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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social issues and arguments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vœux
    -0.85
     négociations
    -0.84
     ecru
    -0.83
     leçons
    -0.82
     hairc
    -0.81
     bénéfices
    -0.79
     indestru
    -0.78
     Bartholo
    -0.77
     McInt
    -0.77
     preuves
    -0.77
    POSITIVE LOGITS
     minuta
    0.77
     psicologia
    0.71
     fras
    0.69
     curiosa
    0.66
     furg
    0.65
     interessa
    0.63
     crede
    0.63
     kawa
    0.62
     resources
    0.62
     alpes
    0.61
    Act Density 0.357%

    No Known Activations