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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by possessive adjectives

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating relationships or family connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.77
    vine
    -0.71
    pmwiki
    -0.67
    vell
    -0.60
    daq
    -0.59
     fools
    -0.59
    itect
    -0.59
    fulness
    -0.59
     comprom
    -0.58
    eele
    -0.57
    POSITIVE LOGITS
     own
    1.34
     namesake
    1.05
     father
    1.00
     hometown
    0.97
     newfound
    0.96
     classmates
    0.96
     eldest
    0.95
     peers
    0.94
     fian
    0.93
     cousin
    0.93
    Act Density 0.351%

    No Known Activations