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

    Neuronpedia

    INDEX
    Explanations

    information about observations or sightings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     trouvait
    -0.49
     Agregar
    -0.48
    Referanser
    -0.48
     Eliminar
    -0.43
     nomme
    -0.43
    듦
    -0.43
    Iné
    -0.43
    Referencer
    -0.42
    Kole
    -0.42
    ochial
    -0.42
    POSITIVE LOGITS
    Saw
    1.06
    saw
    1.01
     saw
    0.99
     Saw
    0.97
     Sees
    0.92
     saws
    0.89
     SEEN
    0.88
     SAW
    0.87
     sawing
    0.85
     thut
    0.85
    Act Density 0.116%

    No Known Activations