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

    Neuronpedia

    INDEX
    Explanations

    numeric expressions related to weight and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.10
    3:0.04
    4:0.04
    5:0.03
    6:0.10
    7:0.37
    8:0.04
    9:0.04
    10:0.10
    11:0.05
    Negative Logits
     Inher
    -1.81
     Bye
    -1.74
     Promotion
    -1.69
     overlook
    -1.61
     Occ
    -1.61
     Anniversary
    -1.58
     elimination
    -1.54
     mediation
    -1.51
    itism
    -1.50
     Recon
    -1.49
    POSITIVE LOGITS
    lbs
    2.43
     pounds
    2.38
     lbs
    2.33
    pound
    2.14
     kg
    2.11
    kg
    2.02
     weights
    1.95
     suitcase
    1.94
    weights
    1.93
    uggage
    1.92
    Act Density 0.003%

    No Known Activations