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

    Neuronpedia

    INDEX
    Explanations

    repetitive or recurring patterns in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    litos
    -0.51
    Nuorodos
    -0.49
    <bos>
    -0.49
    Šaltiniai
    -0.48
    Sklici
    -0.48
     vairāk
    -0.46
    rasco
    -0.46
    Produzione
    -0.46
    Caratteristiche
    -0.46
    culadora
    -0.46
    POSITIVE LOGITS
     repeat
    1.17
     repeats
    1.11
     Repetition
    1.11
     Repe
    1.08
     repeater
    1.07
     Repeat
    1.07
     repetition
    1.07
     repeating
    1.05
     repeated
    1.04
     Repeated
    1.02
    Act Density 0.141%

    No Known Activations