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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    actions or occurrences that involve attribution, generation, or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issue
    -0.67
    adier
    -0.62
    esan
    -0.61
    ierre
    -0.59
    hun
    -0.59
    arty
    -0.58
    hov
    -0.58
    ansky
    -0.56
    ttle
    -0.56
    cipled
    -0.56
    POSITIVE LOGITS
     by
    0.60
     srf
    0.60
     behavi
    0.60
    NESS
    0.57
     tradem
    0.57
    adoes
    0.57
    ocument
    0.56
    -+
    0.55
     BY
    0.55
     inconsist
    0.55
    Act Density 0.632%

    No Known Activations