributions
ww-0.006
www-0.005
heart-0.005
ons-0.005
loo-0.005
Token,
Token ID11
Feature activation+5.28e-03

Pos logit contributions
ww+0.148
www+0.132
mber+0.129
ins+0.127
loo+0.127
Neg logit contributions
 bank-0.072
 banks-0.066
 allowance-0.064
 anymore-0.058
 bottom-0.053
Token Sara
Token ID24799
Feature activation-1.05e-02

Pos logit contributions
ww+0.009
www+0.008
heart+0.007
ons+0.007
mber+0.007
Neg logit contributions
 bank-0.009
 banks-0.008
 allowance-0.008
ro-0.007
isc-0.007
Token!
Token ID0
Feature activation+8.89e-03

Pos logit contributions
 bank+0.012
 banks+0.011
 allowance+0.010
isc+0.009
ro+0.009
Neg logit contributions
ww-0.023
www-0.021
mber-0.021
loo-0.020
heart-0.019
Token This
Token ID770
Feature activation+1.69e-02

Pos logit contributions
ww+0.015
www+0.013
heart+0.012
ons+0.012
mber+0.012
Neg logit contributions
 bank-0.015
 banks-0.015
 allowance-0.014
ro-0.013
isc-0.013
Token is
Token ID318
Feature activation+1.65e-02

Pos logit contributions
ww+0.032
heart+0.030
www+0.029
mber+0.027
ins+0.027
Neg logit contributions
 bank-0.027
 allowance-0.024
 banks-0.023
ork-0.022
ro-0.021
Token find
Token ID1064
Feature activation-1.44e-02

Pos logit contributions
 bank+0.014
 banks+0.013
 allowance+0.012
ro+0.011
 usual+0.011
Neg logit contributions
ww-0.016
www-0.014
heart-0.012
mber-0.012
ons-0.012
Token it
Token ID340
Feature activation+4.91e-03

Pos logit contributions
 bank+0.026
 banks+0.024
 allowance+0.024
 any+0.023
 find+0.022
Neg logit contributions
ww-0.023
www-0.020
mber-0.019
loo-0.017
heart-0.017
Token?"
Token ID1701
Feature activation+2.95e-02

Pos logit contributions
ww+0.003
www+0.002
heart+0.001
mber+0.001
ons+0.001
Neg logit contributions
 bank-0.014
 banks-0.014
 allowance-0.013
ro-0.012
 usual-0.012
Token The
Token ID383
Feature activation-1.01e-02

Pos logit contributions
ww+0.064
www+0.057
heart+0.052
ons+0.051
loo+0.051
Neg logit contributions
 bank-0.039
 banks-0.037
 allowance-0.034
ro-0.031
 symp-0.030
Token all
Token ID477
Feature activation+1.73e-02

Pos logit contributions
 bank+0.015
 banks+0.014
 bottom+0.011
 allowance+0.011
 anymore+0.010
Neg logit contributions
ww-0.022
www-0.019
ons-0.018
heart-0.017
mber-0.017
Tokenigator
Token ID23823
Feature activation+8.42e-02

Pos logit contributions
ww+0.023
www+0.019
prise+0.018
corn+0.017
ins+0.016
Neg logit contributions
 bank-0.035
 banks-0.032
 contain-0.030
ro-0.030
tered-0.030
Token said
Token ID531
Feature activation-3.15e-03

Pos logit contributions
ww+0.138
www+0.118
heart+0.104
ons+0.101
mber+0.100
Neg logit contributions
 bank-0.158
 banks-0.151
 allowance-0.143
ro-0.132
 symp-0.130
Token,
Token ID11
Feature activation+3.37e-03

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.005
isc+0.005
ro+0.005
Neg logit contributions
ww-0.005
www-0.004
heart-0.004
?"-0.004
ons-0.004
Token "
Token ID366
Feature activation-1.68e-02

Pos logit contributions
ww+0.006
www+0.005
heart+0.005
ons+0.005
mber+0.005
Neg logit contributions
 bank-0.005
 banks-0.005
 allowance-0.005
isc-0.004
ro-0.004
TokenYes
Token ID5297
Feature activation+3.63e-02

Pos logit contributions
 bank+0.030
 banks+0.029
 allowance+0.028
ro+0.025
isc+0.025
Neg logit contributions
ww-0.028
www-0.024
heart-0.022
ons-0.021
?"-0.021
Token,
Token ID11
Feature activation+1.53e-03

Pos logit contributions
ww+0.076
www+0.067
mber+0.062
ons+0.061
loo+0.061
Neg logit contributions
 bank-0.048
 banks-0.045
 allowance-0.043
 symp-0.038
isc-0.038
TokenThen
Token ID6423
Feature activation+9.97e-04

Pos logit contributions
ww+0.005
www+0.005
heart+0.004
ons+0.004
?"+0.004
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.003
ro-0.003
isc-0.003
Token,
Token ID11
Feature activation+6.62e-03

Pos logit contributions
ww+0.002
www+0.002
heart+0.002
mber+0.002
ins+0.002
Neg logit contributions
 bank-0.001
 banks-0.001
 allowance-0.001
 usual-0.001
 symp-0.001
Token a
Token ID257
Feature activation-1.98e-03

Pos logit contributions
ww+0.013
www+0.012
heart+0.011
ons+0.011
mber+0.011
Neg logit contributions
 bank-0.010
 banks-0.009
 allowance-0.009
 usual-0.008
ro-0.007
Token kind
Token ID1611
Feature activation-8.72e-03

Pos logit contributions
 bank+0.003
 banks+0.002
 allowance+0.002
 usual+0.002
ro+0.002
Neg logit contributions
ww-0.004
www-0.003
ons-0.003
heart-0.003
ins-0.003
Token mail
Token ID6920
Feature activation-1.10e-02

Pos logit contributions
 bank+0.014
ro+0.012
 banks+0.012
 allowance+0.012
isc+0.012
Neg logit contributions
ww-0.016
www-0.014
ons-0.013
ins-0.012
heart-0.012
Tokenman
Token ID805
Feature activation+6.76e-02

Pos logit contributions
 bank+0.023
 allowance+0.021
 banks+0.021
isc+0.020
ro+0.020
Neg logit contributions
ww-0.015
www-0.013
heart-0.011
mber-0.010
imi-0.010
Token came
Token ID1625
Feature activation-4.93e-03

Pos logit contributions
ww+0.139
www+0.125
mber+0.112
heart+0.109
imi+0.108
Neg logit contributions
 bank-0.101
 banks-0.088
 allowance-0.086
ked-0.076
 buy-0.076
Token by
Token ID416
Feature activation-3.26e-02

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.005
ro+0.005
isc+0.004
Neg logit contributions
ww-0.011
www-0.010
heart-0.009
mber-0.009
ons-0.009
Token.
Token ID13
Feature activation+2.55e-03

Pos logit contributions
 bank+0.049
 banks+0.047
 allowance+0.044
isc+0.041
ro+0.038
Neg logit contributions
ww-0.063
www-0.056
?"-0.052
heart-0.052
ons-0.051
Token The
Token ID383
Feature activation-9.95e-03

Pos logit contributions
ww+0.006
www+0.005
heart+0.005
ons+0.004
mber+0.004
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.003
ro-0.003
isc-0.003
Token mail
Token ID6920
Feature activation-1.08e-02

Pos logit contributions
 bank+0.018
 banks+0.018
 allowance+0.017
ro+0.015
isc+0.015
Neg logit contributions
ww-0.017
www-0.014
heart-0.013
ons-0.012
mber-0.012
Token Andy
Token ID12382
Feature activation+3.35e-02

Pos logit contributions
 bank+0.010
 banks+0.010
 allowance+0.009
isc+0.008
ro+0.008
Neg logit contributions
ww-0.013
www-0.011
heart-0.011
?"-0.011
ons-0.010
Token's
Token ID338
Feature activation+3.95e-03

Pos logit contributions
ww+0.062
www+0.055
heart+0.052
ons+0.052
?"+0.050
Neg logit contributions
 bank-0.048
 banks-0.048
 allowance-0.046
isc-0.041
ro-0.040
Token picture
Token ID4286
Feature activation+1.95e-02

Pos logit contributions
ww+0.007
www+0.006
heart+0.006
ons+0.005
?"+0.005
Neg logit contributions
 bank-0.006
 banks-0.006
 allowance-0.006
ro-0.005
isc-0.005
Token!
Token ID0
Feature activation+1.15e-02

Pos logit contributions
ww+0.043
www+0.039
mber+0.035
heart+0.035
?"+0.034
Neg logit contributions
 bank-0.025
 banks-0.023
 allowance-0.022
ro-0.020
isc-0.019
Token
Token ID198
Feature activation-2.03e-03

Pos logit contributions
ww+0.028
www+0.025
w+0.024
 course+0.024
ons+0.023
Neg logit contributions
 bank-0.011
 banks-0.010
isc-0.010
ro-0.008
urd-0.008
TokenAndy
Token ID35314
Feature activation+6.74e-02

Pos logit contributions
tted+0.003
 banks+0.003
 bank+0.003
side+0.003
urd+0.003
Neg logit contributions
ww-0.003
heart-0.003
 yours-0.003
www-0.003
ries-0.003
Token looked
Token ID3114
Feature activation-5.82e-03

Pos logit contributions
ww+0.138
www+0.121
heart+0.109
loo+0.109
mber+0.107
Neg logit contributions
 bank-0.100
 banks-0.094
 allowance-0.086
ro-0.079
 symp-0.078
Token at
Token ID379
Feature activation+2.50e-02

Pos logit contributions
 bank+0.009
 banks+0.009
 allowance+0.008
ro+0.008
isc+0.008
Neg logit contributions
ww-0.011
www-0.010
heart-0.009
?"-0.009
ons-0.008
Token the
Token ID262
Feature activation+1.29e-02

Pos logit contributions
ww+0.045
www+0.040
heart+0.036
ons+0.035
?"+0.035
Neg logit contributions
 bank-0.042
 banks-0.040
 allowance-0.038
ro-0.034
isc-0.034
Token freshly
Token ID29026
Feature activation-2.95e-02

Pos logit contributions
ww+0.022
www+0.019
heart+0.017
ons+0.017
?"+0.016
Neg logit contributions
 bank-0.023
 banks-0.022
 allowance-0.021
ro-0.019
isc-0.019
Token printed
Token ID10398
Feature activation-9.00e-03

Pos logit contributions
 bank+0.048
 banks+0.045
 allowance+0.042
ro+0.038
 usual+0.037
Neg logit contributions
ww-0.055
www-0.048
heart-0.045
mber-0.043
?"-0.041
Token believe
Token ID1975
Feature activation+6.61e-03

Pos logit contributions
?"+0.020
?+0.019
ww+0.019
www+0.018
ull+0.017
Neg logit contributions
 banks-0.019
 bank-0.019
isc-0.017
 allowance-0.017
side-0.017
Token it
Token ID340
Feature activation+1.04e-02

Pos logit contributions
ww+0.012
www+0.011
ons+0.009
mber+0.009
heart+0.009
Neg logit contributions
 bank-0.011
 banks-0.010
 allowance-0.010
 symp-0.010
ro-0.009
Token.
Token ID13
Feature activation+2.26e-03

Pos logit contributions
ww+0.021
www+0.019
heart+0.017
ons+0.017
?"+0.017
Neg logit contributions
 bank-0.015
 banks-0.014
 allowance-0.013
isc-0.012
ro-0.012
Token He
Token ID679
Feature activation+8.12e-03

Pos logit contributions
ww+0.005
www+0.004
heart+0.004
ons+0.004
mber+0.003
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.003
ro-0.003
 symp-0.003
Token took
Token ID1718
Feature activation+5.79e-03

Pos logit contributions
ww+0.017
www+0.015
heart+0.014
loo+0.013
ons+0.013
Neg logit contributions
 bank-0.012
 banks-0.011
 allowance-0.010
ro-0.010
 symp-0.009
Token the
Token ID262
Feature activation+1.59e-02

Pos logit contributions
ww+0.011
www+0.009
heart+0.008
ons+0.008
?"+0.008
Neg logit contributions
 bank-0.010
 banks-0.009
 allowance-0.009
ro-0.008
isc-0.008
Token ring
Token ID5858
Feature activation+7.25e-03

Pos logit contributions
ww+0.026
www+0.022
heart+0.020
mber+0.019
ons+0.019
Neg logit contributions
 bank-0.030
 banks-0.029
 allowance-0.027
ro-0.025
isc-0.025
Token from
Token ID422
Feature activation-3.73e-02

Pos logit contributions
ww+0.015
www+0.013
heart+0.012
ons+0.012
?"+0.012
Neg logit contributions
 bank-0.010
 banks-0.010
 allowance-0.009
isc-0.008
ro-0.008
Token Anna
Token ID11735
Feature activation+9.61e-03

Pos logit contributions
 bank+0.067
 banks+0.064
 allowance+0.061
ro+0.056
 usual+0.056
Neg logit contributions
ww-0.066
www-0.057
heart-0.050
ons-0.048
mber-0.048
Token and
Token ID290
Feature activation+7.00e-03

Pos logit contributions
ww+0.017
www+0.015
ons+0.015
?"+0.014
heart+0.014
Neg logit contributions
 bank-0.014
 banks-0.014
 allowance-0.013
urd-0.012
isc-0.012
Token looked
Token ID3114
Feature activation-1.33e-03

Pos logit contributions
ww+0.014
www+0.013
heart+0.012
loo+0.011
mber+0.011
Neg logit contributions
 bank-0.011
 banks-0.010
 allowance-0.010
ro-0.009
ked-0.008
Token are
Token ID389
Feature activation-1.09e-02

Pos logit contributions
ww+0.011
www+0.010
?"+0.009
ons+0.009
?+0.008
Neg logit contributions
 bank-0.009
 banks-0.009
 allowance-0.008
 symp-0.008
ro-0.008
Token successful
Token ID4388
Feature activation-1.63e-02

Pos logit contributions
 bank+0.014
 allowance+0.013
 banks+0.013
 properly+0.011
 usual+0.011
Neg logit contributions
ww-0.024
www-0.022
heart-0.021
mber-0.021
loo-0.019
Token.
Token ID13
Feature activation-1.22e-02

Pos logit contributions
 bank+0.024
 banks+0.023
 allowance+0.022
ro+0.019
 anymore+0.018
Neg logit contributions
ww-0.033
www-0.029
mber-0.027
heart-0.027
ons-0.026
Token You
Token ID921
Feature activation+7.50e-03

Pos logit contributions
 bank+0.026
 banks+0.025
 allowance+0.023
ro+0.022
isc+0.022
Neg logit contributions
ww-0.017
www-0.014
heart-0.012
?"-0.012
ons-0.012
Token are
Token ID389
Feature activation-1.08e-02

Pos logit contributions
ww+0.016
www+0.014
heart+0.013
ons+0.013
mber+0.013
Neg logit contributions
 bank-0.010
 banks-0.010
 allowance-0.009
ro-0.008
isc-0.008
Token mean
Token ID1612
Feature activation+2.55e-02

Pos logit contributions
 bank+0.014
 allowance+0.013
 banks+0.012
 usual+0.011
 properly+0.011
Neg logit contributions
ww-0.024
heart-0.021
www-0.021
mber-0.020
loo-0.019
Token."
Token ID526
Feature activation-1.57e-02

Pos logit contributions
ww+0.059
www+0.054
mber+0.050
ons+0.048
heart+0.048
Neg logit contributions
 bank-0.028
 banks-0.027
 allowance-0.025
 anymore-0.024
ro-0.024
Token
Token ID198
Feature activation-5.02e-03

Pos logit contributions
 bank+0.027
 banks+0.026
 allowance+0.024
isc+0.022
ro+0.022
Neg logit contributions
ww-0.027
www-0.024
?"-0.022
ons-0.021
mber-0.021
Token
Token ID198
Feature activation-3.55e-03

Pos logit contributions
 bank+0.008
 banks+0.008
 allowance+0.007
ro+0.006
isc+0.006
Neg logit contributions
ww-0.010
www-0.008
ons-0.008
?"-0.008
heart-0.008
TokenMax
Token ID11518
Feature activation-1.59e-02

Pos logit contributions
 bank+0.005
 banks+0.005
 allowance+0.005
ro+0.004
tted+0.004
Neg logit contributions
ww-0.007
heart-0.006
www-0.006
loo-0.006
mber-0.006
Token cannot
Token ID2314
Feature activation+3.06e-02

Pos logit contributions
 bank+0.028
 banks+0.027
 allowance+0.025
ro+0.023
 symp+0.023
Neg logit contributions
ww-0.028
www-0.024
heart-0.022
mber-0.021
ons-0.021
Token I
Token ID314
Feature activation+2.06e-02

Pos logit contributions
ww+0.005
ons+0.004
www+0.004
w+0.004
loo+0.004
Neg logit contributions
 bank-0.004
 banks-0.003
isc-0.003
 allowance-0.003
ro-0.003
Token wish
Token ID4601
Feature activation-6.10e-04

Pos logit contributions
ww+0.043
www+0.039
heart+0.035
?"+0.035
ons+0.034
Neg logit contributions
 bank-0.028
 banks-0.027
 allowance-0.025
ro-0.022
isc-0.022
Token I
Token ID314
Feature activation+2.01e-02

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
 usual+0.001
isc+0.001
Neg logit contributions
ww-0.001
www-0.001
mber-0.001
heart-0.001
ons-0.001
Token had
Token ID550
Feature activation-5.29e-03

Pos logit contributions
ww+0.046
www+0.041
heart+0.038
ons+0.037
?"+0.037
Neg logit contributions
 bank-0.024
 banks-0.023
 allowance-0.021
ro-0.018
isc-0.018
Token some
Token ID617
Feature activation-3.96e-03

Pos logit contributions
 bank+0.007
 banks+0.006
 allowance+0.006
 usual+0.006
 injuries+0.005
Neg logit contributions
ww-0.011
www-0.010
heart-0.010
loo-0.009
mber-0.009
Token juice
Token ID13135
Feature activation-4.95e-03

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.006
 usual+0.005
ro+0.005
Neg logit contributions
ww-0.007
www-0.007
mber-0.006
heart-0.006
very-0.006
Token.
Token ID13
Feature activation-1.40e-03

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.005
ro+0.005
 usual+0.005
Neg logit contributions
ww-0.011
www-0.010
heart-0.009
ons-0.009
mber-0.009
Tokenâ
Token ID22940
Feature activation+3.66e-02

Pos logit contributions
 bank+0.002
 banks+0.002
 allowance+0.002
isc+0.002
ro+0.002
Neg logit contributions
ww-0.003
ons-0.002
www-0.002
loo-0.002
ins-0.002
Token
Token ID26391
Feature activation-3.00e-02

Pos logit contributions
ww+0.076
www+0.067
heart+0.062
ons+0.062
mber+0.061
Neg logit contributions
 bank-0.049
 banks-0.047
 allowance-0.041
ro-0.040
isc-0.040
Token Tim
Token ID5045
Feature activation+1.19e-02

Pos logit contributions
 bank+0.045
 banks+0.043
 allowance+0.040
isc+0.037
ro+0.036
Neg logit contributions
ww-0.058
www-0.051
heart-0.049
mber-0.046
loo-0.045
Token thought
Token ID1807
Feature activation+3.93e-03

Pos logit contributions
ww+0.024
www+0.020
loo+0.019
ons+0.018
heart+0.018
Neg logit contributions
 bank-0.019
 banks-0.017
 allowance-0.016
isc-0.015
ro-0.015
Token.
Token ID13
Feature activation-9.49e-03

Pos logit contributions
 bank+0.007
 banks+0.007
 allowance+0.006
ro+0.006
isc+0.005
Neg logit contributions
ww-0.011
www-0.010
heart-0.009
ons-0.009
mber-0.009
Token You
Token ID921
Feature activation+8.68e-03

Pos logit contributions
 bank+0.017
 banks+0.017
 allowance+0.016
isc+0.016
ro+0.016
Neg logit contributions
ww-0.015
www-0.013
heart-0.012
ons-0.011
mber-0.011
Token are
Token ID389
Feature activation-1.26e-02

Pos logit contributions
ww+0.017
www+0.015
?"+0.014
ons+0.014
heart+0.014
Neg logit contributions
 bank-0.013
 banks-0.012
 allowance-0.011
 symp-0.010
ro-0.010
Token making
Token ID1642
Feature activation+9.03e-03

Pos logit contributions
 bank+0.014
 banks+0.012
 allowance+0.012
 usual+0.011
 find+0.010
Neg logit contributions
ww-0.030
www-0.027
heart-0.027
loo-0.025
mber-0.025
Token me
Token ID502
Feature activation-4.35e-03

Pos logit contributions
ww+0.016
www+0.015
loo+0.013
mber+0.013
heart+0.012
Neg logit contributions
 bank-0.015
 banks-0.015
 allowance-0.014
 symp-0.012
 usual-0.012
Token happy
Token ID3772
Feature activation-6.02e-03

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.005
ro+0.005
isc+0.005
Neg logit contributions
ww-0.009
www-0.008
heart-0.008
ons-0.007
mber-0.007
Token.
Token ID13
Feature activation-1.09e-02

Pos logit contributions
 bank+0.006
 banks+0.006
 anymore+0.005
 allowance+0.005
ro+0.005
Neg logit contributions
ww-0.015
www-0.014
mber-0.013
ons-0.012
Charlie-0.012
Token And
Token ID843
Feature activation+2.92e-03

Pos logit contributions
 bank+0.020
 allowance+0.019
 banks+0.019
isc+0.019
ro+0.018
Neg logit contributions
ww-0.016
www-0.014
heart-0.013
ons-0.012
mber-0.012
Token you
Token ID345
Feature activation-4.70e-03

Pos logit contributions
ww+0.004
www+0.003
loo+0.003
ons+0.003
heart+0.003
Neg logit contributions
 bank-0.006
 allowance-0.006
 banks-0.006
ro-0.005
 usual-0.005
Token are
Token ID389
Feature activation-1.29e-02

Pos logit contributions
 bank+0.007
 banks+0.007
 allowance+0.007
 symp+0.006
isc+0.006
Neg logit contributions
ww-0.009
www-0.008
?"-0.007
ons-0.007
heart-0.007
Token making
Token ID1642
Feature activation+8.34e-03

Pos logit contributions
 bank+0.012
 allowance+0.010
 banks+0.010
 find+0.010
 usual+0.010
Neg logit contributions
ww-0.031
www-0.029
heart-0.028
loo-0.027
mber-0.026
Token for
Token ID329
Feature activation+1.56e-02

Pos logit contributions
 bank+0.000
 allowance+0.000
 banks+0.000
 symp+0.000
 until+0.000
Neg logit contributions
ww-0.001
www-0.001
ons-0.001
mber-0.001
heart-0.001
Token the
Token ID262
Feature activation+1.02e-02

Pos logit contributions
ww+0.031
www+0.028
heart+0.028
mber+0.027
loo+0.025
Neg logit contributions
 bank-0.021
 injuries-0.019
 banks-0.019
 allowance-0.018
 separate-0.018
Token fun
Token ID1257
Feature activation+6.47e-03

Pos logit contributions
ww+0.020
www+0.018
mber+0.017
heart+0.016
ons+0.016
Neg logit contributions
 bank-0.016
 banks-0.015
 allowance-0.015
 usual-0.013
 bottom-0.013
Token,"
Token ID553
Feature activation-5.13e-04

Pos logit contributions
ww+0.012
mber+0.012
www+0.011
P+0.011
Charlie+0.011
Neg logit contributions
 bank-0.008
 banks-0.007
 anymore-0.007
 allowance-0.007
 until-0.006
Token Sam
Token ID3409
Feature activation+1.52e-02

Pos logit contributions
 allowance+0.001
 bank+0.001
 banks+0.001
 usual+0.001
 symp+0.001
Neg logit contributions
ww-0.001
www-0.001
heart-0.001
mber-0.001
ons-0.001
Token says
Token ID1139
Feature activation-8.39e-03

Pos logit contributions
ww+0.028
www+0.024
loo+0.020
heart+0.020
mber+0.019
Neg logit contributions
 bank-0.029
 banks-0.028
 allowance-0.026
 find-0.023
 symp-0.023
Token.
Token ID13
Feature activation-5.42e-03

Pos logit contributions
 bank+0.013
 banks+0.013
 allowance+0.011
isc+0.010
ro+0.010
Neg logit contributions
ww-0.016
www-0.014
?"-0.013
ons-0.013
heart-0.013
Token
Token ID198
Feature activation-3.52e-03

Pos logit contributions
 bank+0.005
 banks+0.004
 allowance+0.004
ro+0.004
 until+0.004
Neg logit contributions
ww-0.014
www-0.013
heart-0.013
ons-0.012
w-0.011
Token
Token ID198
Feature activation-2.73e-03

Pos logit contributions
 bank+0.004
 banks+0.004
 allowance+0.003
ro+0.003
 symp+0.003
Neg logit contributions
ww-0.008
www-0.008
heart-0.007
mber-0.007
ons-0.007
TokenThey
Token ID2990
Feature activation+5.24e-03

Pos logit contributions
 bank+0.005
 banks+0.005
ro+0.004
 allowance+0.004
tted+0.004
Neg logit contributions
ww-0.004
www-0.004
heart-0.004
mber-0.003
ons-0.003
Token hug
Token ID16225
Feature activation-1.26e-02

Pos logit contributions
ww+0.011
www+0.010
?"+0.009
heart+0.009
ons+0.009
Neg logit contributions
 bank-0.007
 banks-0.007
 allowance-0.007
ro-0.006
isc-0.006
Token will
Token ID481
Feature activation-1.86e-02

Pos logit contributions
ww+0.028
www+0.024
?"+0.023
?+0.021
heart+0.021
Neg logit contributions
 banks-0.025
 bank-0.025
 allowance-0.023
 symp-0.021
 usual-0.021
Token teach
Token ID4545
Feature activation-1.91e-02

Pos logit contributions
 bank+0.024
 banks+0.022
 allowance+0.021
ro+0.018
isc+0.017
Neg logit contributions
ww-0.042
www-0.037
heart-0.035
mber-0.034
ons-0.034
Token you
Token ID345
Feature activation-5.60e-03

Pos logit contributions
 bank+0.037
 allowance+0.036
 banks+0.036
 anymore+0.033
 usual+0.033
Neg logit contributions
ww-0.028
www-0.024
loo-0.021
mber-0.021
aver-0.020
Token some
Token ID617
Feature activation-8.59e-03

Pos logit contributions
 bank+0.009
 banks+0.008
 allowance+0.008
ro+0.007
 usual+0.007
Neg logit contributions
ww-0.011
www-0.010
mber-0.009
heart-0.009
ons-0.008
Token songs
Token ID7259
Feature activation+7.96e-03

Pos logit contributions
 bank+0.013
 allowance+0.012
 banks+0.012
ro+0.011
 usual+0.010
Neg logit contributions
ww-0.017
www-0.015
mber-0.014
heart-0.014
very-0.013
Token."
Token ID526
Feature activation-1.05e-02

Pos logit contributions
ww+0.019
www+0.018
heart+0.016
mber+0.016
ons+0.015
Neg logit contributions
 bank-0.008
 banks-0.008
 allowance-0.007
ro-0.007
 anymore-0.007
Token She
Token ID1375
Feature activation+2.35e-03

Pos logit contributions
 bank+0.012
 banks+0.012
 allowance+0.011
ro+0.010
 symp+0.010
Neg logit contributions
ww-0.024
www-0.022
heart-0.020
ons-0.019
loo-0.019
Token lifts
Token ID27103
Feature activation-4.54e-03

Pos logit contributions
ww+0.004
www+0.004
heart+0.003
mber+0.003
ons+0.003
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.004
ro-0.003
isc-0.003
Token Anna
Token ID11735
Feature activation+2.70e-03

Pos logit contributions
 bank+0.009
 banks+0.008
 allowance+0.008
isc+0.007
ro+0.007
Neg logit contributions
ww-0.007
www-0.006
?"-0.005
heart-0.005
ons-0.005
Token and
Token ID290
Feature activation+1.20e-03

Pos logit contributions
ww+0.005
www+0.004
ons+0.004
?"+0.004
 my+0.004
Neg logit contributions
 bank-0.004
 banks-0.004
 allowance-0.004
isc-0.003
 usual-0.003
Token puts
Token ID7584
Feature activation+1.90e-03

Pos logit contributions
ww+0.002
www+0.002
heart+0.002
mber+0.002
loo+0.002
Neg logit contributions
 bank-0.002
 banks-0.002
 allowance-0.002
ro-0.002
 symp-0.002
Token girl
Token ID2576
Feature activation+1.18e-02

Pos logit contributions
ww+0.004
ons+0.004
www+0.004
heart+0.003
ins+0.003
Neg logit contributions
 bank-0.004
 banks-0.003
ro-0.003
 allowance-0.003
 symp-0.003
Token named
Token ID3706
Feature activation+7.24e-03

Pos logit contributions
ww+0.017
www+0.014
heart+0.012
ons+0.012
?"+0.011
Neg logit contributions
 bank-0.025
 banks-0.024
 allowance-0.023
ro-0.021
isc-0.021
Token Av
Token ID5184
Feature activation-2.31e-02

Pos logit contributions
ww+0.011
www+0.010
?"+0.009
heart+0.008
ons+0.008
Neg logit contributions
 bank-0.014
 banks-0.014
 allowance-0.013
isc-0.012
ro-0.012
Tokena
Token ID64
Feature activation-2.17e-02

Pos logit contributions
 bank+0.047
 banks+0.046
 allowance+0.043
isc+0.039
 injuries+0.039
Neg logit contributions
ww-0.034
www-0.028
?"-0.027
mber-0.026
ons-0.026
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
 bank+0.034
 banks+0.033
 allowance+0.032
isc+0.028
ro+0.028
Neg logit contributions
ww-0.040
?"-0.035
www-0.035
?-0.033
ons-0.033
Token She
Token ID1375
Feature activation-9.65e-03

Pos logit contributions
 bank+0.022
 banks+0.021
 allowance+0.020
 injuries+0.020
isc+0.018
Neg logit contributions
ww-0.020
www-0.017
?"-0.017
mber-0.016
heart-0.016
Token was
Token ID373
Feature activation+1.51e-03

Pos logit contributions
 bank+0.015
 banks+0.014
 allowance+0.013
ro+0.012
isc+0.012
Neg logit contributions
ww-0.019
www-0.017
heart-0.015
ons-0.015
mber-0.015
Token only
Token ID691
Feature activation-2.54e-02

Pos logit contributions
ww+0.003
www+0.003
heart+0.002
?"+0.002
ons+0.002
Neg logit contributions
 bank-0.002
 banks-0.002
 allowance-0.002
ro-0.002
isc-0.002
Token three
Token ID1115
Feature activation-2.82e-02

Pos logit contributions
 bank+0.039
 banks+0.039
 allowance+0.033
side+0.032
 symp+0.031
Neg logit contributions
ww-0.050
www-0.043
heart-0.040
 my-0.040
mber-0.039
Token years
Token ID812
Feature activation-2.03e-02

Pos logit contributions
 bank+0.053
 banks+0.051
 allowance+0.048
isc+0.045
ro+0.045
Neg logit contributions
ww-0.045
www-0.039
heart-0.035
ons-0.034
?"-0.034
Token old
Token ID1468
Feature activation-2.07e-02

Pos logit contributions
 bank+0.030
 banks+0.029
 allowance+0.027
ro+0.024
isc+0.024
Neg logit contributions
ww-0.040
www-0.036
heart-0.032
ons-0.032
mber-0.032
Token.
Token ID13
Feature activation-2.63e-03

Pos logit contributions
 bank+0.023
 banks+0.023
 allowance+0.021
isc+0.020
tted+0.019
Neg logit contributions
ww-0.023
www-0.020
?"-0.019
heart-0.019
?-0.019
Token She
Token ID1375
Feature activation-4.00e-04

Pos logit contributions
 bank+0.005
 banks+0.005
 allowance+0.005
 contain+0.004
 injuries+0.004
Neg logit contributions
ww-0.004
www-0.004
heart-0.003
?"-0.003
mber-0.003
Token looked
Token ID3114
Feature activation-4.46e-03

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.000
ro+0.000
isc+0.000
Neg logit contributions
ww-0.001
www-0.001
heart-0.001
ons-0.001
mber-0.001
Token at
Token ID379
Feature activation+2.70e-02

Pos logit contributions
 bank+0.007
 banks+0.006
 allowance+0.006
ro+0.005
isc+0.005
Neg logit contributions
ww-0.009
www-0.008
heart-0.007
?"-0.007
ons-0.007
Token the
Token ID262
Feature activation+1.27e-02

Pos logit contributions
ww+0.048
www+0.042
heart+0.038
ons+0.037
?"+0.037
Neg logit contributions
 bank-0.046
 banks-0.044
 allowance-0.042
ro-0.038
isc-0.038
Token mark
Token ID1317
Feature activation-1.01e-02

Pos logit contributions
ww+0.021
www+0.019
heart+0.016
ons+0.016
mber+0.016
Neg logit contributions
 bank-0.023
 banks-0.022
 allowance-0.021
ro-0.019
isc-0.019
Token on
Token ID319
Feature activation+3.24e-03

Pos logit contributions
 bank+0.014
 banks+0.014
 allowance+0.013
ro+0.012
 symp+0.011
Neg logit contributions
ww-0.021
www-0.019
heart-0.017
mber-0.016
ons-0.016
Token her
Token ID607
Feature activation+2.18e-03

Pos logit contributions
ww+0.005
www+0.005
heart+0.004
?"+0.004
ons+0.004
Neg logit contributions
 bank-0.006
 banks-0.006
 allowance-0.005
isc-0.005
ro-0.005
Token knee
Token ID10329
Feature activation-3.74e-02

Pos logit contributions
ww+0.004
?"+0.003
?+0.003
 my+0.003
www+0.003
Neg logit contributions
 bank-0.003
 banks-0.003
 allowance-0.003
urd-0.003
tted-0.003
Token and
Token ID290
Feature activation+9.29e-04

Pos logit contributions
 banks+0.061
 bank+0.061
 allowance+0.059
isc+0.053
 symp+0.052
Neg logit contributions
ww-0.063
www-0.054
?"-0.050
ons-0.050
heart-0.050
Token smiled
Token ID13541
Feature activation-1.10e-03

Pos logit contributions
ww+0.002
www+0.002
loo+0.002
heart+0.002
ons+0.002
Neg logit contributions
 bank-0.001
 banks-0.001
 allowance-0.001
 usual-0.001
ro-0.001
Token was
Token ID373
Feature activation+5.49e-04

Pos logit contributions
 bank+0.018
 banks+0.018
 allowance+0.017
ro+0.015
isc+0.015
Neg logit contributions
ww-0.025
www-0.022
heart-0.021
ons-0.020
mber-0.020
Token going
Token ID1016
Feature activation-3.03e-03

Pos logit contributions
ww+0.001
www+0.001
heart+0.001
ons+0.001
mber+0.001
Neg logit contributions
 bank-0.001
 banks-0.001
 allowance-0.001
 usual-0.001
isc-0.001
Token to
Token ID284
Feature activation-4.28e-03

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.003
ro+0.002
isc+0.002
Neg logit contributions
ww-0.008
www-0.007
heart-0.006
mber-0.006
ons-0.006
Token meet
Token ID1826
Feature activation-1.44e-02

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.006
ro+0.005
isc+0.005
Neg logit contributions
ww-0.009
www-0.008
heart-0.007
ons-0.007
mber-0.007
Token a
Token ID257
Feature activation-5.23e-03

Pos logit contributions
 bank+0.023
 banks+0.022
 allowance+0.021
isc+0.018
ro+0.018
Neg logit contributions
ww-0.028
www-0.024
heart-0.022
ons-0.021
mber-0.021
Token prince
Token ID19716
Feature activation-9.13e-03

Pos logit contributions
 bank+0.007
 banks+0.007
 allowance+0.007
 usual+0.006
isc+0.006
Neg logit contributions
ww-0.010
www-0.009
heart-0.009
ons-0.009
loo-0.008
Token.
Token ID13
Feature activation-3.80e-05

Pos logit contributions
 bank+0.011
 banks+0.010
 allowance+0.010
ro+0.008
isc+0.008
Neg logit contributions
ww-0.021
www-0.019
heart-0.017
mber-0.017
ons-0.017
Token She
Token ID1375
Feature activation-1.26e-03

Pos logit contributions
 bank+0.000
 banks+0.000
 allowance+0.000
 injuries+0.000
ro+0.000
Neg logit contributions
ww-0.000
www-0.000
?"-0.000
heart-0.000
mber-0.000
Token put
Token ID1234
Feature activation+8.21e-03

Pos logit contributions
 bank+0.002
 banks+0.002
 allowance+0.002
ro+0.001
isc+0.001
Neg logit contributions
ww-0.003
www-0.002
heart-0.002
ons-0.002
loo-0.002
Token on
Token ID319
Feature activation+3.44e-03

Pos logit contributions
ww+0.018
www+0.017
heart+0.015
loo+0.015
mber+0.015
Neg logit contributions
 bank-0.010
 allowance-0.009
 banks-0.009
 usual-0.008
isc-0.008
Token her
Token ID607
Feature activation+3.76e-03

Pos logit contributions
ww+0.006
www+0.005
heart+0.004
ons+0.004
mber+0.004
Neg logit contributions
 bank-0.006
 banks-0.006
 allowance-0.006
ro-0.005
isc-0.005
Token that
Token ID326
Feature activation-9.88e-03

Pos logit contributions
 bank+0.003
 until+0.002
 anymore+0.002
 banks+0.002
 after+0.002
Neg logit contributions
ww-0.009
www-0.008
igator-0.008
loo-0.008
rooms-0.008
Token she
Token ID673
Feature activation-1.14e-02

Pos logit contributions
 bank+0.020
 banks+0.019
 allowance+0.018
ro+0.017
isc+0.017
Neg logit contributions
ww-0.015
www-0.012
heart-0.011
ons-0.010
mber-0.010
Token had
Token ID550
Feature activation-6.86e-03

Pos logit contributions
 bank+0.015
 banks+0.014
 allowance+0.013
ro+0.011
isc+0.011
Neg logit contributions
ww-0.025
www-0.022
heart-0.020
ons-0.020
loo-0.020
Token a
Token ID257
Feature activation-9.35e-03

Pos logit contributions
 bank+0.010
 banks+0.010
 allowance+0.009
ro+0.008
 usual+0.008
Neg logit contributions
ww-0.013
www-0.012
heart-0.011
ons-0.010
loo-0.010
Token clean
Token ID3424
Feature activation-2.21e-02

Pos logit contributions
 bank+0.015
 banks+0.014
 allowance+0.014
ro+0.012
isc+0.012
Neg logit contributions
ww-0.018
www-0.015
heart-0.014
ons-0.014
mber-0.013
Token plate
Token ID7480
Feature activation-1.67e-02

Pos logit contributions
 bank+0.034
 banks+0.032
 allowance+0.030
ro+0.027
isc+0.027
Neg logit contributions
ww-0.043
www-0.038
heart-0.034
ons-0.034
mber-0.033
Token and
Token ID290
Feature activation-3.99e-03

Pos logit contributions
 bank+0.021
 banks+0.019
 allowance+0.018
ro+0.017
 usual+0.016
Neg logit contributions
ww-0.037
www-0.033
heart-0.030
mber-0.030
ons-0.029
Token a
Token ID257
Feature activation-1.02e-02

Pos logit contributions
 bank+0.006
 allowance+0.005
 banks+0.005
 usual+0.005
ro+0.004
Neg logit contributions
ww-0.008
www-0.007
heart-0.007
mber-0.007
loo-0.007
Token full
Token ID1336
Feature activation-7.64e-03

Pos logit contributions
 bank+0.016
 banks+0.015
 allowance+0.015
ro+0.013
isc+0.013
Neg logit contributions
ww-0.019
www-0.017
heart-0.016
ons-0.015
mber-0.015
Token tum
Token ID11814
Feature activation-1.54e-02

Pos logit contributions
 bank+0.010
 banks+0.009
 allowance+0.008
 usual+0.007
ro+0.007
Neg logit contributions
ww-0.017
www-0.015
ons-0.014
heart-0.014
ins-0.013
Tokenmy
Token ID1820
Feature activation-3.29e-03

Pos logit contributions
 bank+0.035
 banks+0.034
 allowance+0.032
ro+0.031
isc+0.031
Neg logit contributions
ww-0.019
www-0.015
mber-0.012
heart-0.011
ons-0.010
Token can
Token ID460
Feature activation-7.90e-04

Pos logit contributions
 bank+0.006
 banks+0.005
 allowance+0.005
ro+0.004
isc+0.004
Neg logit contributions
ww-0.011
www-0.010
mber-0.010
heart-0.010
ons-0.009
Token hug
Token ID16225
Feature activation-1.31e-02

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
isc+0.001
ro+0.001
Neg logit contributions
ww-0.002
www-0.001
?"-0.001
heart-0.001
ons-0.001
Token and
Token ID290
Feature activation-2.45e-03

Pos logit contributions
 bank+0.025
 banks+0.024
 allowance+0.023
ro+0.022
isc+0.021
Neg logit contributions
ww-0.020
www-0.017
loo-0.015
mber-0.015
heart-0.014
Token make
Token ID787
Feature activation-1.59e-03

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.003
ro+0.002
 buy+0.002
Neg logit contributions
ww-0.006
www-0.005
mber-0.005
heart-0.005
loo-0.005
Token grow
Token ID1663
Feature activation-1.05e-02

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.003
 symp+0.003
isc+0.003
Neg logit contributions
ww-0.002
www-0.002
mber-0.002
loo-0.002
heart-0.002
Tokenl
Token ID75
Feature activation-8.74e-02

Pos logit contributions
 bank+0.017
 banks+0.016
 allowance+0.015
ro+0.014
isc+0.014
Neg logit contributions
ww-0.020
www-0.018
heart-0.016
?"-0.016
ons-0.016
Token grow
Token ID1663
Feature activation-1.06e-02

Pos logit contributions
 bank+0.123
 banks+0.118
 allowance+0.109
ro+0.098
isc+0.096
Neg logit contributions
ww-0.181
www-0.162
heart-0.146
mber-0.145
ons-0.143
Tokenl
Token ID75
Feature activation-8.74e-02

Pos logit contributions
 bank+0.017
 banks+0.016
 allowance+0.015
ro+0.014
isc+0.014
Neg logit contributions
ww-0.020
www-0.017
heart-0.016
?"-0.015
ons-0.015
Token sounds
Token ID5238
Feature activation+2.82e-02

Pos logit contributions
 bank+0.126
 banks+0.120
 allowance+0.113
ro+0.100
isc+0.100
Neg logit contributions
ww-0.178
www-0.157
heart-0.143
ons-0.141
?"-0.140
Token,"
Token ID553
Feature activation+4.79e-03

Pos logit contributions
ww+0.064
www+0.059
loo+0.054
mber+0.054
ons+0.054
Neg logit contributions
 bank-0.032
 banks-0.030
 allowance-0.028
 until-0.026
 anymore-0.025
Token Lily
Token ID20037
Feature activation+7.15e-03

Pos logit contributions
ww+0.010
www+0.009
loo+0.008
ons+0.008
heart+0.008
Neg logit contributions
 bank-0.006
 allowance-0.006
 banks-0.006
ro-0.005
 usual-0.005
Token a
Token ID257
Feature activation-2.83e-03

Pos logit contributions
 bank+0.009
 banks+0.008
 allowance+0.008
ro+0.007
isc+0.007
Neg logit contributions
ww-0.011
www-0.009
heart-0.008
ons-0.008
?"-0.008
Token bad
Token ID2089
Feature activation-1.32e-02

Pos logit contributions
 bank+0.004
 banks+0.004
 allowance+0.004
 usual+0.003
ro+0.003
Neg logit contributions
ww-0.006
www-0.005
heart-0.005
ons-0.005
mber-0.005
Token tum
Token ID11814
Feature activation-9.47e-03

Pos logit contributions
 bank+0.021
 banks+0.019
 allowance+0.019
ro+0.017
isc+0.016
Neg logit contributions
ww-0.026
www-0.023
heart-0.021
ons-0.021
mber-0.020
Tokenmy
Token ID1820
Feature activation+7.53e-03

Pos logit contributions
 bank+0.021
 banks+0.021
 allowance+0.020
ro+0.019
isc+0.019
Neg logit contributions
ww-0.012
www-0.009
mber-0.007
heart-0.007
ons-0.006
Token ac
Token ID936
Feature activation-3.70e-02

Pos logit contributions
ww+0.015
www+0.013
?"+0.012
ons+0.012
heart+0.012
Neg logit contributions
 bank-0.011
 banks-0.011
 allowance-0.010
isc-0.010
urd-0.009
Tokenhe
Token ID258
Feature activation-9.11e-02

Pos logit contributions
 bank+0.054
 banks+0.052
 allowance+0.048
ro+0.043
isc+0.043
Neg logit contributions
ww-0.075
www-0.066
heart-0.060
ons-0.059
mber-0.059
Token and
Token ID290
Feature activation-2.02e-03

Pos logit contributions
 bank+0.139
 banks+0.130
 allowance+0.123
ro+0.113
 usual+0.109
Neg logit contributions
ww-0.184
www-0.162
heart-0.145
mber-0.142
ons-0.140
Token felt
Token ID2936
Feature activation-1.28e-02

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.003
 usual+0.002
ro+0.002
Neg logit contributions
ww-0.004
www-0.004
heart-0.003
mber-0.003
loo-0.003
Token very
Token ID845
Feature activation+1.74e-03

Pos logit contributions
 bank+0.019
 banks+0.018
 allowance+0.017
isc+0.017
ro+0.017
Neg logit contributions
ww-0.024
www-0.021
?"-0.021
 my-0.020
heart-0.020
Token sick
Token ID6639
Feature activation-5.61e-03

Pos logit contributions
ww+0.004
www+0.003
heart+0.003
?"+0.003
ons+0.003
Neg logit contributions
 bank-0.002
 banks-0.002
 allowance-0.002
isc-0.002
ro-0.002
Token.
Token ID13
Feature activation-3.01e-03

Pos logit contributions
 bank+0.009
 banks+0.008
 allowance+0.008
isc+0.007
 symp+0.007
Neg logit contributions
ww-0.011
www-0.009
?"-0.009
heart-0.009
ons-0.008
Token
Token ID198
Feature activation+1.02e-05

Pos logit contributions
ww+0.001
www+0.001
?"+0.001
unt+0.001
ons+0.001
Neg logit contributions
 bank-0.002
 banks-0.002
 allowance-0.002
 contain-0.001
 symp-0.001
Token
Token ID198
Feature activation+6.95e-04

Pos logit contributions
ww+0.000
www+0.000
?"+0.000
ons+0.000
mber+0.000
Neg logit contributions
 bank-0.000
 banks-0.000
 allowance-0.000
ro-0.000
isc-0.000
TokenSpot
Token ID32565
Feature activation-2.73e-02

Pos logit contributions
ww+0.001
www+0.001
?"+0.001
ons+0.001
mber+0.001
Neg logit contributions
 bank-0.001
 banks-0.001
 allowance-0.001
 symp-0.001
isc-0.001
Token found
Token ID1043
Feature activation-3.20e-03

Pos logit contributions
 bank+0.043
 banks+0.041
 allowance+0.039
ro+0.035
isc+0.035
Neg logit contributions
ww-0.052
www-0.046
heart-0.041
ons-0.041
?"-0.040
Token Wh
Token ID854
Feature activation-6.31e-02

Pos logit contributions
 bank+0.006
 banks+0.006
 allowance+0.006
 symp+0.005
ro+0.005
Neg logit contributions
ww-0.005
www-0.004
 my-0.004
ons-0.004
?"-0.004
Tokenisk
Token ID1984
Feature activation-1.41e-01

Pos logit contributions
 bank+0.074
 banks+0.069
 allowance+0.068
 symp+0.053
 contain+0.053
Neg logit contributions
ww-0.145
www-0.131
ons-0.124
imi-0.122
heart-0.121
Tokeners
Token ID364
Feature activation-5.84e-03

Pos logit contributions
 bank+0.241
 banks+0.229
 allowance+0.212
ro+0.206
tted+0.199
Neg logit contributions
ww-0.246
www-0.214
heart-0.195
?"-0.188
mber-0.183
Token and
Token ID290
Feature activation+3.34e-03

Pos logit contributions
 bank+0.010
 banks+0.009
 allowance+0.009
isc+0.009
ro+0.008
Neg logit contributions
ww-0.009
www-0.008
ons-0.008
?"-0.008
?-0.008
Token said
Token ID531
Feature activation-3.29e-03

Pos logit contributions
ww+0.006
www+0.006
heart+0.005
loo+0.005
mber+0.005
Neg logit contributions
 bank-0.005
 banks-0.005
 allowance-0.005
ro-0.004
isc-0.004
Token,
Token ID11
Feature activation+5.35e-03

Pos logit contributions
 bank+0.005
 banks+0.005
 allowance+0.005
ro+0.004
isc+0.004
Neg logit contributions
ww-0.006
www-0.006
heart-0.005
ons-0.005
mber-0.005
Token "
Token ID366
Feature activation-2.19e-02

Pos logit contributions
ww+0.010
www+0.009
heart+0.008
ons+0.008
mber+0.008
Neg logit contributions
 bank-0.008
 banks-0.008
 allowance-0.007
ro-0.007
isc-0.007
Token book
Token ID1492
Feature activation+2.42e-02

Pos logit contributions
 bank+0.014
 banks+0.013
 allowance+0.013
ro+0.012
isc+0.012
Neg logit contributions
ww-0.010
www-0.008
heart-0.007
ons-0.007
mber-0.007
Token falls
Token ID8953
Feature activation+7.47e-03

Pos logit contributions
ww+0.042
www+0.037
heart+0.033
mber+0.032
ons+0.032
Neg logit contributions
 bank-0.042
 banks-0.040
 allowance-0.039
ro-0.035
isc-0.034
Token off
Token ID572
Feature activation+1.61e-02

Pos logit contributions
ww+0.014
www+0.012
heart+0.011
?"+0.011
ons+0.011
Neg logit contributions
 bank-0.012
 banks-0.012
 allowance-0.011
isc-0.010
 symp-0.010
Token the
Token ID262
Feature activation+1.60e-02

Pos logit contributions
ww+0.030
www+0.027
heart+0.024
ons+0.024
?"+0.024
Neg logit contributions
 bank-0.025
 banks-0.024
 allowance-0.023
isc-0.021
 symp-0.020
Token books
Token ID3835
Feature activation-2.29e-03

Pos logit contributions
ww+0.028
www+0.024
 my+0.023
?"+0.023
ons+0.022
Neg logit contributions
 banks-0.026
 bank-0.025
 allowance-0.023
isc-0.022
 symp-0.022
Tokenhe
Token ID258
Feature activation-8.74e-02

Pos logit contributions
 bank+0.003
 banks+0.003
 allowance+0.003
isc+0.003
 symp+0.003
Neg logit contributions
ww-0.005
www-0.004
ons-0.004
?"-0.004
loo-0.004
Tokenlf
Token ID1652
Feature activation+5.07e-02

Pos logit contributions
 bank+0.208
 banks+0.197
 allowance+0.194
ro+0.189
 usual+0.178
Neg logit contributions
ww-0.106
www-0.084
heart-0.069
mber-0.064
ins-0.054
Token.
Token ID13
Feature activation+5.70e-03

Pos logit contributions
ww+0.092
www+0.082
ons+0.078
?"+0.076
loo+0.075
Neg logit contributions
 bank-0.074
 banks-0.074
 allowance-0.069
isc-0.065
 symp-0.062
Token It
Token ID632
Feature activation-4.29e-04

Pos logit contributions
ww+0.008
www+0.007
?"+0.006
ons+0.006
mber+0.006
Neg logit contributions
 bank-0.012
 banks-0.011
 allowance-0.011
uries-0.010
isc-0.010
Token makes
Token ID1838
Feature activation-6.95e-04

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
ro+0.001
isc+0.001
Neg logit contributions
ww-0.001
www-0.001
heart-0.001
ons-0.000
?"-0.000
Token a
Token ID257
Feature activation-4.58e-03

Pos logit contributions
 bank+0.001
 banks+0.001
 allowance+0.001
isc+0.001
ro+0.001
Neg logit contributions
ww-0.001
www-0.001
ons-0.001
heart-0.001
 my-0.001
Token strange
Token ID6283
Feature activation+7.72e-03

Pos logit contributions
ww+0.031
www+0.028
ons+0.026
ins+0.026
loo+0.025
Neg logit contributions
 bank-0.017
 banks-0.015
 allowance-0.014
 usual-0.014
 seem-0.012
Token happened
Token ID3022
Feature activation+3.06e-02

Pos logit contributions
ww+0.014
www+0.012
mber+0.011
ins+0.010
P+0.010
Neg logit contributions
 bank-0.013
 banks-0.012
 allowance-0.011
 usual-0.011
ro-0.011
Token.
Token ID13
Feature activation+3.59e-03

Pos logit contributions
ww+0.072
www+0.065
mber+0.058
heart+0.058
ons+0.057
Neg logit contributions
 bank-0.036
 banks-0.034
 allowance-0.030
ro-0.028
 symp-0.027
Token The
Token ID383
Feature activation-9.10e-03

Pos logit contributions
ww+0.008
www+0.007
ons+0.006
heart+0.006
loo+0.006
Neg logit contributions
 bank-0.005
 banks-0.004
 allowance-0.004
ro-0.004
isc-0.004
Token books
Token ID3835
Feature activation-5.48e-03

Pos logit contributions
 bank+0.016
 banks+0.015
 allowance+0.014
 usual+0.013
ro+0.013
Neg logit contributions
ww-0.016
www-0.014
ons-0.013
heart-0.013
mber-0.012
Tokenhe
Token ID258
Feature activation-8.95e-02

Pos logit contributions
 bank+0.007
 banks+0.007
 allowance+0.006
ro+0.005
 symp+0.005
Neg logit contributions
ww-0.012
www-0.011
heart-0.010
mber-0.010
ons-0.010
Tokenlf
Token ID1652
Feature activation+5.28e-02

Pos logit contributions
 bank+0.204
 banks+0.191
 allowance+0.188
ro+0.183
 usual+0.178
Neg logit contributions
ww-0.118
www-0.093
heart-0.074
mber-0.065
 yours-0.065
Token became
Token ID2627
Feature activation+3.21e-02

Pos logit contributions
ww+0.111
www+0.099
heart+0.088
mber+0.087
ons+0.086
Neg logit contributions
 bank-0.076
 banks-0.071
 allowance-0.066
ro-0.059
 symp-0.057
Token restless
Token ID42537
Feature activation+8.84e-03

Pos logit contributions
ww+0.067
www+0.060
heart+0.054
ons+0.053
mber+0.053
Neg logit contributions
 bank-0.045
 banks-0.043
 allowance-0.040
ro-0.036
isc-0.035
Token.
Token ID13
Feature activation+5.34e-03

Pos logit contributions
ww+0.018
www+0.016
heart+0.014
ons+0.014
?"+0.014
Neg logit contributions
 bank-0.013
 banks-0.012
 allowance-0.012
isc-0.010
ro-0.010
Token It
Token ID632
Feature activation-5.65e-04

Pos logit contributions
ww+0.012
www+0.011
heart+0.010
ons+0.009
mber+0.009
Neg logit contributions
 bank-0.007
 banks-0.007
 allowance-0.006
ro-0.005
isc-0.005