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

    Neuronpedia

    INDEX
    Explanations

    phrases and titles that denote authority or suggest professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mnop
    -0.15
    ebek
    -0.14
    ãĥģãĥ¥
    -0.14
    .Companion
    -0.14
    .trace
    -0.14
    à¹Īà¸Ńà¸Ļ
    -0.13
    edn
    -0.13
     Malk
    -0.13
    xec
    -0.13
     fkk
    -0.13
    POSITIVE LOGITS
     =
    0.14
    ’s
    0.14
    adil
    0.14
     Patron
    0.14
     last
    0.13
    èħ¹
    0.13
     san
    0.13
     him
    0.13
     Obama
    0.13
    fieldset
    0.13
    Act Density 0.052%

    No Known Activations