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

    Neuronpedia

    INDEX
    Explanations

    physical actions and violence-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entities
    -0.62
    typename
    -0.61
     Bill
    -0.61
     Gull
    -0.60
    兮
    -0.57
    luri
    -0.56
    贼
    -0.55
    cemment
    -0.54
     C
    -0.53
    alej
    -0.53
    POSITIVE LOGITS
     strike
    1.47
     strikes
    1.40
     striking
    1.38
     hitting
    1.35
     Strikes
    1.34
     Schlag
    1.33
    Strike
    1.30
     Strike
    1.29
     struck
    1.27
     hit
    1.25
    Act Density 0.258%

    No Known Activations