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

    Neuronpedia

    INDEX
    Explanations

    references to employment statistics or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.07
    3:0.05
    4:0.15
    5:0.02
    6:0.03
    7:0.37
    8:0.03
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
    emetery
    -1.71
    yip
    -1.67
    inventoryQuantity
    -1.66
    odon
    -1.62
    myra
    -1.60
    snap
    -1.59
    ById
    -1.59
    ebin
    -1.56
    cture
    -1.54
    changes
    -1.52
    POSITIVE LOGITS
     comedic
    1.65
     superv
    1.65
     engineering
    1.54
     managerial
    1.54
     teaching
    1.49
     faculty
    1.42
     culinary
    1.41
     professional
    1.40
     subsid
    1.38
     barr
    1.38
    Act Density 0.008%

    No Known Activations