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

    Neuronpedia

    INDEX
    Explanations

    occurrences of ellipses or pauses in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.16
    unity
    -0.14
    iscard
    -0.14
    ugg
    -0.14
     **)&
    -0.14
    ılıç
    -0.14
    (es
    -0.14
    ิà¸Ķ
    -0.14
    arr
    -0.14
    ollo
    -0.13
    POSITIVE LOGITS
     .
    0.24
     .$
    0.17
    __.
    0.16
     .č↵
    0.15
    vs
    0.15
    Ù«
    0.14
    kv
    0.14
     ."
    0.14
    .Ui
    0.14
     .↵↵
    0.14
    Act Density 0.049%

    No Known Activations