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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical statistics and figures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.05
    2:0.06
    3:0.16
    4:0.05
    5:0.29
    6:0.05
    7:0.04
    8:0.04
    9:0.03
    10:0.08
    11:0.04
    Negative Logits
    netflix
    -2.10
     supermarkets
    -2.05
     bins
    -1.92
    adelphia
    -1.89
    natureconservancy
    -1.87
    GROUP
    -1.82
    Netflix
    -1.75
    category
    -1.73
     Newsp
    -1.70
    limits
    -1.70
    POSITIVE LOGITS
    ieu
    1.79
     haha
    1.66
    ette
    1.59
     Karma
    1.58
    ¨
    1.56
     Stir
    1.56
     ka
    1.54
    ]).
    1.53
    luaj
    1.52
    olk
    1.52
    Act Density 0.449%

    No Known Activations