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

    Neuronpedia

    INDEX
    Explanations

    words with specific phonetic patterns, particularly those that create a sense of uniqueness or distinctiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ores
    -0.21
    ãģįãģŁ
    -0.18
    tridge
    -0.16
    à¯įà®
    -0.16
    ook
    -0.16
    rics
    -0.15
    owski
    -0.15
    ziel
    -0.15
    ochen
    -0.14
    heets
    -0.14
    POSITIVE LOGITS
    les
    0.25
    ies
    0.25
    ie
    0.22
    ery
    0.21
    endor
    0.21
    ableObject
    0.20
    ertime
    0.20
    ings
    0.19
    ity
    0.19
    ernaut
    0.19
    Act Density 0.056%

    No Known Activations