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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to adversarial entities, particularly "enemy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.73
    WithIOException
    -0.67
    Personendaten
    -0.65
     ujednoznacz
    -0.63
    contentLoaded
    -0.62
     nî
    -0.61
     referenties
    -0.60
     незавершена
    -0.59
    buttonBar
    -0.59
    ьаж
    -0.59
    POSITIVE LOGITS
     enemy
    1.35
     enemies
    1.11
     Enemy
    1.10
    enemy
    1.08
    Enemy
    1.01
     nemico
    1.00
     musuh
    0.97
     opponent
    0.95
    敵
    0.95
     ennemi
    0.95
    Act Density 0.707%

    No Known Activations