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

    Neuronpedia

    INDEX
    Explanations

    capitalized abbreviations or acronyms preceded by "BE"

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty segments or placeholders in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kson
    -0.68
    geist
    -0.66
    iors
    -0.63
    opter
    -0.63
    raints
    -0.63
    owicz
    -0.62
    ãĤ¡
    -0.62
    strings
    -0.58
    selves
    -0.58
     Franks
    -0.58
    POSITIVE LOGITS
    VILLE
    1.33
    MAN
    1.33
     CITY
    1.28
    STON
    1.25
    INGTON
    1.24
    LAND
    1.24
    COL
    1.23
    OIL
    1.22
    VIEW
    1.20
    TON
    1.20
    Act Density 0.116%

    No Known Activations