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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "and" in various contexts

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

    exciting and positive descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.52
    Huile
    -0.48
    twimg
    -0.45
     AssemblyCulture
    -0.41
     AssemblyCompany
    -0.41
    Collar
    -0.40
    Roots
    -0.39
     lign
    -0.39
     FixedUpdate
    -0.39
    mappedBy
    -0.39
    POSITIVE LOGITS
     exciting
    0.59
     amusing
    0.54
     Exciting
    0.54
     enjoyable
    0.51
     thrilling
    0.50
     excitement
    0.50
     amazing
    0.49
    Exciting
    0.48
    bello
    0.47
     yummy
    0.47
    Act Density 0.037%

    No Known Activations