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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming functions and methods

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    awed
    -0.74
     waning
    -0.74
     looming
    -0.71
     dwindling
    -0.70
    etheless
    -0.68
    living
    -0.68
     seriousness
    -0.65
    heard
    -0.65
    politics
    -0.65
    aukee
    -0.65
    POSITIVE LOGITS
     allows
    1.48
     enables
    1.40
     specifies
    1.36
     converts
    1.32
     ensures
    1.28
     calculates
    1.26
     lets
    1.26
     determines
    1.26
     assigns
    1.25
     retrie
    1.24
    Act Density 0.224%

    No Known Activations