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

    Neuronpedia

    INDEX
    Explanations

    terms related to attribution and citation practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     annot
    -0.16
     Maze
    -0.14
    icare
    -0.13
    utta
    -0.13
     Sullivan
    -0.13
    Å¡ÃŃ
    -0.13
    mony
    -0.13
     Temp
    -0.13
    bil
    -0.13
    anon
    -0.13
    POSITIVE LOGITS
    INUX
    0.17
    579
    0.16
    寸
    0.15
    ãĥ³ãĥĨ
    0.14
    Occurred
    0.14
    елеÑĦон
    0.14
    esti
    0.14
     Suite
    0.14
    _logits
    0.14
    UAL
    0.14
    Act Density 0.016%

    No Known Activations