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

    Neuronpedia

    INDEX
    Explanations

    language related to obligations and duties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sentence starts with conjunction or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.60
    tableFuture
    -0.56
    帖最后由
    -0.53
    TestingModule
    -0.51
     pien
    -0.50
    ніципа
    -0.50
     jengibre
    -0.50
     Verſ
    -0.49
    Duty
    -0.47
     estadounid
    -0.47
    POSITIVE LOGITS
    <?,
    0.36
    taminophen
    0.34
    Xna
    0.32
     setuptools
    0.31
     discouraging
    0.29
    djangoproject
    0.29
     Umgang
    0.28
    彼
    0.28
    COGN
    0.28
    ogly
    0.28
    Act Density 0.029%

    No Known Activations