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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific capitalized letters, abbreviations, or references likely related to a particular category or brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ت
    -0.21
    оÑĢ
    -0.18
    orex
    -0.18
    upt
    -0.18
    ant
    -0.17
    ace
    -0.16
    echa
    -0.16
    uvw
    -0.16
    ix
    -0.16
    kek
    -0.15
    POSITIVE LOGITS
     rom
    0.23
    yi
    0.20
     requ
    0.18
    oward
    0.18
    oton
    0.17
    ench
    0.16
    eni
    0.16
     resh
    0.16
    ugal
    0.16
    omor
    0.16
    Act Density 0.122%

    No Known Activations