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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.37
    1:0.06
    2:0.04
    3:0.07
    4:0.02
    5:0.05
    6:0.02
    7:0.02
    8:0.11
    9:0.11
    10:0.04
    11:0.05
    Negative Logits
    �
    -1.74
     largeDownload
    -1.61
    ccording
    -1.47
     Qué
    -1.37
    oti
    -1.32
     Sioux
    -1.31
    20439
    -1.29
     oun
    -1.28
    ilings
    -1.27
     psychiat
    -1.27
    POSITIVE LOGITS
    ↵
    2.42
    SPONSORED
    1.79
    <|endoftext|>
    1.76
    ↵↵
    1.55
    itud
    1.48
    >[
    1.44
     ["
    1.36
    chrome
    1.36
    course
    1.33
    ibilities
    1.30
    Act Density 0.438%

    No Known Activations