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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical equations and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.72
    ParallelGroup
    -0.71
    twimg
    -0.69
     itſelf
    -0.67
     وتسجيلات
    -0.67
    StoryboardSegue
    -0.65
     出版
    -0.64
     @"/
    -0.64
    ientôt
    -0.63
    Или
    -0.63
    POSITIVE LOGITS
    UNRELATED
    0.52
     Spoilers
    0.49
    unmodifiable
    0.48
     tụ
    0.46
     coalition
    0.45
     sea
    0.45
    MeV
    0.43
    RenderAtEndOf
    0.43
     gros
    0.43
    יקר
    0.43
    Act Density 0.868%

    No Known Activations