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

    Neuronpedia

    INDEX
    Explanations

    words related to the process of changing something to conform with a particular system or ideology

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of "ization," indicating processes or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilan
    -0.82
    monds
    -0.75
    agher
    -0.73
    Lear
    -0.71
    enegger
    -0.71
    itness
    -0.70
    rib
    -0.68
    thouse
    -0.68
    ergy
    -0.67
    VID
    -0.65
    POSITIVE LOGITS
    eering
    1.04
    ism
    0.82
    eers
    0.78
    ist
    0.75
    naire
    0.74
    xual
    0.73
    ISM
    0.73
     Pact
    0.70
     process
    0.69
    naires
    0.69
    Act Density 0.066%

    No Known Activations