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

    Neuronpedia

    INDEX
    Explanations

    numeric values and specific section references in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.67
    AccessorTable
    -0.66
     otomatig
    -0.65
    encodeWith
    -0.61
    هة
    -0.59
    onacci
    -0.59
     rang
    -0.58
     FontWeight
    -0.57
    otheby
    -0.57
    agna
    -0.57
    POSITIVE LOGITS
    subsubsection
    0.88
    subsection
    0.71
    ︎
    0.63
     itſelf
    0.60
     sûr
    0.60
     relever
    0.56
     Moderato
    0.55
     hinaus
    0.55
    +#+#
    0.55
     myſelf
    0.54
    Act Density 0.355%

    No Known Activations