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

    Neuronpedia

    INDEX
    Explanations

    references to specific times and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acons
    -0.18
     Snape
    -0.18
    EndElement
    -0.17
    ãĥ³ãĤº
    -0.16
    HLT
    -0.16
    ugu
    -0.16
    elyn
    -0.15
     полÑĮз
    -0.15
    Hibernate
    -0.14
     Susp
    -0.14
    POSITIVE LOGITS
    LOY
    0.16
    iset
    0.15
    atak
    0.15
    eters
    0.15
    ETERS
    0.15
    ERA
    0.14
    oun
    0.14
    oter
    0.14
    riage
    0.14
     slog
    0.14
    Act Density 0.021%

    No Known Activations