INDEX
Explanations
words related to academic disciplines and areas of study, specifically focusing on philosophy
mentions of philosophy and its various branches or applications
New Auto-Interp
Negative Logits
女
-0.80
esty
-0.79
ells
-0.78
sg
-0.76
rake
-0.75
abs
-0.75
semble
-0.74
recorded
-0.74
ookie
-0.71
present
-0.71
POSITIVE LOGITS
ophical
1.15
philosophy
0.95
ophy
0.86
philosopher
0.81
philosophers
0.81
lectic
0.80
ophe
0.79
ophers
0.77
¿½
0.77
Philosophy
0.76
Activations Density 0.013%