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

    Neuronpedia

    INDEX
    Explanations

    names of movies or shows

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically titles and names related to movies, shows, or notable works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prompting
    -0.69
    -0.68
    ÄŁ
    -0.65
     �
    -0.61
     ende
    -0.61
     listed
    -0.59
     confir
    -0.59
     --------
    -0.58
     separately
    -0.57
     Pry
    -0.57
    POSITIVE LOGITS
    ")
    1.36
    ").
    1.35
    "),
    1.30
    %"
    1.22
    "]
    1.22
    ",
    1.16
    ";
    1.16
    "
    1.14
    "?
    1.14
    ");
    1.13
    Act Density 0.237%

    No Known Activations