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

    Neuronpedia

    INDEX
    Explanations

    the word "some"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -1.06
     ―――――
    -1.05
     raiſ
    -1.05
     itſelf
    -1.03
    expandindo
    -1.00
    Something
    -0.96
     Somewhere
    -0.95
    somewhere
    -0.94
    WithIOException
    -0.94
     '\\;'
    -0.92
    POSITIVE LOGITS
     some
    2.03
     Some
    1.90
    Some
    1.81
    some
    1.37
     SOME
    1.18
     alcuni
    1.01
     algunos
    1.01
     algunas
    1.00
     некоторые
    1.00
     unele
    1.00
    Act Density 0.311%

    No Known Activations