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

    Neuronpedia

    INDEX
    Explanations

    instances of threats and violence in the context of conflict

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

    before verbs of aggression/destruction

    np_acts-logits-general · gemini-2.0-flash

    defeat and destruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.71
     ſein
    -0.59
     continúas
    -0.58
     itſelf
    -0.57
    MouseListener
    -0.56
    LookAnd
    -0.56
    uxxxx
    -0.55
     chofe
    -0.53
    TagMode
    -0.52
     ſche
    -0.52
    POSITIVE LOGITS
     pum
    1.03
     decim
    1.00
     pulver
    0.98
     beat
    0.97
     annihilated
    0.96
     obliter
    0.95
     annihil
    0.89
     obliterated
    0.89
     slaughter
    0.85
     slaughtered
    0.84
    Act Density 0.334%

    No Known Activations