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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to mathematical processes and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inden
    -0.15
    wik
    -0.15
     EXPECT
    -0.15
    //--
    -0.14
    vie
    -0.14
    iska
    -0.14
     Associates
    -0.13
     Waterloo
    -0.13
     buddy
    -0.13
    گاب
    -0.13
    POSITIVE LOGITS
     parameters
    0.24
     assumptions
    0.24
     constants
    0.23
     unspecified
    0.22
     chosen
    0.21
     assumption
    0.21
     assumed
    0.21
     parameter
    0.19
     knobs
    0.19
     terms
    0.19
    Act Density 0.455%

    No Known Activations