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

    Neuronpedia

    INDEX
    Explanations

    mentions of words starting with "Tr"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific subject or entity identified by the token "Tr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yeast
    -0.73
     Mechdragon
    -0.69
    ELS
    -0.68
    WARE
    -0.67
     arts
    -0.67
     tong
    -0.65
     writ
    -0.65
    âĸ¬âĸ¬
    -0.65
     minded
    -0.65
    lihood
    -0.64
    POSITIVE LOGITS
    acer
    1.28
    ainer
    1.26
    ained
    1.23
    unks
    1.23
    istan
    1.21
    icol
    1.20
    umps
    1.20
    ains
    1.18
    agic
    1.16
    icky
    1.14
    Act Density 0.017%

    No Known Activations