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

    Neuronpedia

    INDEX
    Explanations

    proper nouns denoting people, organizations, and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    blast
    -0.66
    llular
    -0.64
    IFT
    -0.63
    abs
    -0.63
     farm
    -0.63
    igers
    -0.62
    ql
    -0.62
    ield
    -0.61
    pez
    -0.61
     heights
    -0.60
    POSITIVE LOGITS
    ly
    0.82
    edly
    0.76
    Ĥİ
    0.71
    translation
    0.70
    eous
    0.70
     Sources
    0.69
    ĪĴ
    0.69
     sources
    0.69
    Sources
    0.68
    tained
    0.68
    Act Density 0.041%

    No Known Activations