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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or symbols indicating pauses or separations in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipel
    -0.17
    -toggler
    -0.16
    Ã
    -0.14
    illet
    -0.14
    arge
    -0.14
    amine
    -0.14
    ago
    -0.14
    yna
    -0.13
    noc
    -0.13
    agment
    -0.13
    POSITIVE LOGITS
    ikal
    0.16
     impact
    0.16
     Toy
    0.15
    ÛĮÙĨÙĩ
    0.15
    olia
    0.15
    immel
    0.14
    Toy
    0.14
    _FMT
    0.14
    reff
    0.13
     ÐĹаÑħ
    0.13
    Act Density 0.021%

    No Known Activations