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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases indicating the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.77
    IndentedString
    -0.76
     raiſ
    -0.67
    NUMX
    -0.67
     poffible
    -0.65
    الإنجليزية
    -0.64
     "];
    -0.63
     poffe
    -0.63
     againſt
    -0.63
    RuleContext
    -0.62
    POSITIVE LOGITS
     is
    1.02
     are
    0.79
     was
    0.79
     should
    0.72
    XmlAccessType
    0.70
     would
    0.67
     can
    0.65
     has
    0.65
     must
    0.63
     will
    0.63
    Act Density 0.499%

    No Known Activations