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

    Neuronpedia

    INDEX
    Explanations

    references to representative, reproductive, or legislation-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estar
    -0.18
    lah
    -0.17
    못
    -0.16
    vyk
    -0.16
    aneous
    -0.16
    imuth
    -0.15
    NDER
    -0.15
    CKER
    -0.15
    bred
    -0.15
    lama
    -0.15
    POSITIVE LOGITS
    roduction
    0.35
    ertoire
    0.35
    licas
    0.34
    lication
    0.33
    rodu
    0.33
    rieve
    0.31
    airs
    0.31
    licate
    0.31
    licated
    0.29
    roduced
    0.29
    Act Density 0.017%

    No Known Activations