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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prits
    -0.52
    だそうです
    -0.43
    calipsis
    -0.43
     insp
    -0.42
     المعيارى
    -0.41
     hilsen
    -0.41
    stoppable
    -0.40
    íncia
    -0.39
    ParallelGroup
    -0.39
    chau
    -0.39
    POSITIVE LOGITS
     mentioned
    0.92
     previously
    0.87
     ſaid
    0.81
    说过
    0.79
    mentioned
    0.77
     stated
    0.75
     earlier
    0.74
     mention
    0.72
    ContentAsync
    0.72
     discussed
    0.72
    Act Density 0.274%

    No Known Activations