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

    Neuronpedia

    INDEX
    Explanations

    descriptions or discussions involving transformation or change

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    alty
    -0.58
    alian
    -0.58
    uku
    -0.56
    anamo
    -0.55
    times
    -0.54
    acid
    -0.54
    xus
    -0.53
    sun
    -0.51
    atus
    -0.51
    cest
    -0.51
    POSITIVE LOGITS
     manageable
    0.79
     usable
    0.70
     profitable
    0.69
     cohesive
    0.69
     viable
    0.68
     nightmare
    0.68
     coherent
    0.67
     mere
    0.66
     respectable
    0.65
     caricature
    0.64
    Act Density 10.907%

    No Known Activations