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

    Neuronpedia

    INDEX
    Explanations

    details related to mathematical variables and structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    withstanding
    -0.94
    ®:
    -0.80
    ®-
    -0.79
    NUMX
    -0.78
    UIControlState
    -0.77
    Vidite
    -0.76
    tably
    -0.76
    etheless
    -0.76
    queous
    -0.74
    Manbalar
    -0.72
    POSITIVE LOGITS
    y
    0.83
    e
    0.80
    t
    0.69
    a
    0.68
    enium
    0.67
    o
    0.64
    oco
    0.61
    loway
    0.61
    Ronnie
    0.61
    مانية
    0.60
    Act Density 0.280%

    No Known Activations