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

    Neuronpedia

    INDEX
    Explanations

    instances of testing and documentation-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oro
    -0.17
     rum
    -0.17
     *</
    -0.15
    .*↵
    -0.15
     Gibbs
    -0.14
    atalog
    -0.14
     tum
    -0.14
    ao
    -0.14
    Äħd
    -0.14
     Editorial
    -0.13
    POSITIVE LOGITS
    kla
    0.16
    æ§
    0.16
    Ế
    0.16
    agli
    0.15
    ãĥ¬ãĤ¹
    0.15
    ivar
    0.15
    ospace
    0.15
    oundary
    0.15
    _kw
    0.14
    thouse
    0.14
    Act Density 0.015%

    No Known Activations