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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ablishment
    -0.94
    ittees
    -0.80
    ciation
    -0.79
    redits
    -0.78
    20439
    -0.76
    Ú
    -0.74
    aneers
    -0.73
    ovo
    -0.73
    à¼
    -0.71
    itect
    -0.71
    POSITIVE LOGITS
     own
    1.40
     grandmother
    1.19
     roommate
    1.16
     mother
    1.16
     girlfriend
    1.15
    self
    1.15
     mom
    1.14
     dad
    1.14
     parents
    1.13
     teammates
    1.13
    Act Density 0.361%

    No Known Activations