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

    Neuronpedia

    INDEX
    Explanations

    references to user paths or directory structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.96
     חיצוניים
    -0.95
    DataAnnotations
    -0.80
    -0.74
     Pary
    -0.71
    :✨
    -0.70
    Tembelea
    -0.70
    haustible
    -0.69
    MockMvc
    -0.68
     Braw
    -0.68
    POSITIVE LOGITS
    Users
    0.59
    OPTS
    0.50
     studier
    0.49
    邃
    0.46
     Fitz
    0.45
     AssemblyCompany
    0.45
     Rowe
    0.45
     users
    0.44
    users
    0.43
     ميل
    0.43
    Act Density 0.001%

    No Known Activations