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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate combat or confrontation against evil forces or organizations

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

    Battles, defeat, or occupation

    np_acts-logits-general · gemini-2.0-flash

    fight evil antagonist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.61
    ]]:
    -0.56
    titleMargin
    -0.54
    ')):
    -0.54
    ]})
    -0.53
    (")");
    -0.53
    gaged
    -0.52
    VYMaps
    -0.52
     kotlinx
    -0.51
    )');
    -0.51
    POSITIVE LOGITS
     enemy
    1.05
     evil
    0.85
    enemy
    0.83
     Enemy
    0.82
     adversary
    0.81
    Evil
    0.80
     enemies
    0.80
     ennemi
    0.79
    evil
    0.79
     nemico
    0.78
    Act Density 0.593%

    No Known Activations