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

    Neuronpedia

    INDEX
    Explanations

    references to software updates and bug fixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Norris
    -0.15
    ÙĪاÙĨ
    -0.14
    itus
    -0.14
    vary
    -0.14
    itution
    -0.13
    ider
    -0.13
    akes
    -0.13
    ä¸ĭæĿ¥
    -0.13
     @$_
    -0.13
     seas
    -0.13
    POSITIVE LOGITS
     minor
    0.26
    minor
    0.22
     Minor
    0.20
     fixes
    0.19
    Minor
    0.17
    ä¿®
    0.17
     cosmetic
    0.17
    رÙħ
    0.17
    _minor
    0.17
    زد
    0.16
    Act Density 0.049%

    No Known Activations