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

    Neuronpedia

    INDEX
    Explanations

    references to numbered sections and chapters in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lisi
    -0.16
    unik
    -0.15
    ardu
    -0.14
    ilden
    -0.14
    activex
    -0.14
    urr
    -0.14
    leys
    -0.14
    hausen
    -0.14
    igkeit
    -0.14
    cie
    -0.13
    POSITIVE LOGITS
    aines
    0.15
     Jenner
    0.15
    \Abstract
    0.14
    ours
    0.14
     Hers
    0.14
     Na
    0.14
     bl
    0.14
    utex
    0.14
     Widow
    0.14
    arium
    0.14
    Act Density 0.022%

    No Known Activations