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

    Neuronpedia

    INDEX
    Explanations

    words related to separation or division

    oai_token-act-pair · gpt-3.5-turbo

    mentions of paralysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.92
    OME
    -0.78
    士
    -0.76
    éĹĺ
    -0.73
    ¥µ
    -0.73
    ELD
    -0.72
     Carbuncle
    -0.71
    hower
    -0.71
    hirt
    -0.69
    andestine
    -0.67
    POSITIVE LOGITS
    allel
    1.03
    ietal
    0.95
    rot
    0.94
    amount
    0.93
    abolic
    0.91
    anoia
    0.90
    ison
    0.89
    rots
    0.88
    icularly
    0.86
    agraph
    0.86
    Act Density 0.015%

    No Known Activations