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

    Neuronpedia

    INDEX
    Explanations

    key numeric and statistical relationships or representations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apor
    -0.18
    amarin
    -0.16
    izu
    -0.16
    ,readonly
    -0.15
    addock
    -0.15
    ufe
    -0.14
    ادÙĦ
    -0.14
    onden
    -0.14
    imar
    -0.13
    umat
    -0.13
    POSITIVE LOGITS
    arks
    0.17
    sembler
    0.16
    fos
    0.14
    Å¡e
    0.14
    rollers
    0.14
    sprites
    0.14
    ystore
    0.14
     Tro
    0.14
    rac
    0.14
    tro
    0.13
    Act Density 0.061%

    No Known Activations