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

    Neuronpedia

    INDEX
    Explanations

    elements related to conflict and combat in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onauts
    -0.52
    addPreferredGap
    -0.48
    delwed
    -0.47
    ffindor
    -0.47
    AutoScaleMode
    -0.46
     untrained
    -0.45
    BeginContext
    -0.44
    featureID
    -0.43
     createSprite
    -0.43
    ViewFeatures
    -0.42
    POSITIVE LOGITS
     evil
    1.08
     villain
    0.99
     villains
    0.87
    evil
    0.86
     Evil
    0.84
    Evil
    0.80
    villain
    0.76
     sinister
    0.74
     зло
    0.73
     villa
    0.72
    Act Density 0.576%

    No Known Activations