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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "watch" in various contexts

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

    watch, watchlist, monitoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.59
    \{\\
    -0.39
     defaultstate
    -0.35
    <_>
    -0.35
    TokenNameDOT
    -0.34
     <<<<<<<<<<<<<<
    -0.34
     conse
    -0.34
    ปร
    -0.33
    可
    -0.33
     Aurora
    -0.32
    POSITIVE LOGITS
    watch
    2.78
     watch
    2.34
    Watch
    2.22
     Watch
    2.19
    WATCH
    2.06
     WATCH
    2.02
     watches
    1.76
    watches
    1.73
     Watches
    1.52
     watched
    1.52
    Act Density 0.003%

    No Known Activations