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

    Neuronpedia

    INDEX
    Explanations

    references to combat or fighting techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.51
    ЧИТА
    -0.49
     ProtoMessage
    -0.47
     trompe
    -0.47
     المعيارى
    -0.45
    formin
    -0.45
    "]();
    -0.45
    '])){
    -0.45
    ScopeManager
    -0.45
     Majefty
    -0.45
    POSITIVE LOGITS
     martial
    0.73
     unarmed
    0.57
     Martial
    0.56
    martial
    0.56
    Martial
    0.54
    🥋
    0.50
     karate
    0.49
     бое
    0.47
     Karate
    0.47
     training
    0.47
    Act Density 0.202%

    No Known Activations