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

    Neuronpedia

    INDEX
    Explanations

    references to length measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bernie
    -0.46
    msubsup
    -0.45
    UnsafeEnabled
    -0.44
    infer
    -0.43
     Infer
    -0.42
    }`).
    -0.42
     Bernie
    -0.42
     infer
    -0.42
     Casino
    -0.42
     Kuk
    -0.42
    POSITIVE LOGITS
     length
    2.81
    length
    2.78
     Length
    2.61
    Length
    2.55
    LENGTH
    2.33
     LENGTH
    2.28
     lengths
    2.03
     lenght
    2.00
    ength
    1.92
     Länge
    1.91
    Act Density 0.059%

    No Known Activations