INDEX
Explanations
introducing explanations or examples
New Auto-Interp
Negative Logits
also
0.56
juga
0.53
or
0.51
also
0.48
نیز
0.47
也可
0.46
cũng
0.46
,
0.46
също
0.45
Также
0.45
POSITIVE LOGITS
nämlich
0.81
मसलन
0.76
அதாவது
0.74
Namely
0.73
Firstly
0.71
namelijk
0.71
namely
0.69
namely
0.65
totiž
0.64
firstly
0.64
Activations Density 4.603%