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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing feelings or emotions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    conservancy
    -0.79
    xual
    -0.75
    alsh
    -0.72
    uning
    -0.70
    inka
    -0.69
    edia
    -0.69
    ourning
    -0.68
    orem
    -0.68
    ondo
    -0.66
     Shutterstock
    -0.66
    POSITIVE LOGITS
     hollow
    0.92
     like
    0.88
     awkward
    0.87
     distinctly
    0.80
     oddly
    0.80
     unreal
    0.79
     authentic
    0.79
     snug
    0.79
     comfortable
    0.78
     inadequate
    0.78
    Act Density 0.058%

    No Known Activations