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

    Neuronpedia

    INDEX
    Explanations

    names of individuals in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals associated with notable actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardon
    -0.91
    xon
    -0.82
    utsche
    -0.82
    lov
    -0.76
    osta
    -0.75
    illance
    -0.74
    alm
    -0.74
    iary
    -0.72
    Naz
    -0.71
    err
    -0.70
    POSITIVE LOGITS
     animate
    0.83
     Shirley
    0.76
    nces
    0.76
    nton
    0.73
     Iro
    0.72
     Lum
    0.72
     Sunder
    0.72
     plumbing
    0.72
     Hir
    0.71
     literacy
    0.71
    Act Density 0.028%

    No Known Activations