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

    Neuronpedia

    INDEX
    Explanations

    results of sports matches

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to draws, stoppages, and decisions in competitive events or matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.77
    spect
    -0.75
    agents
    -0.72
    here
    -0.70
    istries
    -0.69
    seys
    -0.68
    fol
    -0.68
    kinson
    -0.67
     Lerner
    -0.66
    ubric
    -0.66
    POSITIVE LOGITS
     defeat
    1.34
     victory
    1.31
     forfeit
    1.22
     KO
    1.19
     knockout
    1.17
     shootout
    1.15
    Winner
    1.14
     win
    1.13
     defeats
    1.13
    Result
    1.12
    Act Density 0.209%

    No Known Activations