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

    Neuronpedia

    INDEX
    Explanations

    references to groups of people or generalizations about society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.94
    expandindo
    -0.90
    MigrationBuilder
    -0.89
    DockStyle
    -0.88
    parsedMessage
    -0.87
     виправивши
    -0.85
     defStyleAttr
    -0.84
     gynhyrchwyd
    -0.83
     TextAppearance
    -0.81
    URLException
    -0.80
    POSITIVE LOGITS
    Some
    1.14
     Some
    1.00
    some
    1.00
     some
    0.97
     Alguns
    0.95
    SOME
    0.95
     Certains
    0.94
     Algunas
    0.88
     Algunos
    0.88
     algunas
    0.86
    Act Density 0.186%

    No Known Activations