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

    Neuronpedia

    INDEX
    Explanations

    references to humility and the nature of self-worth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obus
    -0.15
    ALA
    -0.15
    ifix
    -0.15
    oya
    -0.15
     Goddess
    -0.14
    御
    -0.14
    ActionCode
    -0.14
    earable
    -0.14
    дон
    -0.14
     Donovan
    -0.14
    POSITIVE LOGITS
     experimental
    0.17
    experimental
    0.17
     Christ
    0.17
     Ung
    0.17
     Experimental
    0.17
    Experimental
    0.17
     Bun
    0.16
    èĴĻ
    0.16
    kova
    0.15
     cords
    0.15
    Act Density 0.100%

    No Known Activations