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

    Neuronpedia

    INDEX
    Explanations

    references to film-related terms like movie collections or critical reviews

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "critique" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velt
    -0.76
    noon
    -0.73
    orthy
    -0.72
    loo
    -0.71
    Leary
    -0.68
    gypt
    -0.66
    pires
    -0.65
    ¿½
    -0.65
    XT
    -0.64
    pora
    -0.63
    POSITIVE LOGITS
    erion
    1.43
    ique
    1.19
    iques
    1.15
    icism
    1.13
    eria
    1.05
    iqu
    1.00
     Crit
    0.94
    osure
    0.88
    ically
    0.86
    icals
    0.83
    Act Density 0.006%

    No Known Activations