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

    Neuronpedia

    INDEX
    Explanations

    phrases related to real-life situations or facts

    oai_token-act-pair · gpt-3.5-turbo

    references to social, economic, and political realities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fight
    -0.70
    nesty
    -0.69
    BUG
    -0.65
    Harris
    -0.65
    rip
    -0.65
    Naz
    -0.65
    ded
    -0.62
    lier
    -0.62
    idine
    -0.62
    raid
    -0.62
    POSITIVE LOGITS
    uggest
    1.07
    etter
    1.07
    atisf
    1.01
    omething
    0.99
    hops
    0.99
    cape
    0.96
    hips
    0.95
    ettings
    0.94
    poons
    0.91
    ongs
    0.90
    Act Density 0.060%

    No Known Activations