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

    Neuronpedia

    INDEX
    Explanations

    locations, proper nouns, and names of companies or individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.67
    ĨĴ
    -0.66
    llah
    -0.65
     Pwr
    -0.61
     thous
    -0.59
     Sense
    -0.57
    CLASSIFIED
    -0.57
     salsa
    -0.56
    Ö¼
    -0.56
     lur
    -0.56
    POSITIVE LOGITS
    emort
    0.90
    heed
    0.88
    oyd
    0.82
    ansk
    0.82
    gow
    0.81
    ocene
    0.76
    ativity
    0.76
    anchester
    0.74
    aptop
    0.73
    ounge
    0.73
    Act Density 1.607%

    No Known Activations