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

    Neuronpedia

    INDEX
    Explanations

    quantities related to energy and interactions between objects

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    enumi
    -0.91
    \{\\
    -0.83
     MainAxisSize
    -0.78
     ModelExpression
    -0.76
     NUKAT
    -0.75
    IBOutlet
    -0.73
     AssemblyCompany
    -0.73
     AttributeSet
    -0.71
     ་་
    -0.67
    TestingModule
    -0.67
    POSITIVE LOGITS
     a
    0.61
     to
    0.58
     an
    0.54
     pick
    0.52
     “
    0.50
     just
    0.49
     for
    0.49
     spesies
    0.47
     har
    0.46
    emlrt
    0.46
    Act Density 0.147%

    No Known Activations