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

    Neuronpedia

    INDEX
    Explanations

    references to software development issues and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hel
    -0.18
    asons
    -0.16
    FIXME
    -0.15
    anel
    -0.14
    -fw
    -0.14
    osy
    -0.14
    artin
    -0.14
    paces
    -0.14
     Hud
    -0.14
    -cigaret
    -0.14
    POSITIVE LOGITS
    eyse
    0.16
     Dex
    0.14
    yte
    0.14
    ืà¸Ńà¸Ĥ
    0.14
     Erk
    0.14
     Thy
    0.14
    ionales
    0.13
    bbing
    0.13
    aved
    0.13
     therm
    0.13
    Act Density 0.023%

    No Known Activations