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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unda
    -0.16
    rons
    -0.15
    arpa
    -0.15
    à¹ĩà¸Ķ
    -0.15
    aat
    -0.15
    PostBack
    -0.14
    izza
    -0.14
    oya
    -0.14
     Joan
    -0.14
    REPORT
    -0.14
    POSITIVE LOGITS
     Bomb
    0.19
     sieve
    0.18
     Erd
    0.17
    isel
    0.17
     Klo
    0.16
    lis
    0.16
    erd
    0.16
    Bomb
    0.16
     Ramsey
    0.16
     estimation
    0.15
    Act Density 0.277%

    No Known Activations