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

    Neuronpedia

    INDEX
    Explanations

    words related to instant actions or responses

    oai_token-act-pair · gpt-3.5-turbo

    the term "instant" and its derivatives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.97
    pherd
    -0.79
    atche
    -0.78
    bard
    -0.77
    ALD
    -0.77
    byss
    -0.76
    anners
    -0.75
    avid
    -0.73
    llah
    -0.71
    unal
    -0.71
    POSITIVE LOGITS
    aneously
    2.00
    aneous
    1.46
     gratification
    1.44
    iations
    1.31
    iation
    1.28
    iated
    1.22
    iating
    1.19
     replay
    1.12
    iate
    1.01
    iates
    0.98
    Act Density 0.014%

    No Known Activations