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

    Neuronpedia

    INDEX
    Explanations

    references to spoilers in various contexts, particularly in media or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĤ
    -0.15
    mae
    -0.15
    unes
    -0.15
    agi
    -0.15
    elic
    -0.15
    avers
    -0.15
    ELY
    -0.15
    istrovstvÃŃ
    -0.15
    -LAST
    -0.14
     Crus
    -0.14
    POSITIVE LOGITS
     spo
    0.29
    Spo
    0.26
    spo
    0.25
     Spo
    0.23
    iler
    0.21
    à¹Īำ
    0.19
    ilers
    0.19
    cial
    0.18
    ilt
    0.17
    ils
    0.17
    Act Density 0.011%

    No Known Activations