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

    Neuronpedia

    INDEX
    Explanations

    specific physical objects and their arrangements within a space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itemprop
    -0.15
    äs
    -0.14
    flater
    -0.14
    анÑģ
    -0.14
     EXEMPLARY
    -0.14
    iddet
    -0.13
    thora
    -0.13
    paired
    -0.13
     ÑģоÑģ
    -0.13
    à¸Ķำà¹Ģà¸Ļ
    -0.13
    POSITIVE LOGITS
     made
    0.24
    made
    0.21
     called
    0.21
     fast
    0.20
     that
    0.19
     cut
    0.19
     held
    0.19
     aff
    0.18
     sim
    0.18
     which
    0.18
    Act Density 0.574%

    No Known Activations