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

    Neuronpedia

    INDEX
    Explanations

    numerical specifications related to size or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.06
    4:0.07
    5:0.03
    6:0.04
    7:0.38
    8:0.03
    9:0.04
    10:0.09
    11:0.10
    Negative Logits
    manship
    -1.68
     resusc
    -1.56
     legality
    -1.55
    �
    -1.54
     principals
    -1.54
     morality
    -1.53
     morals
    -1.53
    aution
    -1.53
     stewards
    -1.52
    wash
    -1.52
    POSITIVE LOGITS
    66666666
    1.86
     diameter
    1.79
     Size
    1.75
     size
    1.71
    iameter
    1.68
     sizes
    1.64
     circumference
    1.62
    XL
    1.58
    Size
    1.55
     Large
    1.53
    Act Density 0.009%

    No Known Activations