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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and phrases indicating ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENCE
    -0.77
    umption
    -0.74
    otto
    -0.73
    ĸļ
    -0.72
     Trader
    -0.72
    rium
    -0.71
    enment
    -0.69
    matter
    -0.68
    hip
    -0.68
    Spoiler
    -0.68
    POSITIVE LOGITS
     favorite
    1.04
     favorites
    1.04
     favourite
    1.02
     assistants
    0.94
     favourites
    0.93
     own
    0.93
     daughters
    0.92
     buddies
    0.89
     predecessors
    0.88
     sons
    0.87
    Act Density 0.073%

    No Known Activations