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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gram
    -0.66
     Paste
    -0.65
    vi
    -0.64
    ocument
    -0.64
    webkit
    -0.62
    microsoft
    -0.62
    umbered
    -0.61
    ãĤ¹ãĥĪ
    -0.61
    tery
    -0.60
    packages
    -0.59
    POSITIVE LOGITS
     detriment
    1.29
     liking
    1.22
     fullest
    1.22
     own
    1.19
     knees
    1.14
    venge
    1.04
     respective
    0.99
     conclusion
    0.98
     rightful
    0.95
     destination
    0.93
    Act Density 0.112%

    No Known Activations