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

    Neuronpedia

    INDEX
    Explanations

    terminology related to scoring in games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalTable
    -0.50
    extAlignment
    -0.46
    ScopeManager
    -0.45
    GRect
    -0.43
    PostInfinity
    -0.42
    ContentAlignment
    -0.41
     snippetHide
    -0.40
    靡
    -0.40
    APORE
    -0.39
     Anfitrión
    -0.38
    POSITIVE LOGITS
     reward
    0.66
     score
    0.64
     rewards
    0.62
     Reward
    0.57
    Reward
    0.57
    score
    0.54
     assign
    0.52
    reward
    0.52
     scoring
    0.52
     weighting
    0.51
    Act Density 0.598%

    No Known Activations