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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to people or characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The," indicating a focus on introductions or titles in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pai
    -0.79
    peak
    -0.71
    æ³
    -0.70
    herer
    -0.69
    estamp
    -0.68
     ï
    -0.67
    rade
    -0.67
    etooth
    -0.66
    Index
    -0.66
    payer
    -0.65
    POSITIVE LOGITS
     sequel
    1.31
     film
    1.21
     screenplay
    1.17
     movie
    1.14
     filmmakers
    1.13
     studio
    1.08
     remake
    1.07
     actress
    1.06
     actor
    1.05
     reboot
    1.05
    Act Density 0.194%

    No Known Activations