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

    Neuronpedia

    INDEX
    Explanations

    references to conflict and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    victim
    -0.17
     Victims
    -0.15
     victim
    -0.15
     victims
    -0.15
    913
    -0.14
    ostringstream
    -0.14
     Victim
    -0.14
    itorio
    -0.14
     innocent
    -0.14
     Warrior
    -0.14
    POSITIVE LOGITS
     enemy
    0.23
     foe
    0.20
     spoilers
    0.20
     enemies
    0.19
     opponent
    0.18
     Enemy
    0.18
     evil
    0.18
     adversary
    0.18
     dangerous
    0.17
     opponents
    0.17
    Act Density 0.400%

    No Known Activations