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

    Neuronpedia

    INDEX
    Explanations

    references to news articles or press releases

    oai_token-act-pair · gpt-3.5-turbo

    references to the Associated Press (AP) news agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.76
     Britann
    -0.72
     Labrador
    -0.70
     Fenrir
    -0.69
     Jew
    -0.68
     Lieberman
    -0.68
    ãĥīãĥ©ãĤ´ãĥ³
    -0.64
     true
    -0.64
     Grimm
    -0.62
     Labour
    -0.62
    POSITIVE LOGITS
    PLIED
    1.23
    AP
    1.20
    PLIC
    1.11
    olicy
    1.08
    rison
    1.07
    ocalyptic
    1.06
    ocalypse
    1.01
    apa
    1.00
    aeda
    0.99
    olitan
    0.99
    Act Density 0.006%

    No Known Activations