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

    Neuronpedia

    INDEX
    Explanations

    references to updates or changes in information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elden
    -0.17
    raf
    -0.16
    utter
    -0.15
    ken
    -0.15
     HERO
    -0.15
    hari
    -0.15
    kdir
    -0.14
    arshal
    -0.14
     Wer
    -0.14
    sher
    -0.14
    POSITIVE LOGITS
    asca
    0.15
     bid
    0.15
    etes
    0.15
     bids
    0.14
    oola
    0.14
    bid
    0.14
    NU
    0.14
    aga
    0.14
    fault
    0.14
    irie
    0.13
    Act Density 0.000%

    No Known Activations