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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to statistics or measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    بين
    -0.58
     like
    -0.58
     beginning
    -0.55
     hard
    -0.55
     ten
    -0.55
     making
    -0.55
     To
    -0.55
     
    -0.54
     i
    -0.54
     saying
    -0.54
    POSITIVE LOGITS
     meis
    1.62
     igno
    1.56
     grati
    1.45
     saar
    1.45
     sappi
    1.43
     ordina
    1.42
     fatis
    1.41
     imposs
    1.41
     suspic
    1.40
     hina
    1.37
    Act Density 0.100%

    No Known Activations