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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political agreements, negotiations, and policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     casio
    -1.68
     fta
    -1.57
     blos
    -1.56
     squa
    -1.54
     aen
    -1.52
     mef
    -1.52
     fuj
    -1.50
     scrat
    -1.48
     seiz
    -1.46
     fto
    -1.45
    POSITIVE LOGITS
    “
    0.84
     “
    0.83
    ”
    0.79
     "
    0.79
     «
    0.71
    ，“
    0.71
    }$
    0.70
     نسخة
    0.69
     ”
    0.69
    »
    0.69
    Act Density 0.165%

    No Known Activations