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

    Neuronpedia

    INDEX
    Explanations

    negations and contradictions in statements

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

    Contractions ending in "n't"

    np_acts-logits-general · gemini-2.0-flash

    wouldn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    פיה
    -0.53
    Permalink
    -0.50
     Item
    -0.47
    誼
    -0.47
     luas
    -0.47
     localVar
    -0.46
     Bar
    -0.46
    iak
    -0.45
    Bar
    -0.45
    ik
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    1.29
     تضيفلها
    1.23
    ьаж
    1.19
     дописавши
    1.12
     necessarily
    1.12
    Rhestr
    1.10
    mybatisplus
    1.10
    theless
    1.08
    Hauptartikel
    1.07
     للاسماء
    1.07
    Act Density 0.106%

    No Known Activations