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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical proofs and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    innacle
    -0.15
    uden
    -0.14
    Studio
    -0.14
    ropy
    -0.13
    RAND
    -0.13
    rown
    -0.13
    itzer
    -0.13
    æŀ¶
    -0.12
    .FontStyle
    -0.12
     cig
    -0.12
    POSITIVE LOGITS
    adata
    0.15
    *pow
    0.15
    ByExample
    0.14
    .spin
    0.14
     §§
    0.14
    ارا
    0.13
    .getSeconds
    0.13
    argo
    0.13
     searchData
    0.13
    rana
    0.12
    Act Density 0.059%

    No Known Activations