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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or emphasize the basis or rationale behind a statement or argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     setAddress
    -0.59
     matelas
    -0.59
    manni
    -0.57
    چرا
    -0.56
     attiva
    -0.56
     MotionEvent
    -0.56
    šlo
    -0.55
    illan
    -0.55
    WART
    -0.54
     quadros
    -0.54
    POSITIVE LOGITS
     Based
    1.06
    Based
    1.06
     based
    1.01
     BASED
    0.94
    BASED
    0.91
    based
    0.89
     berdasarkan
    0.88
    dasarkan
    0.86
     anhand
    0.83
    基于
    0.82
    Act Density 0.285%

    No Known Activations