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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases and patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    over and over again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    новништво
    -0.59
     незавершена
    -0.58
     ligiloj
    -0.54
    Personendaten
    -0.52
    dataclass
    -0.52
    AddComponent
    -0.51
    MigrationBuilder
    -0.51
    msgTypes
    -0.50
    ioutil
    -0.50
     دیکھیے
    -0.49
    POSITIVE LOGITS
     repeatedly
    0.86
     recurring
    0.79
    repeated
    0.76
     repeated
    0.75
     Repeated
    0.73
     recurrent
    0.68
    反复
    0.67
    Repeated
    0.66
    Recurring
    0.64
    recurring
    0.64
    Act Density 0.076%

    No Known Activations