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

    Neuronpedia

    INDEX
    Explanations

    references to ceiling and baseline measurements related to images or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    h
    -0.75
    li
    -0.75
    b
    -0.71
    man
    -0.66
     rosse
    -0.66
    G
    -0.65
    P
    -0.65
    B
    -0.65
     meninos
    -0.63
     usati
    -0.63
    POSITIVE LOGITS
     Bitmap
    1.36
    Bitmap
    1.24
     bitmap
    0.98
     snapshots
    0.98
    BeginInit
    0.96
     Ceiling
    0.95
    pshots
    0.93
     Fixture
    0.92
    BibitemShut
    0.91
    snapshots
    0.90
    Act Density 0.048%

    No Known Activations