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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and phrases indicating personal opinions or thoughts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     MÁ
    -0.97
     fosfor
    -0.97
     soggior
    -0.93
     monaster
    -0.93
     susun
    -0.92
     hunde
    -0.89
     masaj
    -0.89
     affez
    -0.89
     guma
    -0.89
     Singapur
    -0.89
    POSITIVE LOGITS
     disagre
    0.95
     apprehen
    0.92
     shenan
    0.91
    I
    0.83
     I
    0.82
     unspeak
    0.82
     intersper
    0.81
     vainly
    0.79
     encomp
    0.79
     impelled
    0.79
    Act Density 0.257%

    No Known Activations