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

    Neuronpedia

    INDEX
    Explanations

    combinations of superlative adjectives to highlight extreme qualities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     remainder
    -0.41
     rest
    -0.23
    remainder
    -0.23
     remaining
    -0.21
     Remaining
    -0.17
     broader
    -0.15
     wider
    -0.15
     happier
    -0.14
     entirety
    -0.14
    remaining
    -0.14
    POSITIVE LOGITS
     most
    0.71
    æľĢ
    0.70
     ê°Ģìŀ¥
    0.62
    most
    0.59
     least
    0.58
     सबस
    0.57
    -most
    0.54
    least
    0.54
     greatest
    0.53
     MOST
    0.52
    Act Density 1.439%

    No Known Activations