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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political statements and actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Intere
    -1.66
     guarante
    -1.66
     fta
    -1.61
     increa
    -1.57
     purcha
    -1.53
     vété
    -1.53
     triomphe
    -1.53
     »>
    -1.53
     matel
    -1.51
     encomp
    -1.50
    POSITIVE LOGITS
     be
    0.73
    complexContent
    0.70
    Garantía
    0.70
    Väl
    0.69
    Viited
    0.69
     للاسماء
    0.67
    Gobierno
    0.66
     continue
    0.66
    المصادر
    0.65
     stay
    0.65
    Act Density 0.258%

    No Known Activations