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

    Neuronpedia

    INDEX
    Explanations

    mentions of artistic, journalistic, or other types of work

    oai_token-act-pair · gpt-3.5-turbo

    references to work or contributions of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ukrain
    -0.71
    Args
    -0.70
     hurry
    -0.66
     actu
    -0.66
    IER
    -0.65
    charg
    -0.64
    AMI
    -0.63
    INTON
    -0.61
    ount
    -0.61
    itialized
    -0.60
    POSITIVE LOGITS
     ethic
    1.01
    flows
    1.00
    mates
    0.92
     internationally
    0.90
    mate
    0.85
    fulness
    0.83
    station
    0.81
    books
    0.80
    manship
    0.79
     ventures
    0.78
    Act Density 0.106%

    No Known Activations