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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and their associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.27
     his
    -0.22
     його
    -0.20
    his
    -0.19
     Himself
    -0.17
     его
    -0.17
     His
    -0.16
    His
    -0.16
     jeho
    -0.16
     jego
    -0.16
    POSITIVE LOGITS
     yourself
    0.33
     yourselves
    0.26
    SELF
    0.26
     own
    0.23
    ths
    0.22
    ’e
    0.22
    your
    0.21
    ’re
    0.20
     your
    0.20
    nger
    0.20
    Act Density 0.218%

    No Known Activations