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

    Neuronpedia

    INDEX
    Explanations

    references to bills or legislative acts

    oai_token-act-pair · gpt-3.5-turbo

    statements related to political actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.70
     semantics
    -0.63
     unchecked
    -0.60
     supers
    -0.60
     validation
    -0.59
    Äĩ
    -0.59
     liner
    -0.57
     consistency
    -0.56
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.55
    lihood
    -0.54
    POSITIVE LOGITS
    assetsadobe
    1.04
    264
    1.03
    265
    0.85
    263
    0.81
    323
    0.76
    Res
    0.74
    annis
    0.74
    Gray
    0.73
    W
    0.72
    G
    0.71
    Act Density 0.029%

    No Known Activations