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

    Neuronpedia

    INDEX
    Explanations

    terms and references related to dependencies and relationships in narrative structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ze
    -0.16
    .ascii
    -0.16
    ndl
    -0.15
    æľ¯
    -0.14
     hat
    -0.14
    cola
    -0.14
    statt
    -0.14
    hed
    -0.14
    ator
    -0.14
    IK
    -0.13
    POSITIVE LOGITS
    iscard
    0.18
    istra
    0.16
    лаг
    0.16
    ãĥ¼ãĤ¹ãĥĪ
    0.15
    chai
    0.15
    esson
    0.15
    aphael
    0.14
    asure
    0.14
    uhan
    0.14
    pter
    0.14
    Act Density 0.001%

    No Known Activations