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

    Neuronpedia

    INDEX
    Explanations

    references to notable figures, particularly authors and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     next
    -0.16
    Æ°Æ¡ng
    -0.14
     instead
    -0.14
     and
    -0.14
     ones
    -0.14
    :
    -0.14
    enger
    -0.14
     which
    -0.14
    â
    -0.13
     too
    -0.13
    POSITIVE LOGITS
    quoted
    0.25
     quoted
    0.25
     quote
    0.21
    -quote
    0.19
     Quotes
    0.19
     quoting
    0.18
     paraph
    0.18
     quotes
    0.18
    _quote
    0.18
    quotes
    0.18
    Act Density 0.058%

    No Known Activations