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

    Neuronpedia

    INDEX
    Explanations

    references to classic movies, music, and other favorites

    oai_token-act-pair · gpt-3.5-turbo

    mentions of classic movies and favorites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asse
    -0.72
    rain
    -0.71
    Delivery
    -0.69
    otor
    -0.68
    asus
    -0.66
    irection
    -0.65
    xious
    -0.65
     constitution
    -0.64
    armac
    -0.62
    volent
    -0.61
    POSITIVE LOGITS
    paces
    1.27
    poons
    1.14
    hip
    1.07
    uggest
    1.05
    aurus
    1.05
    pace
    1.01
    ngth
    0.99
    ettings
    0.96
    peak
    0.94
    ervative
    0.93
    Act Density 0.081%

    No Known Activations