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

    Neuronpedia

    INDEX
    Explanations

    specifically, possessive nouns ending in 's

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms, particularly the contraction "’s"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KT
    -0.81
    xxx
    -0.81
    Els
    -0.77
    ording
    -0.75
    livion
    -0.75
    ENN
    -0.74
    —-
    -0.73
    BT
    -0.72
    TAIN
    -0.71
    Ú
    -0.70
    POSITIVE LOGITS
     biggest
    1.00
     inability
    0.99
     newest
    0.97
     penchant
    0.94
     spokesman
    0.91
     own
    0.89
     detractors
    0.89
     youngest
    0.88
     unwillingness
    0.88
     fingerprints
    0.85
    Act Density 0.134%

    No Known Activations