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

    Neuronpedia

    INDEX
    Explanations

    mentions of family relationships, particularly focusing on in-laws

    oai_token-act-pair · gpt-3.5-turbo

    references to legal relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izoph
    -0.77
     periphery
    -0.70
     Flavoring
    -0.68
     livest
    -0.68
     nervous
    -0.67
     speculative
    -0.66
     Governors
    -0.64
     untreated
    -0.63
    ggies
    -0.63
     serious
    -0.63
    POSITIVE LOGITS
    yers
    1.18
    suit
    1.12
    suits
    1.10
    laws
    1.08
    yer
    1.08
    ski
    1.03
    iard
    0.99
    eering
    0.96
    law
    0.96
    eer
    0.92
    Act Density 0.007%

    No Known Activations