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

    Neuronpedia

    INDEX
    Explanations

    punctuation that indicates the end of statements or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.10
    3:0.08
    4:0.08
    5:0.06
    6:0.03
    7:0.08
    8:0.11
    9:0.08
    10:0.14
    11:0.14
    Negative Logits
    iferation
    -1.62
     Marketable
    -1.42
     Thieves
    -1.35
     */
    -1.33
    phabet
    -1.28
     comprom
    -1.27
     Genetics
    -1.27
    gres
    -1.27
     tiss
    -1.26
     TOD
    -1.23
    POSITIVE LOGITS
    ospel
    1.42
     responded
    1.40
     listeners
    1.36
    Dialogue
    1.35
     tripod
    1.34
    Said
    1.33
     spokeswoman
    1.32
     listened
    1.31
     Ibid
    1.30
    SOURCE
    1.29
    Act Density 0.033%

    No Known Activations