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

    Neuronpedia

    INDEX
    Explanations

    pronouns that indicate possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thing
    -0.16
    onical
    -0.16
    aroo
    -0.15
    atti
    -0.14
    uur
    -0.13
    ostel
    -0.13
    gang
    -0.13
     cs
    -0.13
    ington
    -0.12
    ises
    -0.12
    POSITIVE LOGITS
     own
    0.26
    /her
    0.22
    zelf
    0.21
    self
    0.20
     próp
    0.19
    Own
    0.16
     Own
    0.16
    _own
    0.16
    SELF
    0.16
    utta
    0.15
    Act Density 0.960%

    No Known Activations