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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitations or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ')]
    -0.65
    endcsname
    -0.64
     Maynard
    -0.61
    PhysRev
    -0.61
    ''')
    -0.60
    HomeAsUp
    -0.60
     StatefulWidget
    -0.59
    ?")
    -0.59
     NIOS
    -0.58
    ]--;
    -0.58
    POSITIVE LOGITS
     merely
    0.72
     solely
    0.72
     лишь
    0.66
     yalnızca
    0.65
    onAttach
    0.64
    แค่
    0.63
     slechts
    0.61
     exclusivamente
    0.61
     wyłącznie
    0.58
     exclusiva
    0.56
    Act Density 0.217%

    No Known Activations