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

    Neuronpedia

    INDEX
    Explanations

    variables and their mathematical relationships in equations or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.89
     Monfieur
    -0.81
     pleaſure
    -0.78
     ſeveral
    -0.73
     myſelf
    -0.72
     faſt
    -0.68
     themſelves
    -0.66
     ſever
    -0.65
    wiſe
    -0.65
     Beſ
    -0.64
    POSITIVE LOGITS
     Z
    1.96
     z
    1.75
    Z
    1.68
    getZ
    1.19
    z
    1.19
    
    1.05
    Zx
    1.01
    TypedDataSet
    0.94
     ز
    0.91
     з
    0.91
    Act Density 0.136%

    No Known Activations