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

    Neuronpedia

    INDEX
    Explanations

    terms related to processes that are done correctly or according to standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.80
    UpInside
    -0.79
    InjectMocks
    -0.72
     GenerationType
    -0.70
    ⋱
    -0.67
    sizeCache
    -0.66
     mẽ
    -0.62
    ęp
    -0.61
    editForm
    -0.60
    belec
    -0.60
    POSITIVE LOGITS
     properly
    2.50
     correctly
    2.37
    properly
    2.12
     Properly
    2.11
     adequately
    1.88
     appropriately
    1.87
    correctly
    1.84
     correctement
    1.65
     accurately
    1.61
     correctamente
    1.51
    Act Density 0.113%

    No Known Activations