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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing subjective opinions and personal evaluations

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

    following "just" or "simply"

    np_acts-logits-general · gemini-2.0-flash

    just/simply followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    最快更新
    -0.57
    igens
    -0.53
     Tuo
    -0.53
    ContextHolder
    -0.52
    ⏪
    -0.49
     Tot
    -0.48
    craper
    -0.48
     nî
    -0.46
    ery
    -0.46
    balah
    -0.45
    POSITIVE LOGITS
     simply
    2.38
    simply
    2.26
    Simply
    2.05
     simplesmente
    2.03
     simplemente
    2.01
     Simply
    1.96
     semplicemente
    1.80
     Simplemente
    1.78
     einfach
    1.74
     просто
    1.65
    Act Density 0.297%

    No Known Activations