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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a new thought or paragraph, often indicated by special tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PMC
    -0.76
    PMC
    -0.74
     Robbins
    -0.71
     BoxDecoration
    -0.71
     DMA
    -0.67
    typer
    -0.67
    hedral
    -0.66
    offsets
    -0.65
    loyer
    -0.65
    XmlAccessType
    -0.65
    POSITIVE LOGITS
     Wish
    1.28
     wish
    1.27
    Wish
    1.25
    wish
    1.24
     WISH
    1.23
     wished
    1.12
     Wishes
    1.08
     wishes
    1.05
    WISH
    0.91
     wishing
    0.88
    Act Density 0.036%

    No Known Activations