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

    Neuronpedia

    INDEX
    Explanations

    references to complexity and complicated situations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orra
    -0.16
    anta
    -0.15
    annis
    -0.15
    993
    -0.15
    é®
    -0.15
    ikip
    -0.15
    ATCH
    -0.15
    èŃ
    -0.15
    onta
    -0.14
    oz
    -0.14
    POSITIVE LOGITS
     complexity
    0.20
    ÃŃch
    0.17
     Complexity
    0.17
     complicated
    0.16
     enough
    0.16
     Candid
    0.15
    cob
    0.15
    PU
    0.15
    alive
    0.14
     drib
    0.14
    Act Density 0.041%

    No Known Activations