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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise, ability, and emotions related to happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.41
    3:0.04
    4:0.01
    5:0.03
    6:0.04
    7:0.06
    8:0.11
    9:0.10
    10:0.05
    11:0.05
    Negative Logits
     Directive
    -1.20
     plague
    -1.16
     precaution
    -1.14
     Lum
    -1.13
     Internal
    -1.13
     rarely
    -1.12
     tradition
    -1.11
     bount
    -1.10
     selection
    -1.10
     characteristic
    -1.09
    POSITIVE LOGITS
    angered
    1.68
     someday
    1.64
    icent
    1.58
    ワン
    1.57
    icted
    1.55
    stories
    1.52
    itialized
    1.50
    atre
    1.46
    ギ
    1.43
    orthy
    1.42
    Act Density 0.174%

    No Known Activations