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

    Neuronpedia

    INDEX
    Explanations

    phrases with the possessive pronoun "their"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "their" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wrap
    -0.76
    iti
    -0.75
    hin
    -0.75
     Unsure
    -0.74
    ean
    -0.70
    mast
    -0.70
    ominated
    -0.69
    atever
    -0.68
    smith
    -0.68
    netflix
    -0.68
    POSITIVE LOGITS
     respective
    1.54
    selves
    1.43
     own
    1.43
     selves
    1.24
     predecessors
    1.05
     counterparts
    1.03
     asses
    0.98
    self
    0.97
     minds
    0.97
     successors
    0.96
    Act Density 0.221%

    No Known Activations