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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical distribution and prediction

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.76
     in
    -0.75
     and
    -0.75
     of
    -0.72
     to
    -0.72
     якості
    -0.71
     
    -0.71
     śmierci
    -0.71
     другому
    -0.70
    ,
    -0.70
    POSITIVE LOGITS
     immen
    1.91
     abbra
    1.90
     dispen
    1.89
     overla
    1.86
     ridu
    1.85
     erec
    1.81
     pessi
    1.79
     igno
    1.78
     robus
    1.77
     incess
    1.77
    Act Density 0.243%

    No Known Activations