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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illet
    -0.15
    AAAAAAAA
    -0.15
    loor
    -0.14
    à¸Ĺย
    -0.14
    ÑģÑĮ
    -0.14
    žen
    -0.14
    idelberg
    -0.13
    tega
    -0.13
    dej
    -0.13
    emean
    -0.13
    POSITIVE LOGITS
    zers
    0.29
    zer
    0.26
    za
    0.18
    zas
    0.17
    talk
    0.16
     Lever
    0.15
    www
    0.15
    indr
    0.15
    outh
    0.15
    ös
    0.15
    Act Density 0.046%

    No Known Activations