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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "written" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -1.35
     Савезне
    -1.33
    expandindo
    -1.26
     AssemblyCompany
    -1.25
    GEBURTSDATUM
    -1.21
     الحره
    -1.20
     ModelExpression
    -1.16
    SourceChecksum
    -1.15
    انيف
    -1.10
     CreateTagHelper
    -1.10
    POSITIVE LOGITS
     written
    0.88
     an
    0.63
     
    0.60
     for
    0.58
    ​
    0.56
     with
    0.56
     followed
    0.55
     in
    0.54
     a
    0.54
     as
    0.51
    Act Density 0.128%

    No Known Activations