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

    Neuronpedia

    INDEX
    Explanations

    pronouns 'it', 'her', or 'the' referring to something specific in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Politics
    -0.58
     Polk
    -0.57
     Queens
    -0.57
     Wanted
    -0.56
     abortions
    -0.56
     Jacksonville
    -0.56
     Angola
    -0.56
     Instruments
    -0.55
     Pearce
    -0.54
     Balls
    -0.53
    POSITIVE LOGITS
    alian
    1.65
    self
    1.39
    chy
    1.36
    atic
    1.26
    unes
    1.20
    atically
    1.11
    's
    0.94
    asca
    0.94
    selves
    0.89
    atical
    0.88
    Act Density 0.197%

    No Known Activations