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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    شود
    0.71
     offensively
    0.71
    dessus
    0.70
    ieval
    0.69
     особа
    0.68
     као
    0.67
    selves
    0.67
    д
    0.65
    ぜ
    0.64
    𝗱
    0.63
    POSITIVE LOGITS
    people
    0.78
    ↵
    0.78
    YW
    0.78
     Boo
    0.77
     Avoid
    0.75
     Química
    0.75
     Glu
    0.73
    ym
    0.73
     সংখ্যা
    0.73
     Ví
    0.73
    Act Density 0.001%

    No Known Activations