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

    Neuronpedia

    INDEX
    Explanations

    punctuation, specifically periods and commas, which signify the end of sentences and lists, respectively

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tees
    -0.15
    ahr
    -0.15
    ifo
    -0.15
    AndView
    -0.14
    274
    -0.14
     Kerr
    -0.14
    env
    -0.13
    ies
    -0.13
    asm
    -0.13
    lio
    -0.13
    POSITIVE LOGITS
    ucene
    0.16
    ideographic
    0.15
    oslav
    0.15
    å¡
    0.15
    /Runtime
    0.15
    quin
    0.15
    å®Ī
    0.14
     nackte
    0.14
    sut
    0.14
    bury
    0.14
    Act Density 0.063%

    No Known Activations