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

    Neuronpedia

    INDEX
    Explanations

    descriptions of actions involving combat or confrontation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.68
    Personendaten
    -0.67
     ujednoznacz
    -0.66
     الرياضيه
    -0.64
    GeneratedMessage
    -0.60
    IActionResult
    -0.59
    NameInMap
    -0.58
     saites
    -0.54
     BorderRadius
    -0.54
    windowFixed
    -0.53
    POSITIVE LOGITS
     enemy
    1.85
     enemies
    1.76
     opponents
    1.74
     opponent
    1.72
     foes
    1.59
    enemy
    1.54
     foe
    1.52
     adversaries
    1.48
     adversary
    1.45
     opposition
    1.39
    Act Density 0.455%

    No Known Activations