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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to patents and inventions

    oai_token-act-pair · gpt-3.5-turbo

    references to inventions and intellectual property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andra
    -0.77
    iland
    -0.70
    spin
    -0.69
    etta
    -0.68
    cium
    -0.68
    icka
    -0.67
    ça
    -0.67
    orde
    -0.66
    coal
    -0.65
    vez
    -0.65
    POSITIVE LOGITS
    uyomi
    0.91
    rious
    0.82
    geist
    0.80
    urable
    0.80
    eer
    0.77
     inventor
    0.74
    ItemTracker
    0.74
    eers
    0.73
    eering
    0.72
    ENTION
    0.72
    Act Density 0.023%

    No Known Activations