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

    Neuronpedia

    INDEX
    Explanations

    possessive forms indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wife
    -0.16
     personally
    -0.15
     his
    -0.15
     Wife
    -0.15
    his
    -0.15
     commute
    -0.14
     son
    -0.14
     ego
    -0.13
     himself
    -0.13
     ÙĪزار
    -0.13
    POSITIVE LOGITS
     own
    0.28
     latest
    0.23
     newest
    0.23
     próp
    0.18
    latest
    0.18
    propri
    0.18
     subsidiary
    0.18
     itself
    0.17
     largest
    0.17
    raison
    0.17
    Act Density 0.248%

    No Known Activations