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

    Neuronpedia

    INDEX
    Explanations

    elements related to scoring and points in games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abay
    -0.14
     uncomment
    -0.14
    anka
    -0.14
    isine
    -0.14
    alm
    -0.13
     opak
    -0.13
    ظ
    -0.13
    pay
    -0.12
     Taxes
    -0.12
     reimburse
    -0.12
    POSITIVE LOGITS
     points
    0.83
     Points
    0.68
    points
    0.64
    Points
    0.63
    -points
    0.60
    _points
    0.57
    .points
    0.56
    (points
    0.51
     puntos
    0.49
    POINTS
    0.48
    Act Density 0.178%

    No Known Activations