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

    Neuronpedia

    INDEX
    Explanations

    terminology related to interfaces and boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.56
     inflater
    -0.56
    ंदीखरीदारी
    -0.51
     schia
    -0.49
    Aiheesta
    -0.49
    swal
    -0.47
     блу
    -0.46
     ModelAndView
    -0.46
    iformes
    -0.45
    emplare
    -0.45
    POSITIVE LOGITS
     boundary
    1.15
     Boundary
    1.03
     border
    1.03
     Boundaries
    1.02
     boundaries
    1.00
    boundary
    1.00
    InputBorder
    0.97
    Boundary
    0.95
     borders
    0.94
     demarcation
    0.94
    Act Density 0.534%

    No Known Activations