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

    Neuronpedia

    INDEX
    Explanations

    instances where individuals are under coercive or harmful conditions

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

    subjected to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Чыганаклар
    -0.52
     незавершена
    -0.50
    Personendaten
    -0.49
    isseaux
    -0.46
     ujednoznacz
    -0.46
    messenger
    -0.44
     Affaires
    -0.43
    はじめに
    -0.43
    SourceChecksum
    -0.43
    LookAnd
    -0.43
    POSITIVE LOGITS
     subjected
    0.90
     subjecting
    0.68
     undergone
    0.64
     endforeach
    0.58
     undergoing
    0.58
     undergo
    0.57
     imposed
    0.55
     subjection
    0.54
     underwent
    0.54
     undergoes
    0.52
    Act Density 0.018%

    No Known Activations