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

    Neuronpedia

    INDEX
    Explanations

    words related to government policies or regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Souha
    -0.80
     Mlle
    -0.76
     Portugu
    -0.76
     Cfr
    -0.75
     Abbé
    -0.75
     Ibidem
    -0.73
     intrigu
    -0.73
     Bartholo
    -0.73
     apprehen
    -0.73
     Hieronymus
    -0.72
    POSITIVE LOGITS
     actual
    1.02
    actual
    0.93
     directly
    0.86
     actually
    0.82
     direct
    0.81
     outright
    0.81
     necessarily
    0.78
     ACTUAL
    0.74
    Actual
    0.71
    direct
    0.70
    Act Density 0.565%

    No Known Activations