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

    Neuronpedia

    INDEX
    Explanations

    descriptions of scenes or actions happening in a particular location

    oai_token-act-pair · gpt-3.5-turbo

    sentences that include various types of punctuation or endings, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     independ
    -0.87
     utilize
    -0.82
     util
    -0.79
     advoc
    -0.79
     tremend
    -0.78
    é»Ĵ
    -0.77
    aucas
    -0.75
    uly
    -0.73
     dimensional
    -0.72
     commer
    -0.72
    POSITIVE LOGITS
     But
    1.29
     Occasionally
    1.22
     Yet
    1.16
     Asked
    1.14
     Everywhere
    1.12
     Meanwhile
    1.08
     Others
    1.07
     And
    1.06
     Sometimes
    1.05
     Scores
    1.05
    Act Density 0.543%

    No Known Activations