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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters related to mathematical expressions or notation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    y
    -0.95
    '
    -0.69
    ^{\
    -0.69
    i
    -0.68
     Arag
    -0.68
    e
    -0.67
    ई
    -0.65
     Junge
    -0.64
     Cummings
    -0.64
    ary
    -0.63
    POSITIVE LOGITS
    }^\
    1.48
    ^\
    1.39
    _\
    1.04
    YGON
    0.94
    Coeff
    0.91
    ︎
    0.91
     Yann
    0.91
     Préférences
    0.87
    :✨
    0.85
    volezza
    0.85
    Act Density 0.013%

    No Known Activations