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

    Neuronpedia

    INDEX
    Explanations

    commands and code snippets within text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     COP
    -0.51
     cop
    -0.47
    —
    -0.47
    شن
    -0.44
     Sk
    -0.43
    COP
    -0.43
     Sik
    -0.42
     DataLoader
    -0.42
     COPD
    -0.42
    voiture
    -0.42
    POSITIVE LOGITS
     ļ
    0.83
     paff
    0.78
     dispen
    0.78
     alkoh
    0.77
     hek
    0.75
     kram
    0.75
     mī
    0.74
     ftu
    0.74
     tille
    0.73
     mef
    0.73
    Act Density 0.294%

    No Known Activations