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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors related to products and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouf
    -0.80
     smelled
    -0.74
    ittee
    -0.73
    ĸļ
    -0.70
    undrum
    -0.69
    ften
    -0.69
     tremend
    -0.68
     misunder
    -0.68
     sailed
    -0.67
    achu
    -0.66
    POSITIVE LOGITS
     scenarios
    1.10
     situations
    1.03
     versions
    1.02
     applications
    1.01
     environments
    1.00
     backgrounds
    0.99
     structures
    0.96
     architectures
    0.96
     individuals
    0.95
     models
    0.94
    Act Density 0.481%

    No Known Activations