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

    Neuronpedia

    INDEX
    Explanations

    organizations, companies, or institutions referenced in news articles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to institutions, organizations, and media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otos
    -0.70
    tein
    -0.66
    ultimate
    -0.64
     grandson
    -0.64
    awar
    -0.62
    apego
    -0.61
    sole
    -0.59
    CHAT
    -0.59
    potion
    -0.59
     heroism
    -0.58
    POSITIVE LOGITS
    hips
    1.27
     such
    1.05
    hip
    1.00
     including
    0.96
    '
    0.95
    hops
    0.93
     worldwide
    0.91
     alike
    0.89
    paces
    0.87
     vying
    0.87
    Act Density 0.265%

    No Known Activations