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

    Neuronpedia

    INDEX
    Explanations

    accents in text

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.87
    matic
    -0.82
    orial
    -0.73
    urated
    -0.69
     primates
    -0.68
    writers
    -0.68
    enegger
    -0.65
    ulative
    -0.65
     apes
    -0.62
    utra
    -0.60
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.16
    ï¸ı
    0.96
    ĺ
    0.91
    ľ
    0.90
    ¸
    0.89
    ª
    0.89
    Ĺ
    0.88
    ļ
    0.87
    fter
    0.86
    ¼
    0.86
    Act Density 0.233%

    No Known Activations