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

    Neuronpedia

    INDEX
    Explanations

    patterns of consecutive wins or losses in competitive scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.69
    BeginContext
    -0.62
    HasColumnType
    -0.56
    ReusableCell
    -0.54
     ainda
    -0.53
    sidemargin
    -0.49
     prí
    -0.48
     insuffisamment
    -0.47
    一张
    -0.46
    Slf
    -0.46
    POSITIVE LOGITS
     consecutive
    0.93
     Theſe
    0.81
     Monfieur
    0.81
     faſt
    0.78
     purpoſe
    0.77
     streak
    0.77
     raiſ
    0.76
     streaks
    0.75
     Jefus
    0.74
     itſelf
    0.73
    Act Density 0.257%

    No Known Activations