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

    Neuronpedia

    INDEX
    Explanations

    repeated first-person possessive pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     feroit
    -0.40
     kobieta
    -0.35
     escla
    -0.35
     poveznice
    -0.34
     provoquer
    -0.34
     kvinnor
    -0.33
    vább
    -0.33
     näm
    -0.33
     surgió
    -0.32
     planche
    -0.32
    POSITIVE LOGITS
     own
    1.30
    自己的
    0.84
    their
    0.79
     his
    0.79
     Their
    0.77
     ihrer
    0.77
     자신의
    0.76
     Own
    0.75
    Own
    0.75
    Their
    0.75
    Act Density 0.649%

    No Known Activations