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

    Neuronpedia

    INDEX
    Explanations

    references to conflicts or battles, whether literal or metaphorical

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

    ongoing battles, past fights, or duration of conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.44
     quỷ
    -0.35
    ]")]
    -0.35
     okuyayım
    -0.35
     Ouvrez
    -0.35
     hyö
    -0.34
    RTLR
    -0.34
    iocene
    -0.34
    lewati
    -0.34
    NavigationView
    -0.34
    POSITIVE LOGITS
     fight
    1.04
     fought
    1.02
    fight
    0.94
    fought
    0.89
     battle
    0.88
     fights
    0.88
     FIGHT
    0.88
     fighting
    0.88
    Fight
    0.87
     Fight
    0.86
    Act Density 0.116%

    No Known Activations