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

    Neuronpedia

    INDEX
    Explanations

    phrases with the pronoun "They"

    oai_token-act-pair · gpt-3.5-turbo

    references to a subject referred to as "They."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CCC
    -0.79
     Eleven
    -0.68
    âĺħâĺħ
    -0.67
    âĢ¢âĢ¢
    -0.63
     Amen
    -0.63
     Sirius
    -0.63
    duc
    -0.62
    ige
    -0.62
    album
    -0.62
    Rating
    -0.61
    POSITIVE LOGITS
    're
    1.15
    'll
    1.07
    selves
    1.03
    pherd
    1.02
    zbollah
    1.00
    've
    0.97
    'd
    0.88
    self
    0.86
    gemony
    0.86
    reditary
    0.85
    Act Density 0.192%

    No Known Activations