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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "watch" and its variations in context

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

    "watch" (or "Watch") in various contexts

    np_acts-logits-general · gemini-2.0-flash

    watching words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    teries
    -0.68
    AddTagHelper
    -0.66
     Abp
    -0.65
    ◆◆
    -0.65
    ArgsConstructor
    -0.61
    cline
    -0.55
    ."],
    -0.53
    />";
    -0.53
     оригіналу
    -0.52
     EClass
    -0.52
    POSITIVE LOGITS
    tower
    0.90
     atenta
    0.79
    towers
    0.78
    dogs
    0.76
     helplessly
    0.67
    dog
    0.66
    DOG
    0.61
    👀
    0.60
    Dog
    0.59
     closely
    0.59
    Act Density 0.148%

    No Known Activations