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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    racuse
    -0.68
    vine
    -0.61
    ukong
    -0.60
     Provided
    -0.59
    uve
    -0.59
     divul
    -0.55
    spe
    -0.55
     Garner
    -0.54
    mable
    -0.54
    ilial
    -0.53
    POSITIVE LOGITS
     own
    1.43
    self
    1.03
    selves
    0.93
     OWN
    0.88
     Own
    0.82
     entire
    0.81
     usual
    0.80
     heaviest
    0.73
     customary
    0.73
    opic
    0.73
    Act Density 0.293%

    No Known Activations