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

    Neuronpedia

    INDEX
    Explanations

    information related to personal anecdotes, historical events, political discussions, and legal matters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    iov
    -0.87
     TOUR
    -0.87
    uay
    -0.84
     Osw
    -0.78
    ivas
    -0.77
    iom
    -0.77
    rand
    -0.77
    atem
    -0.76
    sth
    -0.76
    uci
    -0.76
    POSITIVE LOGITS
    ffer
    0.82
     audition
    0.82
     fulfil
    0.77
     emergencies
    0.77
    uana
    0.76
     gunmen
    0.73
     unsuspecting
    0.73
     deliveries
    0.72
     inspections
    0.72
     audiences
    0.72
    Act Density 0.495%

    No Known Activations