INDEX
Explanations
verbs related to emotional experiences and commitments
New Auto-Interp
Negative Logits
jvu
-0.16
ÑĥÑģÑĤ
-0.16
uste
-0.15
sdale
-0.15
esome
-0.15
stp
-0.15
ese
-0.14
sworth
-0.14
otor
-0.14
.unwrap
-0.14
POSITIVE LOGITS
secular
0.14
ãĥĥãĥĹ
0.14
ancer
0.13
ampion
0.13
ëĭ¤ê°Ģ
0.13
Lionel
0.13
béné
0.13
rep
0.13
landed
0.13
these
0.13
Activations Density 0.014%