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

    Neuronpedia

    INDEX
    Explanations

    references to websites and their formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leigh
    -0.19
    anking
    -0.16
    arend
    -0.15
    forge
    -0.15
    atural
    -0.14
    crew
    -0.14
    raries
    -0.14
    ว
    -0.14
    aar
    -0.13
    ovement
    -0.13
    POSITIVE LOGITS
    igar
    0.15
    ondo
    0.15
    irut
    0.14
     nextState
    0.14
    èŃ
    0.14
    ovsky
    0.14
    Ñīин
    0.13
     submodule
    0.13
     DAL
    0.13
    eka
    0.13
    Act Density 0.216%

    No Known Activations