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

    Neuronpedia

    INDEX
    Explanations

    expressions related to uncertainty, expectations, and assumptions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     třeba
    -0.47
    起
    -0.44
     Ayrıca
    -0.43
    ilyen
    -0.43
     بالق
    -0.42
    dor
    -0.41
    yce
    -0.40
    jednoc
    -0.40
    LookAnd
    -0.40
    дитесь
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.92
     مرئيه
    0.81
     AttributeSet
    0.79
    __":
    0.76
     doInBackground
    0.75
     HasFactory
    0.74
     ویکی‌پدیای
    0.74
    )";
    0.73
    setVerticalGroup
    0.72
    Autoritní
    0.72
    Act Density 0.107%

    No Known Activations