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

    Neuronpedia

    INDEX
    Explanations

    discourse markers indicating a contrast or shift in thought

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

    but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElement
    -0.44
     mengen
    -0.43
    elance
    -0.41
    adpleegd
    -0.41
    ondata
    -0.40
    دانشنامهٔ
    -0.39
    naires
    -0.39
    %)$
    -0.39
    ţion
    -0.38
    apé
    -0.38
    POSITIVE LOGITS
    But
    1.23
     But
    1.13
     BUT
    0.92
    but
    0.90
    BUT
    0.88
     but
    0.79
    但
    0.74
     pero
    0.73
    Pero
    0.71
    Nhưng
    0.70
    Act Density 0.055%

    No Known Activations