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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UCC
    -0.83
     ➢
    -0.80
     McLaren
    -0.77
    Wand
    -0.76
    ing
    -0.74
     Kers
    -0.73
    FieldNumber
    -0.73
    cheibe
    -0.73
     Abbe
    -0.73
     ujednoznacz
    -0.72
    POSITIVE LOGITS
    }_{
    1.09
     underval
    0.74
     STEIN
    0.72
     Mey
    0.71
    ilstein
    0.69
    ribune
    0.69
     Bunny
    0.68
     cun
    0.68
     Trimble
    0.68
    \}_{
    0.67
    Act Density 0.308%

    No Known Activations