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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TintMode
    -1.00
    ագրություններ
    -0.99
     myſelf
    -0.97
    KommentareTeilen
    -0.97
    ocarditis
    -0.94
     auffi
    -0.93
     itſelf
    -0.93
    存于互联网档案馆
    -0.92
     <<<<<<<<<<<<<<
    -0.92
     للاسماء
    -0.90
    POSITIVE LOGITS
    Except
    1.36
     except
    1.35
     Except
    1.31
    except
    1.15
     unless
    1.04
     excepto
    1.00
     sauf
    0.93
    unless
    0.93
     EXCEPT
    0.92
    Unless
    0.92
    Act Density 0.100%

    No Known Activations