INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
people
0.79
บุคคล
0.70
pessoas
0.68
people
0.64
premises
0.63
ljudi
0.63
mensen
0.63
miscellaneous
0.63
persons
0.61
consists
0.61
POSITIVE LOGITS
daughter
0.97
男孩
0.89
adolesc
0.88
adoles
0.88
🧒
0.87
daughter
0.86
daughters
0.86
nieces
0.85
teenage
0.84
adolescente
0.84
Activations Density 0.270%