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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "notice" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schulte
    -0.68
     Bag
    -0.65
     Home
    -0.61
    спубли
    -0.61
     Mor
    -0.60
     Eber
    -0.60
     Gil
    -0.60
     Dunbar
    -0.59
     Bart
    -0.58
     Bran
    -0.58
    POSITIVE LOGITS
     NOTICE
    1.48
     Notice
    1.46
    NOTICE
    1.38
     Notices
    1.37
    Notice
    1.36
     notices
    1.35
    notice
    1.34
     noticed
    1.33
     notice
    1.32
    Notices
    1.27
    Act Density 0.050%

    No Known Activations