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

    Neuronpedia

    INDEX
    Explanations

    questions directed at the reader or listener

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    878
    -0.17
    cz
    -0.16
    cete
    -0.16
    acre
    -0.15
    awy
    -0.15
    ofire
    -0.15
    fone
    -0.14
    268
    -0.14
     Gaw
    -0.14
    swick
    -0.14
    POSITIVE LOGITS
    á»Ĺ
    0.16
    iki
    0.16
    ied
    0.15
    æIJ
    0.15
    ISIBLE
    0.14
    elan
    0.14
    мен
    0.14
    ¥IJ
    0.14
    egt
    0.14
    undry
    0.14
    Act Density 0.017%

    No Known Activations