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

    Neuronpedia

    INDEX
    Explanations

    numeric representations of fractions and their corresponding terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rell
    -0.17
    sian
    -0.17
    .scalablytyped
    -0.16
    cox
    -0.14
    ä¹ħ
    -0.14
    aul
    -0.14
    FT
    -0.13
    /manual
    -0.13
     AUX
    -0.13
    FormData
    -0.13
    POSITIVE LOGITS
     fifth
    0.38
     sixth
    0.36
     seventh
    0.35
     fourth
    0.35
     eighth
    0.34
     tenth
    0.34
     fif
    0.33
     ninth
    0.32
     Sixth
    0.30
    Fourth
    0.30
    Act Density 0.031%

    No Known Activations