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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ington
    -0.15
    atti
    -0.15
    ness
    -0.13
     (
    -0.13
    ict
    -0.13
    ãĤ¢ãĥ«
    -0.13
    çļĦ大
    -0.13
     possibility
    -0.13
    illery
    -0.13
    itive
    -0.12
    POSITIVE LOGITS
     own
    0.39
    /her
    0.29
    SELF
    0.25
     próp
    0.25
    Own
    0.23
     Own
    0.23
    zelf
    0.22
    own
    0.21
    self
    0.20
     OWN
    0.20
    Act Density 0.950%

    No Known Activations