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

    Neuronpedia

    INDEX
    Explanations

    comparative statistics and proportions related to taxation and demographic data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.30
    1:0.13
    2:0.05
    3:0.04
    4:0.04
    5:0.12
    6:0.02
    7:0.02
    8:0.06
    9:0.06
    10:0.06
    11:0.06
    Negative Logits
    chapter
    -1.68
     jour
    -1.50
     Orn
    -1.50
    onom
    -1.46
     Pt
    -1.45
    ello
    -1.44
    istor
    -1.42
    ablo
    -1.39
    aquin
    -1.39
    pillar
    -1.39
    POSITIVE LOGITS
     inferior
    1.72
     propensity
    1.66
    luster
    1.64
     superior
    1.63
     advantage
    1.62
     average
    1.56
    iencies
    1.55
    ensive
    1.53
    agged
    1.52
    %]
    1.52
    Act Density 0.128%

    No Known Activations