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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their usage in questions and statements

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

    should or should not happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     did
    -0.79
     Did
    -0.74
    Did
    -0.71
    did
    -0.62
     DID
    -0.49
    DID
    -0.39
    のかもしれません
    -0.33
     try
    -0.32
    complexType
    -0.32
     favored
    -0.30
    POSITIVE LOGITS
    should
    0.96
     should
    0.92
    Should
    0.88
     Should
    0.84
     shouldnt
    0.76
     shouldn
    0.74
     debería
    0.73
     dovrebbe
    0.72
     invokingState
    0.72
     ſhould
    0.71
    Act Density 0.195%

    No Known Activations