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

    Neuronpedia

    INDEX
    Explanations

    expressions of reluctance or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    attery
    -0.17
    illo
    -0.15
    aining
    -0.14
    çŃĭ
    -0.14
    гÑĢа
    -0.14
    Äįku
    -0.14
    inning
    -0.14
     Latter
    -0.13
    neys
    -0.13
     architecture
    -0.13
    POSITIVE LOGITS
    TD
    0.16
    ucle
    0.15
    warts
    0.15
    _Handler
    0.15
    ombat
    0.15
    TEL
    0.15
    ovy
    0.14
    ëŀ
    0.14
    fic
    0.14
    hog
    0.14
    Act Density 0.136%

    No Known Activations