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

    Neuronpedia

    INDEX
    Explanations

    text related to international names or terms with non-English characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    estate
    -0.80
    imer
    -0.71
    enegger
    -0.69
    ogene
    -0.63
    oms
    -0.60
     Templ
    -0.60
    ochem
    -0.59
    asted
    -0.58
    iston
    -0.57
    ovie
    -0.57
    POSITIVE LOGITS
    ð
    0.86
    cus
    0.80
    cers
    0.78
    scribed
    0.78
    nder
    0.76
    zbek
    0.75
    scribe
    0.75
    ¢
    0.75
    ption
    0.73
    ths
    0.73
    Act Density 0.015%

    No Known Activations