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

    Neuronpedia

    INDEX
    Explanations

    mentions of familial relationships through the term "law"

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships through the term "in-law"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     periphery
    -0.65
     livest
    -0.64
    ħĭ
    -0.64
     achievable
    -0.63
     cumbers
    -0.62
    izoph
    -0.62
    chnology
    -0.62
     gobl
    -0.61
     maturity
    -0.60
     gratification
    -0.59
    POSITIVE LOGITS
    suit
    1.22
    yer
    1.15
    suits
    1.12
    yers
    1.10
    iard
    1.02
    ski
    1.00
    laws
    0.95
    lessness
    0.89
    law
    0.87
     Enforcement
    0.87
    Act Density 0.011%

    No Known Activations