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

    Neuronpedia

    INDEX
    Explanations

    strong emotional reactions and evaluations in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     كومونز
    -0.66
     noten
    -0.59
     farbe
    -0.59
     poliuret
    -0.58
    новниш
    -0.56
     ortop
    -0.56
    клопе
    -0.55
    جغرافيا
    -0.55
    InkWell
    -0.54
     ThemeData
    -0.54
    POSITIVE LOGITS
     suscep
    1.50
     maneu
    1.45
     unwarran
    1.37
     disreg
    1.36
     disagre
    1.36
     depic
    1.36
     increa
    1.33
     indestru
    1.31
     unden
    1.30
     reluct
    1.29
    Act Density 0.375%

    No Known Activations