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

    Neuronpedia

    INDEX
    Explanations

    quantitative data related to production and financial performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yscale
    -0.16
    çĪĨ
    -0.16
    ระà¹Ģà¸ļ
    -0.15
    rames
    -0.15
     explosion
    -0.14
    rega
    -0.14
     explode
    -0.14
     erupt
    -0.14
     schnell
    -0.14
     explosive
    -0.13
    POSITIVE LOGITS
     unchanged
    0.41
     flat
    0.35
     stable
    0.30
     slight
    0.30
     slightly
    0.29
    -flat
    0.28
     steady
    0.28
     little
    0.28
    unch
    0.27
     Flat
    0.27
    Act Density 0.082%

    No Known Activations