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

    Neuronpedia

    INDEX
    Explanations

    proper nouns involving names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesday
    -0.72
    ankind
    -0.62
    aukee
    -0.60
    eatures
    -0.59
     remem
    -0.55
    ascus
    -0.55
    mercial
    -0.54
    glers
    -0.54
    ippi
    -0.54
    urrencies
    -0.53
    POSITIVE LOGITS
    ansas
    0.82
    itect
    0.79
    inian
    0.76
     Cortex
    0.70
    ondo
    0.68
    agos
    0.67
    awi
    0.66
    INAL
    0.65
    ements
    0.64
    Spoiler
    0.63
    Act Density 0.070%

    No Known Activations