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

    Neuronpedia

    INDEX
    Explanations

    references to physical shapes and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <tbody>
    -0.36
    __(/*!
    -0.36
     Wiktionnaire
    -0.35
    +:+
    -0.34
     StringTokenizer
    -0.34
     ویکی‌پدی
    -0.34
     comuniques
    -0.33
     ***!
    -0.32
    hoeddwyd
    -0.32
     nahilalakip
    -0.31
    POSITIVE LOGITS
    hift
    0.76
     Shape
    0.69
    SHAPE
    0.68
     AttributeSet
    0.66
     SHAPE
    0.65
    shifting
    0.63
    Shape
    0.60
     Bentuk
    0.60
     Shaping
    0.60
    leſs
    0.58
    Act Density 0.135%

    No Known Activations