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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political leaders and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     artig
    -0.69
     ausp
    -0.67
     ordina
    -0.67
    viron
    -0.65
     Église
    -0.65
     siff
    -0.64
     cosi
    -0.64
     prostitu
    -0.64
     parati
    -0.63
     hecta
    -0.63
    POSITIVE LOGITS
     nothin
    0.70
     unspeak
    0.69
     indescri
    0.66
     shenan
    0.63
     there
    0.61
     ineffec
    0.61
     swee
    0.61
     laug
    0.59
     horrend
    0.59
     prolly
    0.58
    Act Density 0.257%

    No Known Activations