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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "brick" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to bricks and brick-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     relativity
    -0.76
    uthor
    -0.68
    ppe
    -0.68
    ffect
    -0.66
    ivia
    -0.66
    orescence
    -0.66
     unintended
    -0.64
    EVA
    -0.63
    judicial
    -0.63
     externalToEVAOnly
    -0.63
    POSITIVE LOGITS
    bats
    1.16
    yard
    1.06
    mort
    1.05
    layer
    1.05
    buster
    0.95
    works
    0.92
     mortar
    0.91
    busters
    0.90
    yards
    0.89
    shaw
    0.85
    Act Density 0.037%

    No Known Activations