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

    Neuronpedia

    INDEX
    Explanations

    specific terms and keywords associated with structured data or coding language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isseur
    -0.17
    633
    -0.17
    itud
    -0.16
    udget
    -0.15
    urgeon
    -0.15
    ctest
    -0.15
    xis
    -0.14
    forth
    -0.14
    \<^
    -0.14
    forward
    -0.14
    POSITIVE LOGITS
    aeda
    0.16
    anz
    0.16
    aldo
    0.15
    reen
    0.15
    dera
    0.14
    /gin
    0.14
    zm
    0.14
    unma
    0.14
    ãĥ¼ãĥľ
    0.13
    akh
    0.13
    Act Density 0.002%

    No Known Activations