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

    Neuronpedia

    INDEX
    Explanations

    references to academic affiliations and professional credentials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     voks
    -0.20
    dech
    -0.17
    dera
    -0.16
    IRR
    -0.16
    missive
    -0.15
    GGLE
    -0.15
     Cincinnati
    -0.15
    doch
    -0.14
     Kaw
    -0.14
    Kansas
    -0.14
    POSITIVE LOGITS
     Norwegian
    0.43
     Oslo
    0.42
     Norway
    0.42
     Bergen
    0.31
    Nor
    0.31
    ø
    0.28
     Ãĺ
    0.28
    øy
    0.28
     oslo
    0.28
    .no
    0.27
    Act Density 0.095%

    No Known Activations