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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns followed by nouns, with a focus on personal ownership or association

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itect
    -0.79
    ocument
    -0.78
    redits
    -0.66
    ablishment
    -0.66
    inctions
    -0.66
    atel
    -0.65
    lahoma
    -0.63
    ibaba
    -0.63
    atable
    -0.62
    daq
    -0.62
    POSITIVE LOGITS
     own
    1.63
     newfound
    1.06
     favourite
    1.00
     favorite
    0.99
     superiors
    0.97
     entire
    0.97
     surroundings
    0.96
     beloved
    0.95
     usual
    0.94
     grandmother
    0.93
    Act Density 0.397%

    No Known Activations