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

    Neuronpedia

    INDEX
    Explanations

    references to a specific company or brand

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific fast-food chain or brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dru
    -0.77
     heck
    -0.65
    lihood
    -0.65
    Downloadha
    -0.65
     Ples
    -0.64
     Arbor
    -0.64
    ãĤ°
    -0.62
     Twain
    -0.61
     Gabriel
    -0.61
     Heck
    -0.60
    POSITIVE LOGITS
    FC
    1.00
    ritical
    0.90
    ranch
    0.90
    asting
    0.89
    ombat
    0.87
    urrent
    0.87
    erning
    0.85
    asters
    0.84
    urry
    0.83
    riad
    0.82
    Act Density 0.006%

    No Known Activations