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

    Neuronpedia

    INDEX
    Explanations

    words related to programming languages and coding concepts

    oai_token-act-pair · gpt-3.5-turbo

    words with the substring "br" or "str"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    company
    -0.67
     bidding
    -0.61
    LOAD
    -0.60
    street
    -0.59
    states
    -0.58
    enter
    -0.55
     productive
    -0.54
     birth
    -0.54
     owning
    -0.54
    peat
    -0.54
    POSITIVE LOGITS
    atus
    1.02
    ador
    0.97
    asonic
    0.96
    æ
    0.92
    atures
    0.90
    aten
    0.89
    acht
    0.88
    ata
    0.88
    inus
    0.88
    anes
    0.86
    Act Density 0.089%

    No Known Activations