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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the concept of exclusion or avoidance

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

    out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.71
     дописавши
    -0.56
    Personendaten
    -0.54
    ✨:
    -0.52
    GTCX
    -0.50
    Демографія
    -0.50
     Conjug
    -0.48
    ativement
    -0.48
    CodedInputStream
    -0.47
    nsic
    -0.47
    POSITIVE LOGITS
    为了
    0.64
    是为了
    0.57
    เพื่อ
    0.54
     afin
    0.54
    為了
    0.53
     щоб
    0.52
     כדי
    0.51
     hopes
    0.50
     because
    0.49
     بهد
    0.48
    Act Density 0.257%

    No Known Activations