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

    Neuronpedia

    INDEX
    Explanations

    superlatives or rankings of countries, cities, diseases, packages, sports, movies, and other entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating rankings or statistics related to population, popularity, and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ité
    -0.69
    roth
    -0.66
    yon
    -0.65
    prototype
    -0.64
    ACY
    -0.64
    norm
    -0.63
    isson
    -0.63
     Orient
    -0.63
    raq
    -0.62
    ighting
    -0.60
    POSITIVE LOGITS
     earners
    0.84
     answ
    0.80
     unsolved
    0.73
     active
    0.72
     drawer
    0.68
    olulu
    0.68
     inactive
    0.68
    oppers
    0.67
     hinder
    0.66
     cooperating
    0.65
    Act Density 0.067%

    No Known Activations