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

    Neuronpedia

    INDEX
    Explanations

    numerical references and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.07
    4:0.07
    5:0.03
    6:0.05
    7:0.24
    8:0.03
    9:0.03
    10:0.18
    11:0.13
    Negative Logits
    soDeliveryDate
    -1.56
    dates
    -1.43
     subtitles
    -1.42
    forth
    -1.40
     redund
    -1.37
    dated
    -1.36
    backs
    -1.34
     fleets
    -1.32
     rewritten
    -1.32
     refunds
    -1.29
    POSITIVE LOGITS
    abetes
    1.53
     Rating
    1.41
     disagree
    1.37
     overweight
    1.36
     measurement
    1.33
     Entered
    1.32
    etermined
    1.31
    ��
    1.31
     Diabetes
    1.28
     percentile
    1.27
    Act Density 0.000%

    No Known Activations