Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     to
    -1.84
    ꯢ
    -1.83
    珦
    -1.72
    就已经
    -1.66
     It
    -1.66
    闼
    -1.65
     มัน
    -1.59
    に使用
    -1.59
    }$.
    -1.49
    聍
    -1.49
    POSITIVE LOGITS
     pouvez
    1.48
    チャンス
    1.46
    Surprisingly
    1.45
    戦い
    1.44
    気持ちが
    1.37
    e
    1.36
     Konkur
    1.33
    5
    1.31
     uda
    1.30
     appétit
    1.30
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.