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

    Neuronpedia

    INDEX
    Explanations

    scientific article citations with digital object identifiers (DOIs)

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    reon
    -1.01
    zees
    -0.85
    vae
    -0.84
     clitor
    -0.84
    quickShipAvailable
    -0.82
    ises
    -0.81
    awaru
    -0.81
    ONSORED
    -0.80
    upon
    -0.79
    Pokémon
    -0.77
    POSITIVE LOGITS
    174
    0.99
    016
    0.97
    322
    0.97
    018
    0.96
    424
    0.95
    502
    0.93
    114
    0.92
    217
    0.91
    506
    0.90
    451
    0.89
    Act Density 0.229%

    No Known Activations