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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.70
    ertain
    -0.68
     Corpus
    -0.67
    gom
    -0.65
    asia
    -0.61
    orporated
    -0.61
    ovies
    -0.60
    ":[
    -0.60
    terson
    -0.60
     Lima
    -0.60
    POSITIVE LOGITS
    senal
    1.46
    cliffe
    0.88
    uling
    0.81
    haps
    0.80
    fect
    0.78
    ansom
    0.77
    ascal
    0.76
    kj
    0.73
    interstitial
    0.73
    utherford
    0.71
    Act Density 0.175%

    No Known Activations