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

    Neuronpedia

    INDEX
    Explanations

    safety and health-related instructions or guidelines

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     journaux
    -0.73
     icônes
    -0.69
     frasi
    -0.67
     prochaines
    -0.66
     ouvrages
    -0.65
     devoirs
    -0.64
     négociations
    -0.64
     numéros
    -0.63
     spectateurs
    -0.61
     musées
    -0.61
    POSITIVE LOGITS
     Keny
    0.75
     Tapa
    0.74
     inspiring
    0.66
     racon
    0.65
     intrigu
    0.64
     Compañ
    0.64
     upvoted
    0.64
     Fait
    0.64
     inspirational
    0.63
     talented
    0.62
    Act Density 0.513%

    No Known Activations