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

    Neuronpedia

    INDEX
    Explanations

    sports-related terms, specifically related to games

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    aft
    -0.66
    LECT
    -0.61
    sie
    -0.60
     Refugees
    -0.60
    hai
    -0.60
    istani
    -0.60
    ingen
    -0.59
    orship
    -0.58
    Adds
    -0.57
    azon
    -0.57
    POSITIVE LOGITS
    plan
    1.02
    manship
    0.90
     against
    0.86
    keepers
    0.84
    winning
    0.83
    day
    0.82
    keeper
    0.82
    PLAY
    0.81
     played
    0.77
     Played
    0.77
    Act Density 0.066%

    No Known Activations