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

    Neuronpedia

    INDEX
    Explanations

    terms related to family relationships, such as parents and grandparents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to familial relationships and maternal or parental concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hered
    -0.95
    liness
    -0.92
    cellent
    -0.92
    lies
    -0.90
    rett
    -0.89
    eller
    -0.89
    bler
    -0.86
    trap
    -0.85
    aroo
    -0.85
    rieg
    -0.84
    POSITIVE LOGITS
    ities
    0.97
     competence
    0.88
    ized
    0.87
     hygiene
    0.86
    ised
    0.82
     liberties
    0.82
     equivalents
    0.82
     incap
    0.81
     indisc
    0.80
     objections
    0.79
    Act Density 0.074%

    No Known Activations