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

    Neuronpedia

    INDEX
    Explanations

    technical abbreviations and acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rc
    -0.20
    rl
    -0.18
    hide
    -0.17
    enheim
    -0.17
    hg
    -0.17
    rist
    -0.16
    rum
    -0.16
    ridor
    -0.16
    richt
    -0.16
    arest
    -0.16
    POSITIVE LOGITS
    (IT
    0.19
    etz
    0.18
    esseract
    0.17
    ET
    0.17
    etr
    0.17
    oler
    0.17
    imestep
    0.16
    BT
    0.16
    elen
    0.16
     ür
    0.16
    Act Density 0.084%

    No Known Activations