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

    Neuronpedia

    INDEX
    Explanations

    references to terms related to redistribution and licensing conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĢή
    -0.15
    Ë
    -0.14
    UnderTest
    -0.14
    ije
    -0.14
     Dist
    -0.14
     ab
    -0.14
    Tel
    -0.14
    oppins
    -0.14
     dist
    -0.13
    ansk
    -0.13
    POSITIVE LOGITS
    gaard
    0.17
    uft
    0.15
    ynos
    0.15
    pawn
    0.15
    yii
    0.15
    yg
    0.15
    ุย
    0.14
    èĪ
    0.14
    YD
    0.14
    pdev
    0.14
    Act Density 0.007%

    No Known Activations