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

    Neuronpedia

    INDEX
    Explanations

    technical information about machinery or industrial processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.07
    2:0.09
    3:0.09
    4:0.04
    5:0.11
    6:0.04
    7:0.03
    8:0.10
    9:0.12
    10:0.10
    11:0.04
    Negative Logits
    ocrates
    -1.46
    ukong
    -1.44
    igion
    -1.43
     Canaan
    -1.42
     Boko
    -1.39
     Metatron
    -1.30
     Mub
    -1.28
    itimate
    -1.28
    icia
    -1.26
    ylum
    -1.25
    POSITIVE LOGITS
     weighs
    1.52
     miniature
    1.35
     paddle
    1.33
    ominium
    1.33
     weighing
    1.33
     weigh
    1.31
    ride
    1.30
     srfAttach
    1.28
     cylinders
    1.27
     Roller
    1.26
    Act Density 0.179%

    No Known Activations