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

    Neuronpedia

    INDEX
    Explanations

    references to literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еж
    -0.17
    ugas
    -0.17
    æ¡IJ
    -0.17
     spar
    -0.16
    λÏį
    -0.16
    ech
    -0.15
    wright
    -0.15
    uido
    -0.14
    endas
    -0.14
    á¹
    -0.14
    POSITIVE LOGITS
    ature
    0.41
    atura
    0.35
    atur
    0.35
    atures
    0.35
    ATURE
    0.33
    acy
    0.29
    ally
    0.24
    ary
    0.24
    atural
    0.23
     nature
    0.23
    Act Density 0.008%

    No Known Activations