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

    Neuronpedia

    INDEX
    Explanations

    pronouns, possessive pronouns, and possessive determiners

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olkien
    -0.86
    adobe
    -0.78
    south
    -0.77
    arios
    -0.76
    wrap
    -0.74
    osate
    -0.72
    urch
    -0.71
    alyst
    -0.70
    needed
    -0.70
    western
    -0.70
    POSITIVE LOGITS
     name
    1.03
     majesty
    1.01
     guts
    1.00
     strengths
    0.99
     Majesty
    0.97
     corpse
    0.95
     weaknesses
    0.94
     birthday
    0.91
     plight
    0.90
     names
    0.89
    Act Density 0.345%

    No Known Activations