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

    Neuronpedia

    INDEX
    Explanations

    references to filenames in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    a
    -0.98
    o
    -0.93
    e
    -0.87
    es
    -0.80
    i
    -0.74
    k
    -0.73
     st
    -0.70
    st
    -0.69
    post
    -0.67
    Post
    -0.66
    POSITIVE LOGITS
     filename
    1.36
    filename
    1.28
    FILENAME
    1.07
    Filename
    1.06
     Filename
    1.05
     للاسماء
    0.97
    titleMargin
    0.96
     GenerationType
    0.94
     filenames
    0.93
    ConstraintMaker
    0.92
    Act Density 0.060%

    No Known Activations