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

    Neuronpedia

    INDEX
    Explanations

    words related to bricks

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "brick."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ntil
    -0.85
    ktop
    -0.80
     Voters
    -0.71
    judicial
    -0.70
    selection
    -0.69
    EVA
    -0.68
    ittee
    -0.65
    uters
    -0.65
    aeda
    -0.65
    ccording
    -0.63
    POSITIVE LOGITS
    bats
    1.27
     bricks
    1.04
    layer
    1.01
     brick
    1.00
     Brick
    0.96
    mort
    0.92
    shaw
    0.91
    yard
    0.88
    works
    0.87
    buster
    0.84
    Act Density 0.006%

    No Known Activations