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

    Neuronpedia

    INDEX
    Explanations

    recurrent phrases indicating upcoming events or segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.98
     itſelf
    -0.87
     raiſ
    -0.82
     Efq
    -0.79
    Autoritní
    -0.79
    はじめに
    -0.78
     للمعارف
    -0.76
    ſelf
    -0.75
     themſelves
    -0.75
     myſelf
    -0.74
    POSITIVE LOGITS
     Next
    1.04
     NEXT
    1.04
     next
    0.92
    NEXT
    0.90
    Next
    0.89
    door
    0.87
    next
    0.87
    setNext
    0.87
     generation
    0.86
     door
    0.83
    Act Density 0.122%

    No Known Activations