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

    Neuronpedia

    INDEX
    Explanations

    elements related to scoring and performance in games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sizing
    -0.15
     Sutton
    -0.15
    ylko
    -0.15
    933
    -0.14
    ilon
    -0.14
     Stefan
    -0.14
    submenu
    -0.14
    784
    -0.14
    enth
    -0.13
    asin
    -0.13
    POSITIVE LOGITS
     score
    0.98
     scores
    0.86
     Score
    0.84
    score
    0.83
    -score
    0.82
    Score
    0.78
    _score
    0.77
     Scores
    0.74
    .score
    0.74
     scored
    0.70
    Act Density 0.133%

    No Known Activations