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

    Neuronpedia

    INDEX
    Explanations

    references to programming constructs or machine-related terms in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     BorderRadius
    -0.51
    currentColor
    -0.50
     langit
    -0.49
    IntoConstraints
    -0.49
    rsa
    -0.49
     terrorismo
    -0.49
    complexType
    -0.47
    ormais
    -0.45
     gratuites
    -0.45
    byshev
    -0.45
    POSITIVE LOGITS
     arcade
    0.72
    Datuak
    0.69
    Xna
    0.68
    地说道
    0.68
    DIPSETTING
    0.68
    Hochspringen
    0.67
     Walkover
    0.62
     Waray
    0.61
    0.61
     fainted
    0.60
    Act Density 0.163%

    No Known Activations