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

    Neuronpedia

    INDEX
    Explanations

    references to duality or pairs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onda
    -0.16
    uring
    -0.15
    iali
    -0.15
    akens
    -0.14
    -League
    -0.14
    isp
    -0.14
    pag
    -0.13
    िड
    -0.13
    NR
    -0.13
    erv
    -0.13
    POSITIVE LOGITS
     sides
    0.25
     halves
    0.24
     side
    0.23
    -side
    0.19
     directions
    0.19
     legs
    0.18
     twin
    0.18
    æĸ¹åIJij
    0.18
     Twin
    0.17
    -sided
    0.17
    Act Density 0.154%

    No Known Activations