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

    Neuronpedia

    INDEX
    Explanations

    programming terms and syntactical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abwe
    -0.16
    addtogroup
    -0.16
    اÛĮÙĩ
    -0.15
    æ¸Ī
    -0.14
    umba
    -0.14
    uttle
    -0.14
    .EVT
    -0.13
    esinde
    -0.13
     retard
    -0.13
    styl
    -0.13
    POSITIVE LOGITS
    gree
    0.17
    .impl
    0.16
    icher
    0.15
    zej
    0.14
    ogle
    0.14
    agma
    0.14
    dk
    0.14
    ëŀĮ
    0.14
     warning
    0.14
     Bye
    0.14
    Act Density 0.451%

    No Known Activations