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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific technical elements or components

    oai_token-act-pair · gpt-3.5-turbo

    the term "bits" in various contexts, particularly related to technology and digital media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammad
    -0.78
    WAY
    -0.71
     SOS
    -0.67
     Physicians
    -0.67
     Predators
    -0.63
    NOR
    -0.62
     Kremlin
    -0.61
    INE
    -0.58
    ordan
    -0.57
     dire
    -0.57
    POSITIVE LOGITS
    wagon
    0.99
    meal
    0.98
    bits
    0.93
    terness
    0.92
    cake
    0.88
     bits
    0.87
    acies
    0.84
    wana
    0.84
    itives
    0.83
    umen
    0.82
    Act Density 0.015%

    No Known Activations