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

    Neuronpedia

    INDEX
    Explanations

    financial and political terms and phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     rubrique
    -0.71
     pédagogique
    -0.70
     logarith
    -0.70
     asiatique
    -0.69
     ftre
    -0.68
     Shakspeare
    -0.67
     reft
    -0.67
     laft
    -0.66
     fince
    -0.64
     itinéraire
    -0.64
    POSITIVE LOGITS
     Milán
    0.61
     Compañ
    0.55
     organisation
    0.54
     barran
    0.53
     tambor
    0.53
    Inggris
    0.52
     palab
    0.52
     nonprofit
    0.51
    руппа
    0.51
     Irán
    0.51
    Act Density 0.319%

    No Known Activations