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

    Neuronpedia

    INDEX
    Explanations

    questions and requests for clarification or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vig
    -0.17
    omor
    -0.17
    venta
    -0.16
    erras
    -0.15
    enery
    -0.15
     Citizenship
    -0.14
    Äĩe
    -0.14
     Mor
    -0.14
    uhl
    -0.14
     Sok
    -0.14
    POSITIVE LOGITS
     mal
    0.15
    ellan
    0.15
     carn
    0.14
     gre
    0.14
    »
    0.13
    ãĥ«ãĥĪ
    0.13
     keyof
    0.13
    èIJ¥
    0.13
     Ao
    0.13
    ãĥ«ãĤ¯
    0.13
    Act Density 5.090%

    No Known Activations