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

    Neuronpedia

    INDEX
    Explanations

    words related to personality traits

    oai_token-act-pair · gpt-3.5-turbo

    mentions of personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    een
    -0.77
    REAM
    -0.75
    LOAD
    -0.73
    eries
    -0.72
    yer
    -0.70
    ERY
    -0.70
    anus
    -0.69
    ells
    -0.69
    WARE
    -0.67
    reek
    -0.66
    POSITIVE LOGITS
     personality
    1.05
     traits
    0.97
     trait
    0.95
     disorder
    0.93
    istically
    0.93
     charisma
    0.87
    istics
    0.86
     personalities
    0.85
     quirks
    0.83
    istical
    0.78
    Act Density 0.019%

    No Known Activations