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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or results

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

    origin or reason from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.55
     صوتيه
    -0.47
    DoubleQuotes
    -0.46
    تقاوى
    -0.46
    Rhestr
    -0.44
     désolés
    -0.44
    ')")
    -0.41
    ThemeOverlay
    -0.41
    RetentionPolicy
    -0.41
     مشين
    -0.40
    POSITIVE LOGITS
     nasce
    0.46
     powsta
    0.42
     deriva
    0.41
    都是
    0.40
     entirely
    0.40
     sengaja
    0.40
     ontstaan
    0.40
     frutto
    0.39
     مصنوع
    0.39
     derived
    0.38
    Act Density 0.456%

    No Known Activations