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

    Neuronpedia

    INDEX
    Explanations

    country names or names of significant places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to countries, organizations, or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.80
    ãĥł
    -0.75
    lihood
    -0.70
    alyses
    -0.70
     VIDEOS
    -0.69
    ries
    -0.68
    comings
    -0.68
    ousands
    -0.65
    mares
    -0.65
    ãĥ´
    -0.64
    POSITIVE LOGITS
    isible
    0.92
     incarn
    0.84
    actly
    0.79
     reborn
    0.76
     Certified
    0.75
    ophobic
    0.75
    eligible
    0.73
    worthy
    0.71
     equivalent
    0.70
    stown
    0.68
    Act Density 0.364%

    No Known Activations