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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases indicating dissatisfaction or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.79
     ***!
    -0.76
    extAlignment
    -0.68
     Мексичка
    -0.68
     AssemblyCompany
    -0.64
     NgModule
    -0.64
    utilisons
    -0.63
    :✨
    -0.62
     Witkin
    -0.61
    Демографія
    -0.61
    POSITIVE LOGITS
    else
    0.63
     otherwise
    0.57
     Otherwise
    0.53
    Otherwise
    0.51
     fatale
    0.51
     OTHERWISE
    0.50
    elsif
    0.49
    要不是
    0.49
     sinon
    0.48
    yntaxException
    0.48
    Act Density 0.179%

    No Known Activations