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

    Neuronpedia

    INDEX
    Explanations

    instances where communication or discussion about concepts or topics occurs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utzer
    -0.17
    enton
    -0.15
    duk
    -0.15
    ãĥĭãĤ¢
    -0.15
    Endpoints
    -0.15
    toDouble
    -0.14
    crast
    -0.14
    enos
    -0.14
    atrix
    -0.14
    artner
    -0.14
    POSITIVE LOGITS
    WithString
    0.14
    istream
    0.14
    OTE
    0.14
     misog
    0.14
     pad
    0.14
    ойно
    0.14
    ison
    0.13
    ua
    0.13
    'n
    0.13
    315
    0.13
    Act Density 0.136%

    No Known Activations