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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a person's possessions or activities

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the pronoun "his"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocument
    -0.79
    itect
    -0.78
    Trend
    -0.69
    anguage
    -0.69
    daq
    -0.69
     largeDownload
    -0.69
    amazon
    -0.69
    IVERS
    -0.68
    eers
    -0.68
    uve
    -0.68
    POSITIVE LOGITS
     own
    1.61
    panic
    1.44
     Majesty
    1.18
     wife
    1.14
     father
    1.11
     predecessor
    1.03
    sing
    1.02
     namesake
    1.00
     superiors
    0.99
     brother
    0.99
    Act Density 0.292%

    No Known Activations