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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical symbols and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marien
    -0.96
     étoit
    -0.80
     getItemCount
    -0.79
     joaat
    -0.77
     Stere
    -0.75
     hysteresis
    -0.75
     auroit
    -0.74
     Baile
    -0.73
     Theſe
    -0.72
    ={({
    -0.72
    POSITIVE LOGITS
    lambda
    2.13
     lambda
    1.92
     λ
    1.86
    λ
    1.63
     Lambda
    1.50
    Lambda
    1.22
    mbda
    1.12
     Lamb
    1.12
     lamb
    1.08
    Lamb
    1.07
    Act Density 0.141%

    No Known Activations