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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals or places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of religious figures, specifically the Pope

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    milo
    -0.87
    eland
    -0.71
    Queue
    -0.70
    court
    -0.68
     lawy
    -0.64
    doors
    -0.64
    grave
    -0.63
     Nib
    -0.63
    Disk
    -0.63
    committee
    -0.63
    POSITIVE LOGITS
    choes
    0.65
    20439
    0.64
    ONG
    0.64
    ichick
    0.62
    hin
    0.62
    ishy
    0.61
    iami
    0.61
    pecially
    0.59
    pes
    0.59
    zik
    0.59
    Act Density 0.000%

    No Known Activations