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

    Neuronpedia

    INDEX
    Explanations

    references to Lego themes and variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consult
    -0.15
    pcm
    -0.15
     lyon
    -0.15
    Äįin
    -0.14
    _rw
    -0.14
    IPA
    -0.14
    itore
    -0.14
     TextAlign
    -0.14
    izon
    -0.13
     foreign
    -0.13
    POSITIVE LOGITS
     Brick
    0.34
     brick
    0.28
     bricks
    0.28
     DUP
    0.25
    brick
    0.25
     LEGO
    0.25
     min
    0.23
     Techn
    0.23
     UCS
    0.22
    LE
    0.21
    Act Density 0.016%

    No Known Activations