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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns referring to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -1.02
    pload
    -0.74
    eers
    -0.73
    Downloadha
    -0.70
    skirts
    -0.70
    ices
    -0.69
    eus
    -0.69
    eday
    -0.69
    aspers
    -0.68
    aker
    -0.67
    POSITIVE LOGITS
     impending
    0.86
     own
    0.84
     surroundings
    0.84
     respective
    0.79
     utmost
    0.77
     beloved
    0.72
     particular
    0.69
     descent
    0.68
     choosing
    0.66
     namesake
    0.66
    Act Density 0.277%

    No Known Activations