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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations involving adjustments and variables in a computational context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     infrastruktur
    -0.67
     bakteri
    -0.64
     alkoh
    -0.63
     Embaj
    -0.62
     kriminal
    -0.62
     kooper
    -0.60
     kompak
    -0.60
     panik
    -0.60
     Kalifor
    -0.60
     konserv
    -0.59
    POSITIVE LOGITS
     swarovski
    1.00
     tupperware
    0.94
     ecru
    0.91
     friable
    0.91
     oleo
    0.87
     oreo
    0.86
     arbitrar
    0.83
     pixar
    0.83
     lamborghini
    0.83
     eiffel
    0.82
    Act Density 0.375%

    No Known Activations