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

    Neuronpedia

    INDEX
    Explanations

    references to acts of violence and murder

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

    assassination and murder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.49
     swelled
    -0.48
     swell
    -0.47
     consolidation
    -0.43
     sve
    -0.42
     समीक्षाओं
    -0.42
    estacks
    -0.42
     compliments
    -0.42
    Sve
    -0.42
     improvement
    -0.42
    POSITIVE LOGITS
     murder
    0.68
     assassinated
    0.65
     asesinado
    0.64
    murder
    0.63
     asesinato
    0.61
     murdered
    0.60
    EndContext
    0.59
    Murder
    0.57
     assassination
    0.56
     Murder
    0.54
    Act Density 0.040%

    No Known Activations