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

    Neuronpedia

    INDEX
    Explanations

    phrases related to downloading files or content

    oai_token-act-pair · gpt-3.5-turbo

    references to downloading or accessing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¢âĢ¢
    -0.78
    mire
    -0.73
    âĺħâĺħ
    -0.70
    amer
    -0.69
    Iowa
    -0.69
    Party
    -0.67
    ILE
    -0.66
    Jo
    -0.66
    chron
    -0.65
    CCC
    -0.63
    POSITIVE LOGITS
     selves
    1.35
    atically
    1.29
    selves
    1.27
    atic
    1.15
    self
    1.00
    henko
    0.77
    atics
    0.77
     conduc
    0.77
    MpServer
    0.76
     individually
    0.73
    Act Density 0.128%

    No Known Activations