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

    Neuronpedia

    INDEX
    Explanations

    negative phrases indicating absence or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eger
    -0.19
    arus
    -0.15
    Canceled
    -0.14
    ÑĨÑİ
    -0.13
    illa
    -0.13
    ìļĶìĿ¼
    -0.13
    esters
    -0.13
    UBLISH
    -0.13
    æľ¨
    -0.13
    StateChanged
    -0.13
    POSITIVE LOGITS
     altogether
    0.17
    olini
    0.16
    âĸłâĸł
    0.15
     Tw
    0.14
    INTER
    0.14
    sth
    0.14
    tw
    0.14
    tor
    0.14
    ereco
    0.14
    odal
    0.14
    Act Density 0.265%

    No Known Activations