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

    Neuronpedia

    INDEX
    Explanations

    keywords related to providing instructions or commands

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" and its emphasis in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.71
    ixel
    -0.69
    lav
    -0.67
    orney
    -0.62
    senal
    -0.61
    ascus
    -0.59
    luster
    -0.57
    definition
    -0.57
    interstitial
    -0.56
    glomer
    -0.56
    POSITIVE LOGITS
     kidding
    1.10
    ifications
    1.09
    ifiable
    0.99
    ices
    0.97
    if
    0.87
    icia
    0.87
    ifi
    0.87
     FY
    0.84
    itia
    0.83
     plain
    0.81
    Act Density 0.075%

    No Known Activations