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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty and the necessity to confirm or clarify information

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

    after "be" or "for" that imply certainty

    np_acts-logits-general · gemini-2.0-flash

    expressing certainty or assurance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iann
    -0.54
    loài
    -0.47
    TestingModule
    -0.45
    olle
    -0.44
    OrWhiteSpace
    -0.44
    RenderAtEndOf
    -0.43
    ]<<"
    -0.43
    gbaar
    -0.43
     Implications
    -0.42
    eros
    -0.42
    POSITIVE LOGITS
     sure
    2.08
     certainty
    1.83
     assured
    1.76
    sure
    1.76
     SURE
    1.70
    Sure
    1.52
     assure
    1.52
     certeza
    1.51
     assurance
    1.50
     guarantee
    1.50
    Act Density 0.245%

    No Known Activations