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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing opinions and thoughts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fta
    -1.90
     ftu
    -1.74
     aen
    -1.64
     Juf
    -1.63
     mef
    -1.63
     dises
    -1.62
     emphat
    -1.61
     fup
    -1.59
     effe
    -1.58
     vns
    -1.56
    POSITIVE LOGITS
     it
    0.90
     there
    0.88
     they
    0.83
     if
    0.79
     we
    0.78
     you
    0.75
     don
    0.73
     I
    0.73
     its
    0.72
     unfortunately
    0.71
    Act Density 0.217%

    No Known Activations