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

    Neuronpedia

    INDEX
    Explanations

    details related to experimental design and methodologies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    findpost
    -0.57
    LITERAL
    -0.54
    ddots
    -0.53
    viewDidLoad
    -0.52
    ViewImports
    -0.52
     LCCN
    -0.50
     Coll
    -0.50
    IBU
    -0.50
    endwhile
    -0.50
     arm
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    0.71
    PhysRevLett
    0.53
     mergeFrom
    0.53
    ずつ
    0.52
    PreferredItem
    0.52
    AsUp
    0.51
    الإنجليزية
    0.50
    inaison
    0.50
    บ้าง
    0.49
    씩
    0.48
    Act Density 0.082%

    No Known Activations