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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.05
    2:0.03
    3:0.26
    4:0.11
    5:0.08
    6:0.06
    7:0.02
    8:0.11
    9:0.08
    10:0.02
    11:0.02
    Negative Logits
     newsletter
    -2.44
     Newsweek
    -2.39
     publication
    -2.30
     memos
    -2.22
    blog
    -2.19
     forthcoming
    -2.10
     published
    -2.10
     NYT
    -2.08
    published
    -2.08
     Newsletter
    -2.08
    POSITIVE LOGITS
    oleon
    2.35
     stunts
    2.33
    ihad
    2.23
     Comet
    2.14
    ateurs
    2.10
    igers
    2.07
    azy
    2.04
    digy
    2.03
    zees
    1.97
    itimate
    1.97
    Act Density 0.000%

    No Known Activations