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

    Neuronpedia

    INDEX
    Explanations

    phrases that prompt readers to check out or explore additional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    channelAvailability
    -0.72
    isSpecialOrderable
    -0.70
    roit
    -0.66
    Ö¼
    -0.65
    anguage
    -0.65
    matter
    -0.63
     territ
    -0.62
    ylum
    -0.60
    truth
    -0.60
    wig
    -0.60
    POSITIVE LOGITS
     what
    0.80
     whats
    0.78
    available
    0.72
     how
    0.68
     our
    0.67
     these
    0.66
     some
    0.65
     the
    0.62
     landmarks
    0.61
    apest
    0.61
    Act Density 0.107%

    No Known Activations