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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and inquiries directed at the audience

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

    Sentences starting with "you" or "he"

    np_acts-logits-general · gemini-2.0-flash

    you need support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISODE
    -0.52
     发表于
    -0.52
    sinon
    -0.50
    Blame
    -0.49
     sorte
    -0.49
     lenker
    -0.49
    CloseOperation
    -0.49
    kurs
    -0.48
     đích
    -0.48
    RegressionTest
    -0.48
    POSITIVE LOGITS
     interested
    0.71
    StoryboardSegue
    0.70
    uestions
    0.69
     spørgsmål
    0.67
    躇
    0.67
    questions
    0.67
     frågor
    0.65
     questions
    0.65
     Interested
    0.65
     intéress
    0.64
    Act Density 0.119%

    No Known Activations