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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    orte
    0.98
    oper
    0.93
    otor
    0.92
    ectl
    0.91
    antiene
    0.91
    ulfide
    0.89
     :::
    0.88
    orske
    0.88
    ortex
    0.87
    itrile
    0.87
    POSITIVE LOGITS
    ‌های
    0.82
     ਵਿੱਚ
    0.76
    區域
    0.74
     בי
    0.74
    ながら
    0.73
    “
    0.72
    ["
    0.72
     negó
    0.71
    “.
    0.69
     susah
    0.69
    Act Density 0.000%

    No Known Activations