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

    Neuronpedia

    INDEX
    Explanations

    information related to current events and technological advancements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Was
    -0.53
     I
    -0.53
     Man
    -0.53
     After
    -0.52
     Is
    -0.52
     As
    -0.52
     
    -0.51
     Did
    -0.50
     He
    -0.50
     U
    -0.49
    POSITIVE LOGITS
     thermomix
    1.17
     Luglio
    1.15
     cabrio
    1.12
     jetta
    1.11
     appunt
    1.07
     lamborghini
    1.07
     unlaw
    1.07
     stihl
    1.06
     chrysler
    1.05
     impractica
    1.03
    Act Density 0.328%

    No Known Activations