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

    Neuronpedia

    INDEX
    Explanations

    words indicating relationships and conditional dependencies in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ile
    -0.15
     Trab
    -0.14
    outs
    -0.14
     dign
    -0.14
     bran
    -0.14
     duplic
    -0.14
    417
    -0.14
    à¹īำ
    -0.13
     refl
    -0.13
    iad
    -0.13
    POSITIVE LOGITS
     sake
    0.25
     purposes
    0.25
    chter
    0.16
    .addProperty
    0.15
     addCriterion
    0.15
     purpose
    0.15
    agos
    0.14
    æĿ¥è¯´
    0.14
    èº
    0.14
     reason
    0.14
    Act Density 0.088%

    No Known Activations