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

    Neuronpedia

    INDEX
    Explanations

    sequences of colons or variants related to key-value pairs in structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledon
    -0.16
    Ùĭا
    -0.15
    ök
    -0.15
    weg
    -0.14
    он
    -0.14
    lington
    -0.14
    êt
    -0.14
    readcrumb
    -0.14
    ervers
    -0.14
    amework
    -0.14
    POSITIVE LOGITS
    ones
    0.16
    ermo
    0.15
    usk
    0.14
    ienes
    0.14
    ูà¸ķร
    0.13
    ).__
    0.13
    еÑĤи
    0.13
    åĭ¢
    0.13
    erd
    0.13
    eric
    0.13
    Act Density 0.026%

    No Known Activations