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

    Neuronpedia

    INDEX
    Explanations

    mentions of critiquing or criticism

    oai_token-act-pair · gpt-3.5-turbo

    references or mentions of critiques and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.76
    loo
    -0.69
     Aad
    -0.69
    velt
    -0.67
     Mandela
    -0.64
     Patent
    -0.64
     Permanent
    -0.63
    noon
    -0.63
     Petty
    -0.62
     Argent
    -0.61
    POSITIVE LOGITS
    erion
    1.45
    ique
    1.34
    iques
    1.30
    icism
    1.23
    iqu
    1.17
    eria
    1.06
    ters
    1.00
    ically
    0.99
    ter
    0.90
    icals
    0.87
    Act Density 0.041%

    No Known Activations