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

    Neuronpedia

    INDEX
    Explanations

    personal possessive pronouns, specifically "my"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "my"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apiece
    -0.84
     respectively
    -0.78
    ibaba
    -0.73
     guiIcon
    -0.70
    vernment
    -0.68
    itect
    -0.66
    illac
    -0.66
    leground
    -0.61
     characterized
    -0.61
    etz
    -0.60
    POSITIVE LOGITS
    anmar
    1.27
     husband
    1.21
    stery
    1.21
    opic
    1.15
     wife
    1.13
    ocard
    1.13
     dad
    1.10
    opia
    1.09
     own
    1.03
     colleague
    1.01
    Act Density 0.125%

    No Known Activations