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

    Neuronpedia

    INDEX
    Explanations

    phrases related to game scoring and performance statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    905
    -0.15
     Dro
    -0.15
    yy
    -0.14
    705
    -0.13
    aring
    -0.13
    pany
    -0.13
    OLE
    -0.13
    دÙĩ
    -0.13
    zz
    -0.13
     counters
    -0.13
    POSITIVE LOGITS
     halftime
    0.43
     break
    0.37
    break
    0.30
     Break
    0.28
    -break
    0.28
     half
    0.27
    HAL
    0.26
    Hal
    0.26
     HALF
    0.26
    hal
    0.26
    Act Density 0.038%

    No Known Activations