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

    Neuronpedia

    INDEX
    Explanations

    references to universities and academic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gross
    -0.16
    andler
    -0.16
    oron
    -0.15
     Coff
    -0.15
     gross
    -0.14
    agra
    -0.14
    zer
    -0.14
    endid
    -0.14
    acer
    -0.13
     Princip
    -0.13
    POSITIVE LOGITS
    елен
    0.15
    ÑĢаÑģ
    0.15
    ryn
    0.14
     è¡ĮæĶ¿
    0.14
    .Raise
    0.14
    ngo
    0.14
    329
    0.14
    pike
    0.14
    ataka
    0.14
     Relay
    0.14
    Act Density 0.702%

    No Known Activations