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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.78
    inctions
    -0.71
    ocument
    -0.70
    ciation
    -0.66
    opsis
    -0.65
    ibaba
    -0.65
    uve
    -0.64
    note
    -0.63
     Photograph
    -0.63
     Papers
    -0.62
    POSITIVE LOGITS
     superiors
    1.43
     own
    1.38
     neighbour
    1.32
     neighbours
    1.32
     fellow
    1.31
     peers
    1.31
     colleagues
    1.29
     friends
    1.27
    self
    1.25
     neighbors
    1.23
    Act Density 0.274%

    No Known Activations