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

    Neuronpedia

    INDEX
    Explanations

    concepts and discussions related to statistics and metrics, particularly focusing on their misleading nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.17
    wart
    -0.16
    аниÑĨ
    -0.16
    ington
    -0.16
    anden
    -0.16
    à¤Ĥस
    -0.14
    >Hello
    -0.14
    à¹Ħว
    -0.14
    assa
    -0.14
    pector
    -0.14
    POSITIVE LOGITS
     measures
    0.19
     Measures
    0.18
     measure
    0.17
     proxy
    0.17
     proxies
    0.16
     Proxy
    0.16
    ulp
    0.15
     smooth
    0.15
     Measure
    0.14
    ads
    0.14
    Act Density 0.213%

    No Known Activations