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

    Neuronpedia

    INDEX
    Explanations

    references to live performance and comedy events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     {.
    -0.15
    swire
    -0.15
     gol
    -0.15
     Anc
    -0.14
    ahan
    -0.14
    illac
    -0.14
     půj
    -0.14
    vero
    -0.14
    chine
    -0.14
    iomanip
    -0.14
    POSITIVE LOGITS
     Impro
    0.33
     improv
    0.29
    Impro
    0.27
     sketch
    0.26
     impro
    0.25
     Harold
    0.24
     improve
    0.24
     jams
    0.24
     jam
    0.23
     trou
    0.21
    Act Density 0.013%

    No Known Activations