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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns related to individuals and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼
    -0.78
    eers
    -0.78
     Defin
    -0.72
    Æ
    -0.71
    webkit
    -0.70
     largeDownload
    -0.69
    pri
    -0.68
    PN
    -0.66
    Nic
    -0.64
    otin
    -0.64
    POSITIVE LOGITS
     own
    1.58
     travels
    0.99
     arrival
    0.98
     predecessors
    0.98
     journey
    0.97
     initial
    0.95
     debut
    0.95
     predecessor
    0.95
     allotted
    0.94
     journeys
    0.93
    Act Density 0.215%

    No Known Activations