INDEX
Explanations
punctuation marks, particularly at the end of sentences
New Auto-Interp
Negative Logits
"]}
-0.87
']}
-0.87
*/}
-0.81
"}
-0.78
"]=
-0.76
'}
-0.75
Faust
-0.74
")}
-0.73
']
-0.72
*/}
-0.72
POSITIVE LOGITS
{§0.93
Monfieur
0.93
xenia
0.89
tieth
0.89
いる
0.88
Encyclopædia
0.86
ագրություններ
0.85
għal
0.85
Gaetano
0.85
catalogs
0.84
Activations Density 0.125%