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

    Neuronpedia

    INDEX
    Explanations

    terms related to Lego building components and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lyon
    -0.17
    _rw
    -0.14
    arte
    -0.14
    ptron
    -0.14
    IPA
    -0.14
    ĨĴ
    -0.14
    bara
    -0.14
    .synthetic
    -0.14
    itore
    -0.13
    út
    -0.13
    POSITIVE LOGITS
     Brick
    0.37
     brick
    0.33
     bricks
    0.31
     LEGO
    0.28
    brick
    0.28
     DUP
    0.27
    LE
    0.25
     min
    0.25
     UCS
    0.24
     Creator
    0.23
    Act Density 0.025%

    No Known Activations