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

    Neuronpedia

    INDEX
    Explanations

    the word "normal" or variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to normalization and societal standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    better
    -0.76
    artisan
    -0.75
    hani
    -0.69
    leted
    -0.67
    iosyncr
    -0.67
    Winged
    -0.63
    resent
    -0.62
     Theft
    -0.62
    REL
    -0.62
    çīĪ
    -0.61
    POSITIVE LOGITS
    cy
    1.58
    ization
    1.45
    izing
    1.43
    ised
    1.40
    isation
    1.39
    izes
    1.32
    ising
    1.24
    ized
    1.24
    ize
    1.20
    izations
    1.17
    Act Density 0.042%

    No Known Activations