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

    Neuronpedia

    INDEX
    Explanations

    instances of viewing or watching experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rodillas
    -0.51
     ilustracji
    -0.50
     avanzado
    -0.50
     Aussicht
    -0.45
     procedere
    -0.44
     didukung
    -0.44
     redonda
    -0.44
     ecológica
    -0.43
     ökolog
    -0.43
     inalámbrica
    -0.43
    POSITIVE LOGITS
     watching
    0.97
     Watching
    0.96
     viewer
    0.91
    Watching
    0.90
    watching
    0.88
    viewing
    0.88
     viewing
    0.84
     Viewing
    0.82
     Viewer
    0.81
    viewer
    0.79
    Act Density 0.334%

    No Known Activations