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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    as
    0.98
     furthest
    0.93
     farthest
    0.88
    am
    0.88
     seule
    0.87
    ل
    0.86
    zedł
    0.86
     Unfortunately
    0.85
    હ
    0.85
     jest
    0.85
    POSITIVE LOGITS
    其
    1.31
    ಈ
    1.08
     belliger
    1.05
    📱
    1.03
     harassing
    1.01
    राजनी
    1.00
     fontweight
    0.95
     enquiries
    0.94
    लेज
    0.93
    ドキ
    0.93
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.