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

    Neuronpedia

    INDEX
    Explanations

    specific years and terms often related to academic works

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    twitch
    -0.77
    Streamer
    -0.74
    ãĥİ
    -0.71
    Lt
    -0.70
    âķ
    -0.68
     showers
    -0.66
     waited
    -0.64
    Players
    -0.64
     idols
    -0.64
     flashed
    -0.64
    POSITIVE LOGITS
     book
    1.30
     article
    1.30
     paper
    1.22
     dissertation
    1.21
     essay
    1.20
     seminal
    1.20
     study
    1.18
     bestselling
    1.14
     thesis
    1.11
     forthcoming
    1.11
    Act Density 0.242%

    No Known Activations