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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numeric values and their attributes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.65
     Савезне
    -0.64
    enumii
    -0.60
    onucle
    -0.60
    invokeLater
    -0.60
    PreferredItem
    -0.59
    ☚
    -0.59
    Spoiler
    -0.58
    criminator
    -0.57
    🔥🔥🔥
    -0.57
    POSITIVE LOGITS
    minecraftforge
    0.63
    Cap
    0.59
    ReadInt
    0.56
    kuuta
    0.55
    PhysRevD
    0.54
     unintended
    0.54
    PhysRevLett
    0.54
    esgue
    0.52
     Cap
    0.52
    ########.
    0.52
    Act Density 0.047%

    No Known Activations