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

    Neuronpedia

    INDEX
    Explanations

    references to causes and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ize
    -0.17
    aryl
    -0.15
    izable
    -0.15
    asks
    -0.15
    eters
    -0.15
    aved
    -0.15
    ayload
    -0.14
    oug
    -0.14
    ti
    -0.14
    avery
    -0.14
    POSITIVE LOGITS
     cél
    0.31
    -effect
    0.29
     cele
    0.26
    way
    0.23
    lessly
    0.19
    ways
    0.19
    effect
    0.19
    lesh
    0.18
    WAY
    0.17
    UTION
    0.17
    Act Density 0.043%

    No Known Activations