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

    Neuronpedia

    INDEX
    Explanations

    phrases related to signing up for newsletters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     oiseau
    -0.69
     vermelhas
    -0.63
     voulons
    -0.61
     ferons
    -0.60
     noël
    -0.59
     vété
    -0.59
     impati
    -0.59
     poveznice
    -0.57
     prêtre
    -0.56
     ļ
    -0.56
    POSITIVE LOGITS
     our
    0.93
     Our
    0.93
    Our
    0.92
    our
    0.86
     OUR
    0.78
    OUR
    0.76
     ourselves
    0.76
     own
    0.72
     Ours
    0.67
    我们的
    0.65
    Act Density 0.130%

    No Known Activations