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

    Neuronpedia

    INDEX
    Explanations

    references to speeches or presentations being delivered

    oai_token-act-pair · gpt-3.5-turbo

    words associated with the act of delivering information or presentations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issy
    -0.74
    king
    -0.69
    antage
    -0.69
    bi
    -0.68
    cum
    -0.68
    tic
    -0.67
    xia
    -0.65
    por
    -0.65
    cre
    -0.64
    bia
    -0.64
    POSITIVE LOGITS
    nesday
    0.90
    DeliveryDate
    0.84
    ocument
    0.81
    ĸļ
    0.81
    imentary
    0.78
     pione
    0.77
     aback
    0.77
    uled
    0.73
     behavi
    0.73
     by
    0.71
    Act Density 0.064%

    No Known Activations