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

    Neuronpedia

    INDEX
    Explanations

    strong emphasis on specific numbers or codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or codes related to specifications or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    netflix
    -0.83
    rely
    -0.73
    TextColor
    -0.73
    inic
    -0.65
    stood
    -0.64
    rette
    -0.64
    unct
    -0.64
    ques
    -0.63
    deen
    -0.60
    inas
    -0.60
    POSITIVE LOGITS
    acity
    1.08
     Downing
    0.91
    th
    0.86
    586
    0.83
    ^{
    0.83
    Gb
    0.83
    40
    0.83
    %"
    0.82
    tons
    0.82
    84
    0.80
    Act Density 0.073%

    No Known Activations