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

    Neuronpedia

    INDEX
    Explanations

    attributes of characters in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ei
    -0.16
    eus
    -0.15
    á»ĩ
    -0.15
    ected
    -0.15
    clamp
    -0.15
    y
    -0.15
    eum
    -0.15
    clud
    -0.14
    a
    -0.14
    ATCH
    -0.14
    POSITIVE LOGITS
    heid
    0.28
    heits
    0.19
    heit
    0.18
    igkeit
    0.17
    weg
    0.17
    eness
    0.16
    este
    0.16
    IDAD
    0.16
    keiten
    0.16
    keit
    0.15
    Act Density 0.065%

    No Known Activations