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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scoring points in a competitive context

    oai_token-act-pair · gpt-3.5-turbo

    references to scoring in games or competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uthor
    -0.90
    ntil
    -0.88
    ufact
    -0.81
    ctors
    -0.79
    ournal
    -0.76
    ccording
    -0.73
    quickShipAvailable
    -0.69
    english
    -0.66
     destro
    -0.65
    DAQ
    -0.65
    POSITIVE LOGITS
     points
    1.19
    points
    1.18
    point
    1.11
    manship
    0.96
     point
    0.93
    Points
    0.92
     Points
    0.92
     pts
    0.76
    pointers
    0.75
    heet
    0.74
    Act Density 0.026%

    No Known Activations