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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the abbreviation "FL" and variations of the word "fluid."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.03
     faſt
    -0.78
     quæ
    -0.78
     houſe
    -0.77
     uſ
    -0.77
     myſelf
    -0.77
     purpoſe
    -0.77
     ſen
    -0.76
     himſelf
    -0.76
     iſt
    -0.75
    POSITIVE LOGITS
     fl
    0.91
     cant
    0.75
     dont
    0.68
    fl
    0.68
     arent
    0.65
     didnt
    0.65
    dont
    0.63
     doesnt
    0.63
     wouldnt
    0.62
     isnt
    0.60
    Act Density 0.122%

    No Known Activations