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

    Neuronpedia

    INDEX
    Explanations

    people's names, particularly first names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those starting with the letter 'C'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACTED
    -0.67
     Haitian
    -0.63
    _-
    -0.60
    theless
    -0.60
     Romanian
    -0.59
     dime
    -0.57
     Seym
    -0.56
    ropolitan
    -0.55
     âĸĪ
    -0.54
    ׾
    -0.54
    POSITIVE LOGITS
    acca
    0.90
    ohan
    0.81
    reau
    0.79
    lear
    0.76
    anyon
    0.70
    aney
    0.69
    grain
    0.68
    ensen
    0.68
    orne
    0.68
    rouse
    0.68
    Act Density 0.129%

    No Known Activations