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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "too."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }")
    -0.88
     sement
    -0.85
     vaisselle
    -0.82
    roves
    -0.82
    )");
    -0.79
    Kennedy
    -0.79
     */;
    -0.78
    ViewSet
    -0.75
     Kirsch
    -0.75
    ViewFeatures
    -0.74
    POSITIVE LOGITS
     Too
    1.41
     too
    1.40
     TOO
    1.36
    TOO
    1.34
    too
    1.33
    Too
    1.29
     zbyt
    0.90
    toos
    0.87
    troppo
    0.85
     allzu
    0.83
    Act Density 0.047%

    No Known Activations