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

    Neuronpedia

    INDEX
    Explanations

    technical programming terminology and code-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ضÙĬ
    -0.16
    652
    -0.16
    .qual
    -0.15
     Morav
    -0.15
    ucken
    -0.15
    nesty
    -0.15
    ritz
    -0.15
    assin
    -0.14
    tright
    -0.14
    .mozilla
    -0.14
    POSITIVE LOGITS
    ries
    0.17
    eder
    0.16
    ähl
    0.16
    oby
    0.14
    endl
    0.14
    onte
    0.14
    prime
    0.13
    acus
    0.13
     instead
    0.13
     barric
    0.13
    Act Density 0.149%

    No Known Activations