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

    Neuronpedia

    INDEX
    Explanations

    references to cultural and artistic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĮ
    -0.15
    ationally
    -0.14
    iable
    -0.14
    ãĥ«ãĤ¯
    -0.14
    ìŁģ
    -0.14
    алÑİ
    -0.14
    ildo
    -0.13
    opup
    -0.13
    rellas
    -0.13
    intros
    -0.13
    POSITIVE LOGITS
     wonder
    0.29
     power
    0.28
     essence
    0.27
     spirit
    0.27
     maj
    0.26
     wonders
    0.26
     beauty
    0.25
     rich
    0.25
     ess
    0.25
     magic
    0.24
    Act Density 0.222%

    No Known Activations