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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive adjectives referring to people or groups performing actions

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups performing their responsibilities or jobs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Izan
    -0.66
    forth
    -0.64
    eter
    -0.62
    trl
    -0.61
    isson
    -0.61
    ablishment
    -0.60
    usher
    -0.59
     Provided
    -0.58
    arthed
    -0.57
    racuse
    -0.57
    POSITIVE LOGITS
     own
    1.41
     utmost
    1.09
     usual
    1.07
     homework
    0.97
     rightful
    0.95
     OWN
    0.92
     customary
    0.91
    self
    0.90
     best
    0.90
     Own
    0.85
    Act Density 0.084%

    No Known Activations