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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and generational ties

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inver
    -0.74
    jad
    -0.73
    ilater
    -0.66
     poles
    -0.62
     comet
    -0.61
     gel
    -0.60
    nyder
    -0.60
    prus
    -0.59
     complementary
    -0.59
    ournals
    -0.57
    POSITIVE LOGITS
     Mania
    0.78
    eering
    0.70
    eus
    0.68
    #$
    0.68
    interstitial
    0.67
    roid
    0.64
    esis
    0.64
    ean
    0.63
    uries
    0.62
    eer
    0.62
    Act Density 0.082%

    No Known Activations