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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tatsache
    -0.61
     fact
    -0.49
    fact
    -0.48
     façon
    -0.48
     manière
    -0.48
     feit
    -0.47
     manera
    -0.47
     maneira
    -0.46
     meest
    -0.44
     sätt
    -0.42
    POSITIVE LOGITS
     doors
    1.06
     curtain
    0.92
    IntoConstraints
    0.91
     wheels
    0.90
     tide
    0.89
     clocks
    0.89
     lights
    0.88
     curtains
    0.88
     unthinkable
    0.88
     pendulum
    0.86
    Act Density 0.450%

    No Known Activations