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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "used."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oud
    -0.17
    aggio
    -0.17
    pillar
    -0.15
    uchi
    -0.14
    ella
    -0.14
    olest
    -0.14
    olia
    -0.14
    ůst
    -0.13
    aggi
    -0.13
    /use
    -0.13
    POSITIVE LOGITS
    mir
    0.15
     yo
    0.14
    entic
    0.14
    Pen
    0.13
    entes
    0.13
    /common
    0.13
    hek
    0.13
    âĢŀN
    0.13
    Ñı
    0.13
    uzey
    0.13
    Act Density 0.067%

    No Known Activations