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

    Neuronpedia

    INDEX
    Explanations

    formal expressions and phrases relating to legal and compliance terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     more
    -0.60
     algunos
    -0.56
     algunas
    -0.55
     two
    -0.54
     alguns
    -0.53
     certains
    -0.52
     ciertas
    -0.51
     certain
    -0.51
     something
    -0.51
     algumas
    -0.50
    POSITIVE LOGITS
     kecuali
    0.91
     sauf
    0.89
     Tutte
    0.88
     conceivable
    0.86
     Majefty
    0.84
     وكل
    0.84
     except
    0.83
     excepto
    0.83
     imaginable
    0.83
     đều
    0.83
    Act Density 0.573%

    No Known Activations