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

    Neuronpedia

    INDEX
    Explanations

    words related to education and self-awareness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     dises
    -1.16
     sopr
    -1.15
     sappi
    -1.14
     robus
    -1.07
     lancia
    -1.06
     pessi
    -1.06
     igno
    -1.05
     squa
    -1.05
     Kategor
    -1.03
     umo
    -1.02
    POSITIVE LOGITS
     there
    0.81
     it
    0.80
     they
    0.78
     then
    0.77
     you
    0.72
     we
    0.69
     chances
    0.67
     or
    0.65
    there
    0.64
     she
    0.63
    Act Density 0.208%

    No Known Activations