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

    Neuronpedia

    INDEX
    Explanations

    elements related to tactical and strategic gameplay in war settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jails
    -0.15
     jail
    -0.15
    elsea
    -0.14
     Jail
    -0.14
    aras
    -0.14
     kidnapped
    -0.14
     jailed
    -0.14
     abducted
    -0.14
     surveillance
    -0.14
     hostages
    -0.14
    POSITIVE LOGITS
     EC
    0.23
     AC
    0.23
     scenario
    0.23
     scenarios
    0.22
     historical
    0.22
     Historical
    0.22
     Rules
    0.21
     Scenario
    0.21
     ump
    0.21
     rules
    0.21
    Act Density 0.018%

    No Known Activations