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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating others or an entity called "They."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "They."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     limited
    -0.55
     luck
    -0.55
     balance
    -0.55
     confidence
    -0.54
     advice
    -0.53
     awareness
    -0.51
     himself
    -0.51
     steps
    -0.50
     track
    -0.50
     past
    -0.50
    POSITIVE LOGITS
     They
    2.94
    They
    2.54
     Their
    2.42
    Their
    2.17
    they
    2.17
     THEY
    2.10
    their
    1.72
     they
    1.58
     THEIR
    1.54
     These
    1.52
    Act Density 0.043%

    No Known Activations