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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating specific structural features or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lester
    -0.15
    usta
    -0.14
    inski
    -0.14
    ppy
    -0.14
    hawks
    -0.14
    ych
    -0.14
    monic
    -0.14
    icont
    -0.14
    eer
    -0.14
    innacle
    -0.14
    POSITIVE LOGITS
    ologne
    0.16
    ngth
    0.15
    ä¹ĭä¸Ģ
    0.14
    zeÅĪ
    0.14
    maz
    0.14
    noch
    0.13
     صاØŃ
    0.13
    olie
    0.13
    atas
    0.13
    665
    0.13
    Act Density 0.009%

    No Known Activations