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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership or association

    oai_token-act-pair · gpt-3.5-turbo

    pronouns related to possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilial
    -0.64
     Mahm
    -0.62
     Sonia
    -0.61
    haus
    -0.61
    ared
    -0.60
    ogan
    -0.59
    bender
    -0.59
    hov
    -0.59
     Izan
    -0.58
     Liang
    -0.58
    POSITIVE LOGITS
     bearings
    1.28
     own
    1.24
     footing
    1.02
    selves
    0.91
    self
    0.89
     revenge
    0.85
     feet
    0.84
    elf
    0.84
     rightful
    0.83
     knees
    0.80
    Act Density 0.106%

    No Known Activations