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

    Neuronpedia

    INDEX
    Explanations

    keywords related to system configurations or setup instructions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.86
    utenberg
    -0.74
    ptives
    -0.68
    ptin
    -0.65
    ëĭ
    -0.64
    amus
    -0.64
    rums
    -0.63
    ptive
    -0.63
    jah
    -0.63
    perse
    -0.62
    POSITIVE LOGITS
     behalf
    1.33
     occasion
    1.06
    erous
    1.06
    shore
    1.02
    coming
    0.98
    sets
    0.98
    screen
    0.91
    eday
    0.90
    site
    0.86
    anism
    0.86
    Act Density 0.184%

    No Known Activations