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

    Neuronpedia

    INDEX
    Explanations

    programming structures and syntax within code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andler
    -0.16
    AGMA
    -0.14
    λεÏħ
    -0.14
    ripp
    -0.14
    ::↵
    -0.14
    STS
    -0.13
    embed
    -0.13
    ìŀ¡
    -0.13
     safety
    -0.13
    xBC
    -0.13
    POSITIVE LOGITS
    226
    0.14
    iser
    0.14
     USAGE
    0.14
    imps
    0.14
    ÂĿ
    0.14
     JADX
    0.14
     actionTypes
    0.13
    illery
    0.13
    ediator
    0.13
    ná
    0.13
    Act Density 0.054%

    No Known Activations