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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive pronouns indicating a person

    oai_token-act-pair · gpt-3.5-turbo

    references to personal pronouns and their corresponding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.70
    amily
    -0.59
    IVERS
    -0.55
    andel
    -0.54
     unden
    -0.52
    itely
    -0.50
     Prompt
    -0.50
     cancellation
    -0.49
     alike
    -0.48
     both
    -0.48
    POSITIVE LOGITS
    /
    1.43
    panic
    1.25
    /
    1.10
    /.
    1.05
    /#
    1.05
     or
    1.05
    /,
    1.04
    /$
    1.01
    /_
    0.96
    /(
    0.95
    Act Density 0.258%

    No Known Activations