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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nisi
    -0.14
    çºĮ
    -0.13
    cept
    -0.13
    plusplus
    -0.13
     lest
    -0.13
    æĶ
    -0.12
    imenti
    -0.12
     activeClassName
    -0.12
    ervo
    -0.12
    oda
    -0.12
    POSITIVE LOGITS
     either
    0.98
     Either
    0.91
    Either
    0.88
    either
    0.84
     EITHER
    0.79
     whichever
    0.62
    Whatever
    0.60
     whatever
    0.59
     Whatever
    0.58
    whatever
    0.56
    Act Density 0.253%

    No Known Activations