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

    Neuronpedia

    INDEX
    Explanations

    actions related to movement or physical interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tableFuture
    -0.52
    -0.51
    期刊论文
    -0.51
    ніципалі
    -0.49
     ब्रेकडाउन
    -0.49
    /******/
    -0.47
     ویکی‌پدیا
    -0.47
     resourceCulture
    -0.45
    ValueStyle
    -0.45
     Chwiliwch
    -0.45
    POSITIVE LOGITS
     again
    0.63
     wildly
    0.59
     quietly
    0.56
     normally
    0.55
     lightly
    0.54
     steadily
    0.53
     happily
    0.53
     together
    0.52
     badly
    0.51
     slowly
    0.51
    Act Density 0.124%

    No Known Activations