INDEX
Explanations
actions followed by possessives
New Auto-Interp
Negative Logits
আমাকে
1.26
yourselves
1.24
yourself
1.23
彼は
1.21
lui
1.17
нього
1.15
让他们
1.13
그는
1.11
मुझसे
1.10
Yourself
1.10
POSITIVE LOGITS
seu
2.17
sua
2.04
своего
2.00
suas
1.98
seus
1.97
свое
1.96
свои
1.93
своей
1.89
свою
1.86
अपनी
1.82
Activations Density 1.334%