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

    Neuronpedia

    INDEX
    Explanations

    references to place names and cultural terms in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rut
    -0.16
     covered
    -0.15
    ,
    -0.15
    i
    -0.15
     sub
    -0.14
    alous
    -0.14
    otal
    -0.14
    udget
    -0.14
     year
    -0.14
     Boyle
    -0.14
    POSITIVE LOGITS
     Paladin
    0.15
    ëĶ
    0.15
     oficial
    0.15
    verted
    0.15
    .hl
    0.14
    ollo
    0.14
    ToFit
    0.14
    -Un
    0.14
    δÏİ
    0.14
    å®ĺæĸ¹
    0.13
    Act Density 0.158%

    No Known Activations