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

    Neuronpedia

    INDEX
    Explanations

    instances of proposals and engagements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oven
    -0.20
    Ľå»º
    -0.17
    onas
    -0.16
    ubb
    -0.15
    rist
    -0.15
    íĨłíĨł
    -0.15
    adelphia
    -0.14
    à¸ļาย
    -0.14
     Anton
    -0.14
     mq
    -0.14
    POSITIVE LOGITS
     Roch
    0.16
    aurus
    0.15
     wore
    0.15
    itzer
    0.14
    zer
    0.14
    ìĭĿìĿĦ
    0.14
    uet
    0.14
    ottie
    0.14
    CCA
    0.13
    idend
    0.13
    Act Density 0.130%

    No Known Activations