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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     particulars
    -0.72
    wired
    -0.71
    neys
    -0.71
     CPC
    -0.70
     circumstance
    -0.70
    ifiable
    -0.65
    ened
    -0.64
    ippers
    -0.64
    chens
    -0.63
    sheets
    -0.61
    POSITIVE LOGITS
    osta
    1.83
    velt
    0.80
    quez
    0.79
     Vald
    0.78
    ichi
    0.78
    regor
    0.73
     Cuomo
    0.73
    annis
    0.71
    hea
    0.71
    hei
    0.71
    Act Density 0.012%

    No Known Activations