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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to documentation and formal findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettle
    -0.17
    isp
    -0.16
    hurst
    -0.15
    MLE
    -0.14
    üf
    -0.14
    645
    -0.14
    awl
    -0.14
    oldown
    -0.13
    assium
    -0.13
    ãĥ³ãĥĢ
    -0.13
    POSITIVE LOGITS
     elsewhere
    0.27
     below
    0.17
    Else
    0.17
    else
    0.17
     Else
    0.16
     earlier
    0.16
     вÑĭÑĪе
    0.15
    /Framework
    0.15
    below
    0.15
     above
    0.15
    Act Density 0.147%

    No Known Activations