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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical combat sports or conflicts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    SOURCE
    -0.63
     Schiff
    -0.62
     Principle
    -0.62
    pta
    -0.60
     Kad
    -0.60
     ancest
    -0.59
    operated
    -0.58
     Rica
    -0.58
     Roads
    -0.57
    kefeller
    -0.57
    POSITIVE LOGITS
    iques
    1.02
     bout
    0.88
     bouts
    0.87
    ting
    0.68
    tone
    0.68
    cakes
    0.67
    rix
    0.66
    lers
    0.64
    ique
    0.63
    nec
    0.63
    Act Density 5.254%

    No Known Activations