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

    Neuronpedia

    INDEX
    Explanations

    references to scientific publications and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eries
    -0.15
    rane
    -0.15
    ana
    -0.14
    ows
    -0.14
    adia
    -0.14
     sober
    -0.14
    hots
    -0.14
     standby
    -0.14
     Pleasant
    -0.14
    anya
    -0.14
    POSITIVE LOGITS
    SessionFactory
    0.16
    COMPARE
    0.15
    ãĥĸ
    0.15
    nic
    0.15
    Alchemy
    0.15
    ÏĨη
    0.15
    eah
    0.15
    abwe
    0.15
     kosten
    0.14
    icular
    0.14
    Act Density 0.037%

    No Known Activations