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

    Neuronpedia

    INDEX
    Explanations

    references to bilateral relationships or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITER
    -0.15
    ipl
    -0.15
    ray
    -0.15
    uve
    -0.15
    illa
    -0.15
     Lau
    -0.14
    RAY
    -0.14
     Dry
    -0.14
    ibold
    -0.14
    lek
    -0.14
    POSITIVE LOGITS
    obus
    0.15
    thon
    0.15
    yz
    0.15
    ebek
    0.15
    stral
    0.15
    aes
    0.14
    blr
    0.14
    arez
    0.14
    egade
    0.14
    deaux
    0.14
    Act Density 0.001%

    No Known Activations