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

    Neuronpedia

    INDEX
    Explanations

    proper names followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals and references within a cultural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.76
    mble
    -0.74
    */(
    -0.70
    umbnails
    -0.69
    ĸļ
    -0.59
    sembly
    -0.59
    ãĤ´ãĥ³
    -0.57
    uyomi
    -0.57
     guid
    -0.56
    enegger
    -0.55
    POSITIVE LOGITS
     Creek
    0.68
     Island
    0.66
     Avenue
    0.66
     Street
    0.65
     Beach
    0.63
    eland
    0.61
    inia
    0.58
    Serv
    0.58
     Marsh
    0.57
     Lake
    0.56
    Act Density 0.791%

    No Known Activations