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

    Neuronpedia

    INDEX
    Explanations

    references to Native American terms or imagery

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kuku
    -0.58
     wani
    -0.52
     kuti
    -0.51
    ħħ
    -0.50
     jati
    -0.49
    l
    -0.48
     Crosse
    -0.48
    habhar
    -0.47
     Sush
    -0.47
     kuli
    -0.47
    POSITIVE LOGITS
     coar
    1.04
     uncin
    0.96
     overla
    0.95
     effe
    0.94
     dispen
    0.94
     suspic
    0.91
     igno
    0.90
     robus
    0.87
     embra
    0.87
     bayern
    0.86
    Act Density 0.230%

    No Known Activations