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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically related to organizations or people

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to council or governing bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MQ
    -0.71
     Rabbit
    -0.66
    ATES
    -0.65
    çĭ
    -0.65
    >>>>
    -0.64
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.63
    DEV
    -0.63
     TAMADRA
    -0.62
    FORE
    -0.61
    UP
    -0.60
    POSITIVE LOGITS
    oun
    1.70
    stant
    1.20
    emouth
    1.11
    onsense
    1.01
    ciation
    0.97
    spe
    0.94
    mers
    0.91
    thouse
    0.90
    nel
    0.90
    nown
    0.89
    Act Density 0.006%

    No Known Activations