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

    Neuronpedia

    INDEX
    Explanations

    statements attributed to individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of proper nouns, particularly titles and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.82
    wcs
    -0.79
     unden
    -0.78
    anwhile
    -0.78
    arily
    -0.77
    ioned
    -0.72
    cember
    -0.69
     destro
    -0.69
     charact
    -0.67
     encount
    -0.67
    POSITIVE LOGITS
     Robot
    0.99
     Bezos
    0.95
     Speaker
    0.94
     Spock
    0.94
     Weasley
    0.94
     Snowden
    0.93
     Obama
    0.93
     Trump
    0.92
     McMahon
    0.92
     Musk
    0.92
    Act Density 0.038%

    No Known Activations