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

    Neuronpedia

    INDEX
    Explanations

    adjectives conveying negative evaluations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    solicited
    -0.49
     interessanti
    -0.47
     scoper
    -0.47
    Perché
    -0.46
    -------
    -0.45
    Preço
    -0.44
    authorised
    -0.44
    warran
    -0.43
     buone
    -0.43
     riguard
    -0.42
    POSITIVE LOGITS
     marseille
    0.84
     cannes
    0.80
     carrefour
    0.80
     marte
    0.80
     wretch
    0.80
     popoli
    0.80
     cristi
    0.77
     fuo
    0.76
     cabrio
    0.76
     bourg
    0.75
    Act Density 0.246%

    No Known Activations