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

    Neuronpedia

    INDEX
    Explanations

    words associated with the concept of acknowledgment or attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vard
    -0.17
    ucken
    -0.15
    isser
    -0.15
     дÑĢа
    -0.15
    hani
    -0.15
    vak
    -0.15
    /stretch
    -0.15
    INFRINGEMENT
    -0.15
    .tk
    -0.15
    Outlined
    -0.14
    POSITIVE LOGITS
    aux
    0.15
    akis
    0.15
    YST
    0.14
    à¤ķ
    0.14
    ANGO
    0.14
     Stef
    0.14
    rib
    0.14
    ден
    0.14
     Mothers
    0.14
     coarse
    0.13
    Act Density 0.029%

    No Known Activations