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

    Neuronpedia

    INDEX
    Explanations

    exclamatory statements and onomatopoeic expressions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Kenmerken
    -0.65
    Indien
    -0.57
     Boven
    -0.51
    mide
    -0.49
    Flere
    -0.49
     Hva
    -0.48
     roda
    -0.47
     Verder
    -0.47
    المصادر
    -0.47
     Mú
    -0.47
    POSITIVE LOGITS
     unden
    1.16
     excru
    1.15
     accla
    1.14
     fatis
    1.12
     scrat
    1.10
     lidl
    1.07
     effe
    1.06
     volunte
    1.06
     perfet
    1.05
     unve
    1.05
    Act Density 0.071%

    No Known Activations