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

    Neuronpedia

    INDEX
    Explanations

    pronouns related to possession

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns, specifically "their"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bear
    -0.74
    scape
    -0.74
     Unsure
    -0.73
    zz
    -0.72
    FP
    -0.70
    Thompson
    -0.69
    CCC
    -0.68
     Flan
    -0.67
    Ïĥ
    -0.67
    eers
    -0.66
    POSITIVE LOGITS
     own
    1.52
     respective
    1.48
    selves
    1.22
     selves
    1.11
     predecessors
    1.05
     namesake
    1.01
    self
    1.01
     successors
    0.97
     counterparts
    0.97
     newfound
    0.97
    Act Density 0.207%

    No Known Activations