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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or inadequacy in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iq
    -0.15
    ADS
    -0.14
    δή
    -0.14
     enough
    -0.14
     Pok
    -0.14
     fewer
    -0.14
    irim
    -0.14
    alendar
    -0.13
    ë
    -0.13
    boy
    -0.13
    POSITIVE LOGITS
    auc
    0.17
     no
    0.17
    'gc
    0.17
    utra
    0.16
    Indexed
    0.15
    ayan
    0.15
     Absolutely
    0.15
     offers
    0.15
     riot
    0.15
     offer
    0.15
    Act Density 0.235%

    No Known Activations