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

    Neuronpedia

    INDEX
    Explanations

    references to Lego pieces and their usage in building frames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consult
    -0.15
    ptron
    -0.14
    ryn
    -0.14
    asl
    -0.14
     ÑĤеÑĢиÑĤоÑĢ
    -0.14
    csi
    -0.14
    alah
    -0.14
    ishops
    -0.14
    Äįin
    -0.14
    asal
    -0.13
    POSITIVE LOGITS
     Brick
    0.31
     brick
    0.26
     DUP
    0.26
     bricks
    0.26
    brick
    0.23
     min
    0.23
     Dup
    0.22
     Creator
    0.21
     Techn
    0.20
     LEGO
    0.20
    Act Density 0.015%

    No Known Activations