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

    Neuronpedia

    INDEX
    Explanations

    company or service names that often end in 'inst'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of institutions or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.73
     shroud
    -0.69
    WAYS
    -0.65
     sight
    -0.64
     Learns
    -0.63
     distracting
    -0.63
     [+
    -0.61
    FORMATION
    -0.60
     silence
    -0.60
     gross
    -0.60
    POSITIVE LOGITS
    ington
    1.00
    idine
    0.98
    urion
    0.97
    aci
    0.97
    idium
    0.94
    atech
    0.93
    aq
    0.92
    atoon
    0.92
    acia
    0.92
    inia
    0.92
    Act Density 0.281%

    No Known Activations