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

    Neuronpedia

    INDEX
    Explanations

    references to cultural or religious identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     penghar
    -0.36
     suficientemente
    -0.36
    ´
    -0.35
     ―
    -0.34
    เค้า
    -0.34
    “
    -0.32
     CERTAIN
    -0.31
     “
    -0.31
     "#{
    -0.31
     चीज़
    -0.30
    POSITIVE LOGITS
     Савезне
    0.71
    
    0.64
     ujednoznacz
    0.64
    PerformLayout
    0.63
    Tembelea
    0.63
    EndProject
    0.60
    ValueStyle
    0.60
    󠁴
    0.60
    usermodel
    0.59
     Huh
    0.57
    Act Density 0.041%

    No Known Activations