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

    Neuronpedia

    INDEX
    Explanations

    instances of specific procedural actions or events, particularly those involving formal decisions or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allas
    -0.16
    -exp
    -0.16
    imits
    -0.15
    ذر
    -0.15
    ź
    -0.15
    _EXP
    -0.15
     Chall
    -0.14
     ê
    -0.14
    одеÑĢж
    -0.14
    ifter
    -0.14
    POSITIVE LOGITS
    771
    0.16
    asper
    0.15
    ndern
    0.15
    ansi
    0.14
     Abb
    0.14
    Caught
    0.14
     freopen
    0.14
    Τα
    0.14
    æ¢
    0.14
     Rouge
    0.14
    Act Density 0.208%

    No Known Activations