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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or criticisms in a conversation or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.98
     مشين
    -0.87
    таратура
    -0.87
    NameInMap
    -0.86
     BoxFit
    -0.81
     EconPapers
    -0.75
    VIAF
    -0.75
     AssemblyTitle
    -0.74
     fidélité
    -0.71
     mijne
    -0.70
    POSITIVE LOGITS
     or
    0.71
    ​
    0.58
     the
    0.55
    (!)
    0.55
     to
    0.55
     -
    0.54
    -”
    0.53
     and
    0.52
    -​
    0.52
     (
    0.50
    Act Density 0.541%

    No Known Activations