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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    REC
    -0.72
     permission
    -0.67
    Bird
    -0.66
     variance
    -0.63
     href
    -0.63
    ERC
    -0.62
     visitation
    -0.61
    UTERS
    -0.60
    Madison
    -0.60
     Archangel
    -0.59
    POSITIVE LOGITS
    rane
    1.22
    orus
    1.14
    schild
    1.12
    lear
    1.03
    rome
    1.02
    ocolate
    1.01
    owa
    1.00
    inese
    0.97
    ambers
    0.95
    ocobo
    0.94
    Act Density 6.118%

    No Known Activations