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

    Neuronpedia

    INDEX
    Explanations

    winning or losing streaks in sports or competitive contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of winning or losing streaks in performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤº
    -0.79
    abad
    -0.72
    resources
    -0.70
    Male
    -0.69
    ACTED
    -0.68
     Lod
    -0.66
    gency
    -0.66
    idd
    -0.65
    poses
    -0.64
    onomic
    -0.64
    POSITIVE LOGITS
     streak
    1.23
    iness
    0.88
    manship
    0.87
    uous
    0.84
    icity
    0.82
     streaks
    0.81
    isSpecialOrderable
    0.76
    wcs
    0.69
    yk
    0.69
    terness
    0.68
    Act Density 0.026%

    No Known Activations