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

    Neuronpedia

    INDEX
    Explanations

    references to windows and their characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "window" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avez
    -0.93
    currency
    -0.77
     Haram
    -0.72
    doms
    -0.68
    arus
    -0.68
     Uz
    -0.65
    ername
    -0.64
    rencies
    -0.64
     recomm
    -0.64
    phia
    -0.63
    POSITIVE LOGITS
     pane
    1.26
     sill
    1.19
    pan
    1.02
    ill
    1.02
     tint
    0.97
    glass
    0.95
     wip
    0.95
     ledge
    0.90
    lit
    0.87
    reens
    0.85
    Act Density 0.035%

    No Known Activations