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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and organizations involved in news events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wonderland
    -0.72
    amental
    -0.69
     Savior
    -0.67
     DEBUG
    -0.64
    ocaust
    -0.64
     Marble
    -0.63
     moons
    -0.63
     reson
    -0.61
    viously
    -0.61
     bombshell
    -0.61
    POSITIVE LOGITS
    akh
    0.99
    awi
    0.89
    aka
    0.89
    uddin
    0.88
    aji
    0.86
    dar
    0.85
    adh
    0.85
    nar
    0.83
    anu
    0.81
    kus
    0.81
    Act Density 0.038%

    No Known Activations