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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and titles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ubes
    -0.74
    iculture
    -0.73
    ifference
    -0.71
    icultural
    -0.70
    heast
    -0.69
    jandro
    -0.69
    heastern
    -0.69
    hesda
    -0.66
    urances
    -0.65
    istries
    -0.65
    POSITIVE LOGITS
     abbre
    1.15
     shorthand
    1.12
     acronym
    1.11
    pron
    1.08
     meaning
    1.05
     abbrevi
    1.02
     coined
    1.00
     referring
    0.97
     initials
    0.93
     Meaning
    0.93
    Act Density 0.197%

    No Known Activations