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

    Neuronpedia

    INDEX
    Explanations

    phrases containing possessive nouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive constructions indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.88
    sson
    -0.78
    mo
    -0.71
    alys
    -0.70
    udeau
    -0.70
    forest
    -0.68
    dylib
    -0.68
     Spani
    -0.67
    anges
    -0.66
    èĪ
    -0.66
    POSITIVE LOGITS
     newest
    1.03
     own
    0.98
     flagship
    0.88
     finest
    0.88
     latest
    0.85
     biggest
    0.83
     sake
    0.77
    ullivan
    0.76
     signature
    0.75
     fastest
    0.74
    Act Density 0.138%

    No Known Activations