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

    Neuronpedia

    INDEX
    Explanations

    references to structured message formats or protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esome
    -0.17
    som
    -0.15
    esser
    -0.15
    essler
    -0.15
    side
    -0.15
    iedo
    -0.14
    /preferences
    -0.14
    ture
    -0.14
    seen
    -0.14
    aver
    -0.14
    POSITIVE LOGITS
    ores
    0.18
    urg
    0.15
    aland
    0.15
    oldur
    0.14
    antry
    0.14
    stell
    0.14
    au
    0.14
    olib
    0.14
    orney
    0.14
    yntax
    0.14
    Act Density 0.039%

    No Known Activations