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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.69
     &___
    -0.61
    Cyfeiriadau
    -0.60
    >>()
    -0.59
    openzeppelin
    -0.58
    Longrightarrow
    -0.56
    oredCriteria
    -0.55
     $("#
    -0.54
    reactivex
    -0.54
    {}{}
    -0.52
    POSITIVE LOGITS
     Majefty
    0.94
     Efq
    0.85
     whoſe
    0.79
     himſelf
    0.79
     itſelf
    0.74
     متعلقه
    0.74
     reaſon
    0.70
     Phry
    0.67
     purpoſe
    0.67
     pleaſure
    0.65
    Act Density 0.017%

    No Known Activations