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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning specific names of individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    names of people, countries, and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.89
     Norn
    -0.74
    Marginal
    -0.67
     STATS
    -0.67
     IMAGES
    -0.67
     Archdemon
    -0.66
    ãĤ£
    -0.66
     Duffy
    -0.66
     ãĤµ
    -0.64
    ãĤ¤ãĥĪ
    -0.62
    POSITIVE LOGITS
    iest
    0.75
    ÃŃs
    0.72
    's
    0.71
     il
    0.71
    exclusive
    0.67
    lez
    0.64
    kind
    0.63
    ieri
    0.62
    ottest
    0.61
    /
    0.60
    Act Density 0.228%

    No Known Activations