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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating personal ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ington
    -0.16
    ignum
    -0.14
    atti
    -0.14
    ering
    -0.14
    ord
    -0.13
    ially
    -0.13
    ords
    -0.12
    ness
    -0.12
    ERING
    -0.12
    /OR
    -0.12
    POSITIVE LOGITS
     own
    0.50
    /her
    0.33
     próp
    0.29
     Own
    0.28
    Own
    0.28
    own
    0.28
    self
    0.25
    SELF
    0.25
    zelf
    0.25
     respective
    0.24
    Act Density 0.959%

    No Known Activations