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

    Neuronpedia

    INDEX
    Explanations

    instances of targeting, threats, and assassination in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abestanden
    -0.56
    setupUi
    -0.55
    σια
    -0.52
    roxene
    -0.52
    esModule
    -0.50
     pastas
    -0.50
    ETING
    -0.49
    Verkehr
    -0.49
    Citiți
    -0.49
    createComponent
    -0.49
    POSITIVE LOGITS
     attacking
    1.11
     targeting
    1.09
     targets
    1.08
     attack
    1.03
     attacks
    0.99
     targeted
    0.95
     target
    0.94
     attacked
    0.94
     Targeting
    0.93
    Targeting
    0.92
    Act Density 0.501%

    No Known Activations