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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Abril
    -0.63
    Nein
    -0.57
    Gör
    -0.54
    Minha
    -0.53
    softmax
    -0.53
    Jawaban
    -0.52
    Gibt
    -0.51
    Saiba
    -0.51
    inflater
    -0.51
    Agosto
    -0.50
    POSITIVE LOGITS
     fatis
    1.06
     ftu
    1.06
     dises
    1.01
     fta
    1.00
     fuf
    1.00
     guarante
    0.99
     vns
    0.95
     mépris
    0.95
     fup
    0.95
     fep
    0.94
    Act Density 0.280%

    No Known Activations