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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izio
    -0.15
     Slater
    -0.15
    kaar
    -0.15
    agers
    -0.15
    ÂŃtion
    -0.14
    æk
    -0.14
    .none
    -0.14
    aub
    -0.14
    agra
    -0.14
    ầy
    -0.14
    POSITIVE LOGITS
    anchors
    0.15
     Brig
    0.15
    stants
    0.14
    linger
    0.14
    ego
    0.14
    Plate
    0.14
     Butterfly
    0.13
    æĺĩ
    0.13
    lain
    0.13
    aren
    0.13
    Act Density 0.010%

    No Known Activations