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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting cues in product descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    634
    -0.15
    EXTERNAL
    -0.14
    clid
    -0.14
     polar
    -0.14
     Bonus
    -0.14
     sect
    -0.14
     Bale
    -0.14
    á»ij
    -0.13
     recent
    -0.13
    fell
    -0.13
    POSITIVE LOGITS
    rium
    0.21
    /documentation
    0.17
    eres
    0.15
    asan
    0.15
    ilim
    0.15
    ez
    0.15
    eer
    0.15
    esin
    0.15
    usters
    0.15
    unsafe
    0.15
    Act Density 0.057%

    No Known Activations