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

    Neuronpedia

    INDEX
    Explanations

    prepositions and references to academic departments or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abar
    -0.16
     ffm
    -0.15
    963
    -0.15
    ople
    -0.15
    å¥Ĺ
    -0.14
    ngle
    -0.14
    bd
    -0.14
    mond
    -0.14
    abis
    -0.14
    niž
    -0.13
    POSITIVE LOGITS
     Lump
    0.14
    ango
    0.14
    stadt
    0.13
     cán
    0.13
    sted
    0.13
    ixa
    0.13
    vard
    0.13
    ãĤ¥
    0.13
    verse
    0.12
     rele
    0.12
    Act Density 0.054%

    No Known Activations