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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals and references to collateral in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ld
    -0.79
    BOOK
    -0.79
    iling
    -0.78
    ħĭ
    -0.77
    gress
    -0.76
    wife
    -0.75
    restling
    -0.74
    dream
    -0.74
    ught
    -0.72
    liquid
    -0.72
    POSITIVE LOGITS
    ity
    0.90
     GOODMAN
    0.83
    ization
    0.74
    onite
    0.73
    izations
    0.69
    ateral
    0.68
    ized
    0.66
    ificate
    0.66
    isations
    0.64
     Clement
    0.64
    Act Density 0.101%

    No Known Activations