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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to performances and entertainers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argar
    -0.17
    æįķ
    -0.15
    odom
    -0.15
     musel
    -0.15
    ientes
    -0.14
    pit
    -0.14
    ellt
    -0.14
    riage
    -0.14
    glob
    -0.14
     Kaynak
    -0.14
    POSITIVE LOGITS
    otal
    0.17
     card
    0.16
     magician
    0.16
     Card
    0.16
     cards
    0.15
     ç±
    0.15
    .jasper
    0.15
     Oaks
    0.14
     sé
    0.14
    uppy
    0.14
    Act Density 0.007%

    No Known Activations