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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¯ãĥ¼
    -0.16
    ept
    -0.16
    roys
    -0.16
     Aid
    -0.15
    les
    -0.14
    allery
    -0.14
    claimer
    -0.14
    DCALL
    -0.14
    qus
    -0.14
    osph
    -0.14
    POSITIVE LOGITS
    /Dk
    0.16
    amba
    0.15
    ICODE
    0.15
    atten
    0.15
    μμ
    0.14
    062
    0.14
     grounds
    0.13
    Contents
    0.13
     amb
    0.13
     ambassador
    0.13
    Act Density 0.016%

    No Known Activations