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

    Neuronpedia

    INDEX
    Explanations

    references to "character" and related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    day
    -0.18
    elyn
    -0.17
    ary
    -0.17
    ery
    -0.17
    inand
    -0.15
    seo
    -0.15
    yi
    -0.15
    amer
    -0.15
    orget
    -0.15
    ÑĢа
    -0.14
    POSITIVE LOGITS
    istically
    0.36
    istics
    0.26
    izations
    0.26
    istik
    0.24
    izes
    0.22
    ISTICS
    0.21
    isation
    0.20
    itics
    0.20
    izing
    0.20
    ised
    0.20
    Act Density 0.036%

    No Known Activations