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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive nouns indicating ownership

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns related to individuals in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arios
    -0.88
    ACP
    -0.79
    adobe
    -0.78
    lahoma
    -0.77
    ierre
    -0.76
    execute
    -0.75
    zzo
    -0.74
    angular
    -0.74
    claimer
    -0.70
    agree
    -0.70
    POSITIVE LOGITS
     Majesty
    1.18
     majesty
    1.12
     deepest
    0.83
     footsteps
    0.82
     sensibilities
    0.79
     treacher
    0.77
     eyes
    0.75
     pronunciation
    0.74
     unmarked
    0.74
     newest
    0.74
    Act Density 0.231%

    No Known Activations