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

    Neuronpedia

    INDEX
    Explanations

    negations or qualifiers that specify limitations or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     A
    -0.52
    ↵↵
    -0.50
     and
    -0.49
    A
    -0.48
     
    -0.42
     (
    -0.41
    <eos>
    -0.40
    ers
    -0.40
     ;
    -0.39
     ,
    -0.39
    POSITIVE LOGITS
    RectangleBorder
    1.11
     wireType
    0.99
     مشين
    0.90
     تضيفلها
    0.89
    aarrggbb
    0.87
    oredCriteria
    0.87
     MainAxisSize
    0.86
    存于互联网档案馆
    0.85
     itſelf
    0.85
    adpleegd
    0.85
    Act Density 0.302%

    No Known Activations