INDEX
Explanations
words related to feeling proud or expressing pride
expressions of pride
New Auto-Interp
Negative Logits
PF
-0.78
apter
-0.69
itamin
-0.67
arettes
-0.63
CPU
-0.62
vati
-0.62
abin
-0.62
stove
-0.62
amber
-0.62
Webster
-0.61
POSITIVE LOGITS
hon
0.91
edly
0.91
edIn
0.83
lete
0.76
roud
0.74
est
0.74
sburg
0.74
faced
0.73
proud
0.72
Proud
0.71
Activations Density 0.023%