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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific physical objects or locations within a narrative

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     impra
    -0.81
     accla
    -0.80
     strick
    -0.70
     myn
    -0.70
     unspeak
    -0.66
     gild
    -0.66
     ugg
    -0.65
     encomp
    -0.63
     vagu
    -0.62
     affor
    -0.62
    POSITIVE LOGITS
     window
    1.54
    window
    1.49
     Window
    1.43
     windows
    1.41
    Window
    1.33
    windows
    1.29
     WINDOW
    1.20
    WINDOW
    1.20
    Windows
    1.15
     Windows
    1.10
    Act Density 0.060%

    No Known Activations