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

    Neuronpedia

    INDEX
    Explanations

    words related to institutional systems and policies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systemic or institutional issues and abuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nen
    -0.86
    uden
    -0.76
    cius
    -0.76
    spell
    -0.73
    llan
    -0.72
    vous
    -0.72
    bane
    -0.71
    hammad
    -0.70
    aday
    -0.68
    ertodd
    -0.67
    POSITIVE LOGITS
    ized
    1.44
    ised
    1.26
    ization
    1.18
    izational
    1.15
    izing
    1.12
    ize
    1.08
    izes
    1.06
     racism
    1.04
    ising
    1.03
    isation
    1.02
    Act Density 0.048%

    No Known Activations