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

    Neuronpedia

    INDEX
    Explanations

    terms related to operational practices and performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opers
    -0.20
    owing
    -0.18
    operands
    -0.16
    ling
    -0.16
    iest
    -0.15
    że
    -0.15
    OfType
    -0.15
    lers
    -0.15
    ahan
    -0.15
    rott
    -0.15
    POSITIVE LOGITS
    ally
    0.31
    ALLY
    0.23
    POSITE
    0.20
    ional
    0.19
    /function
    0.18
    posite
    0.18
    alley
    0.18
    ational
    0.17
    manual
    0.17
    365
    0.16
    Act Density 0.042%

    No Known Activations