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

    Neuronpedia

    INDEX
    Explanations

    punctuation in varying contexts, particularly focusing on commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocities
    -0.17
    uries
    -0.15
    kinson
    -0.14
    rang
    -0.14
    rane
    -0.14
     date
    -0.14
    ucid
    -0.14
    jad
    -0.14
    angs
    -0.13
    ieran
    -0.13
    POSITIVE LOGITS
     also
    0.16
    also
    0.15
    ãn
    0.14
    zer
    0.13
    itan
    0.13
    ycz
    0.13
    __.__
    0.13
    pons
    0.13
    åĭ¢
    0.13
    Also
    0.13
    Act Density 0.024%

    No Known Activations