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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "nice" in various forms and contexts

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

    positive adjective "nice"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nawr
    -0.41
    IContainer
    -0.30
     关于
    -0.29
    ForUser
    -0.28
    chapter
    -0.26
    Chapitre
    -0.25
     genommen
    -0.25
    stā
    -0.25
     chapter
    -0.25
    Proceedings
    -0.25
    POSITIVE LOGITS
    Nice
    1.51
     Nice
    1.50
    NICE
    1.17
     NICE
    1.10
    nice
    1.09
     nice
    0.89
    Noice
    0.83
    Nicely
    0.71
     Decent
    0.71
     Neat
    0.70
    Act Density 0.004%

    No Known Activations