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

    Neuronpedia

    INDEX
    Explanations

    celestial objects and related astronomical terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.58
     wako
    -0.55
     baga
    -0.55
     kuan
    -0.54
     huwa
    -0.53
     subsidi
    -0.52
     CWE
    -0.52
     nzuri
    -0.51
    mogat
    -0.51
     bera
    -0.50
    POSITIVE LOGITS
     camry
    0.62
     jetta
    0.59
     mondeo
    0.56
     visually
    0.54
     binoculars
    0.54
     viewing
    0.53
    seeable
    0.53
     mitsubishi
    0.52
     observers
    0.52
    viewing
    0.52
    Act Density 0.524%

    No Known Activations