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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ings
    -0.20
    shaw
    -0.15
    aken
    -0.15
    ãĥģãĥ¥
    -0.14
    pend
    -0.14
    bart
    -0.14
    uell
    -0.14
    ations
    -0.14
    acion
    -0.13
    ãĥ¼ãĥĭ
    -0.13
    POSITIVE LOGITS
    ed
    0.24
    Ø©
    0.18
    AVA
    0.17
    ÛĮ
    0.17
    zelf
    0.17
    errupted
    0.16
    nbsp
    0.15
    egration
    0.15
    edere
    0.15
    #ac
    0.15
    Act Density 0.098%

    No Known Activations