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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a period followed by a number from 6 to 10

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quir
    -0.97
    emic
    -0.78
     submerged
    -0.77
     mur
    -0.75
     canned
    -0.73
     bundled
    -0.71
     settled
    -0.71
     wider
    -0.68
    awed
    -0.68
     abandoned
    -0.67
    POSITIVE LOGITS
     ..."
    1.51
     âĢ¦"
    1.32
     [...]
    1.26
     Therefore
    1.25
     Whereas
    1.17
     Especially
    1.11
     Whether
    1.10
    sic
    1.09
     Accordingly
    1.08
     However
    1.07
    Act Density 0.563%

    No Known Activations