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

    Neuronpedia

    INDEX
    Explanations

    instances of formal statements or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhn
    -0.15
    ohl
    -0.15
    ieder
    -0.14
    avis
    -0.14
    asser
    -0.14
    åºķ
    -0.14
    ัà¸Ĺ
    -0.14
    ush
    -0.13
    ür
    -0.13
    idal
    -0.13
    POSITIVE LOGITS
     Meanwhile
    0.16
    #ab
    0.16
    Meanwhile
    0.16
    úa
    0.15
     Glob
    0.15
    _locked
    0.14
    æĿ¥æºIJ
    0.14
     Likewise
    0.14
    Forms
    0.14
     inc
    0.14
    Act Density 0.073%

    No Known Activations