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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ëij
    -0.14
    bris
    -0.14
    Enlarge
    -0.14
    κοÏħ
    -0.14
    ehr
    -0.14
    MER
    -0.13
    aved
    -0.13
    lse
    -0.13
    {id
    -0.13
    lsa
    -0.13
    POSITIVE LOGITS
    ulle
    0.19
    SWEP
    0.17
     (
    0.15
    enson
    0.14
     Rin
    0.14
    -called
    0.14
    stown
    0.14
     nên
    0.14
     conduct
    0.14
    aken
    0.13
    Act Density 0.071%

    No Known Activations