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

    Neuronpedia

    INDEX
    Explanations

    statements of findings, conclusions, or claims regarding research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -1.18
    GEBURTSDATUM
    -1.10
     bezeichneter
    -1.07
    Personendaten
    -1.06
     незавершена
    -1.05
    Personensuche
    -1.01
    ValueStyle
    -1.01
    :✨
    -0.97
     propOrder
    -0.95
    SourceChecksum
    -0.94
    POSITIVE LOGITS
     Her
    0.44
     First
    0.42
     Pre
    0.40
     she
    0.39
    translates
    0.39
    First
    0.39
    she
    0.38
     forma
    0.38
     forme
    0.38
     her
    0.37
    Act Density 3.914%

    No Known Activations