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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "word" with various contexts and related terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the concept of 'word' and its usage in discussions about communication or expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thumbnails
    -0.75
    abal
    -0.68
     generational
    -0.65
    çī
    -0.63
     Instit
    -0.61
    archives
    -0.61
    idon
    -0.60
     Perspect
    -0.60
     summar
    -0.59
    Catal
    -0.58
    POSITIVE LOGITS
    THING
    0.95
     dime
    0.94
     ounce
    0.92
     whatsoever
    0.88
     whiff
    0.81
     EVER
    0.81
    BLE
    0.78
     slightest
    0.78
    baugh
    0.77
    ODY
    0.72
    Act Density 0.405%

    No Known Activations