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

    Neuronpedia

    INDEX
    Explanations

    references to the "latest" developments or updates across various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lately
    -0.19
    sole
    -0.14
     ìµľê·¼
    -0.14
    -Identifier
    -0.13
    athon
    -0.13
    ëĭ¤ê°Ģ
    -0.13
     подалÑĮ
    -0.13
     recently
    -0.13
    第ä¸Ģ次
    -0.13
     côt
    -0.13
    POSITIVE LOGITS
    -generation
    0.36
     iteration
    0.36
    s
    0.35
     incarnation
    0.35
     edition
    0.34
     addition
    0.33
     installment
    0.33
     generation
    0.32
     additions
    0.30
     batch
    0.30
    Act Density 0.036%

    No Known Activations