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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governmental laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    the frequent use of the word "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iates
    -0.69
    onso
    -0.68
    dom
    -0.67
    uld
    -0.67
    urry
    -0.67
    town
    -0.64
    icism
    -0.64
    osate
    -0.63
    ossom
    -0.62
    ileaks
    -0.61
    POSITIVE LOGITS
    senal
    1.20
    wolves
    1.02
     hereby
    0.93
     supposed
    0.91
     usually
    0.88
    nt
    0.88
    wolf
    0.87
     not
    0.87
     currently
    0.86
     generally
    0.84
    Act Density 0.355%

    No Known Activations