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

    Neuronpedia

    INDEX
    Explanations

    mentions of new or recent releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olet
    -0.19
    untu
    -0.16
     ç²¾
    -0.15
    /embed
    -0.15
    ENSE
    -0.14
    858
    -0.14
    ITIES
    -0.14
    lical
    -0.14
     weather
    -0.14
     bại
    -0.14
    POSITIVE LOGITS
    MOST
    0.15
     ãĥĽ
    0.14
     fork
    0.14
    egra
    0.14
     diseñador
    0.14
    tahun
    0.14
    /latest
    0.13
    ä»·
    0.13
    born
    0.13
    asia
    0.13
    Act Density 0.008%

    No Known Activations