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

    Neuronpedia

    INDEX
    Explanations

    expressions that emphasize the word "just" and its variations, indicating a focus on simplistic or minimalistic attitudes toward experiences

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

    "just" followed by a negative verb or emotion

    np_acts-logits-general · gemini-2.0-flash

    just doing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.77
    findpost
    -0.73
    OGND
    -0.71
    存于互联网档案馆
    -0.66
     zwar
    -0.66
    GraphicsUnit
    -0.65
     linkovi
    -0.65
     sogar
    -0.65
    contentLoaded
    -0.64
    NOK
    -0.62
    POSITIVE LOGITS
    simply
    0.89
     simply
    0.85
     simplesmente
    0.82
    Simply
    0.78
     prostu
    0.74
     Simply
    0.71
     zwy
    0.71
     einfach
    0.70
     Simplemente
    0.70
     simplemente
    0.69
    Act Density 0.101%

    No Known Activations