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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters in contexts that may indicate structure in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.03
    3:0.10
    4:0.04
    5:0.03
    6:0.06
    7:0.41
    8:0.03
    9:0.04
    10:0.05
    11:0.13
    Negative Logits
    arin
    -1.62
     FSA
    -1.53
    anol
    -1.52
    asus
    -1.50
     seminars
    -1.44
     Pent
    -1.44
     Camel
    -1.40
    II
    -1.39
    iege
    -1.36
    sen
    -1.36
    POSITIVE LOGITS
    goal
    1.61
    stre
    1.57
    acio
    1.56
    laim
    1.50
    Publisher
    1.48
    ritic
    1.42
    grave
    1.40
    oire
    1.37
     grate
    1.35
     rever
    1.35
    Act Density 0.004%

    No Known Activations