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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political issues and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     incess
    -0.82
     vitale
    -0.77
     brille
    -0.77
     ló
    -0.76
     poros
    -0.74
     fusil
    -0.73
     perche
    -0.73
     sappi
    -0.72
     tenda
    -0.72
     parati
    -0.72
    POSITIVE LOGITS
     impelled
    0.55
     relinquish
    0.51
     endow
    0.51
     gratify
    0.50
     quitted
    0.49
     negroes
    0.48
     appease
    0.48
     relinquished
    0.48
     lingered
    0.48
     perchance
    0.48
    Act Density 0.256%

    No Known Activations