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

    Neuronpedia

    INDEX
    Explanations

    references to criticisms and critics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crit" in various forms, indicating a focus on critique or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velt
    -0.78
    orthy
    -0.76
    loo
    -0.72
    noon
    -0.69
     Shades
    -0.68
     Tale
    -0.62
    ¿½
    -0.62
    Accessory
    -0.61
    pora
    -0.61
    WD
    -0.61
    POSITIVE LOGITS
    erion
    1.43
    iques
    1.30
    ique
    1.28
    icism
    1.24
    iqu
    1.15
    eria
    1.07
    icals
    1.00
    ically
    1.00
    osure
    0.91
    iants
    0.88
    Act Density 0.016%

    No Known Activations