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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.80
    himself
    -0.61
     infarction
    -0.56
     которому
    -0.55
    xk
    -0.52
     is
    -0.52
    فيلم
    -0.51
     Obispo
    -0.51
    phalt
    -0.50
     stenosis
    -0.49
    POSITIVE LOGITS
     their
    1.94
    Their
    1.87
     Their
    1.77
    their
    1.74
     THEIR
    1.72
     themselves
    1.54
     thier
    1.47
     leurs
    1.34
    themselves
    1.34
     Leur
    1.24
    Act Density 0.093%

    No Known Activations