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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introduces explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.50
     Majefty
    -0.49
     pleaſure
    -0.47
     StatefulWidget
    -0.46
     purpoſe
    -0.45
    省市镇
    -0.44
    críbete
    -0.42
     abbin
    -0.42
     papild
    -0.41
     kirj
    -0.41
    POSITIVE LOGITS
    MemoryWarning
    0.46
    LabelTagHelper
    0.44
    AddTagHelper
    0.42
    IANGLES
    0.42
    keti
    0.42
    enumi
    0.41
    CUBE
    0.41
    ugc
    0.41
    uarts
    0.40
    ecko
    0.40
    Act Density 0.060%

    No Known Activations