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

    Neuronpedia

    INDEX
    Explanations

    curly braces and other mathematical notation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃĹ↵↵
    -0.17
    953
    -0.15
    sÃŃ
    -0.15
    FFE
    -0.14
    952
    -0.14
    ing
    -0.14
     stalled
    -0.13
    лÑĸ
    -0.13
    \Contracts
    -0.13
     Sach
    -0.13
    POSITIVE LOGITS
    renom
    0.18
     Partisi
    0.14
    holm
    0.14
    Æł
    0.14
    üc
    0.14
    elize
    0.13
     Brut
    0.13
    /Foundation
    0.13
    ucha
    0.13
     Nottingham
    0.13
    Act Density 0.028%

    No Known Activations