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

    Neuronpedia

    INDEX
    Explanations

    references to watching content, particularly videos

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

    watch? or watch(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*++
    -0.45
     propOrder
    -0.43
    +:+
    -0.40
     Şi
    -0.37
    tagHelperRunner
    -0.36
     „
    -0.36
     }^{[
    -0.36
     Erkennt
    -0.35
     ‚
    -0.35
     ostavi
    -0.35
    POSITIVE LOGITS
    watch
    0.99
     watch
    0.77
    MLLoader
    0.69
    WATCH
    0.66
     WATCH
    0.61
    Watch
    0.60
     Watch
    0.60
     Watches
    0.59
    DockStyle
    0.59
    watches
    0.59
    Act Density 0.003%

    No Known Activations