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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks and specific sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akra
    -0.16
    imits
    -0.15
    åIJĪæł¼
    -0.14
     minul
    -0.14
    å±Ĭ
    -0.14
     plein
    -0.14
    urses
    -0.14
    istributions
    -0.14
     âĹĦ
    -0.14
    /history
    -0.14
    POSITIVE LOGITS
     bi
    0.18
     career
    0.17
     early
    0.16
     biography
    0.16
     personal
    0.16
     Bi
    0.16
    Bi
    0.15
     works
    0.15
     marriage
    0.15
     as
    0.15
    Act Density 0.076%

    No Known Activations