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

    Neuronpedia

    INDEX
    Explanations

    words related to political and social concepts related to policies and actions, often ending in 'ization'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of "ization" processes, such as urbanization and privatization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ube
    -0.73
     CLIENT
    -0.70
    awan
    -0.69
    puter
    -0.66
    abase
    -0.65
     Wem
    -0.65
    gerald
    -0.64
    bah
    -0.64
     Malone
    -0.63
    quart
    -0.62
    POSITIVE LOGITS
    ism
    0.94
     tendencies
    0.90
    ist
    0.90
     efforts
    0.89
     processes
    0.87
    eering
    0.87
     effected
    0.86
     occurring
    0.86
     wrought
    0.86
     process
    0.85
    Act Density 0.222%

    No Known Activations