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

    Neuronpedia

    INDEX
    Explanations

    references to Russian or Slavic geographic regions and related terms

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    enumii
    -0.87
    findpost
    -0.85
    TagMode
    -0.77
    AnchorStyles
    -0.69
     Seeder
    -0.66
    enumi
    -0.64
    TestingModule
    -0.63
    </tbody>
    -0.60
     nakalista
    -0.60
    DebuggerNonUser
    -0.59
    POSITIVE LOGITS
     themſelves
    0.87
     ſeveral
    0.75
    حياتها
    0.69
     ส์
    0.69
     تانيه
    0.68
     whoſe
    0.67
     Chriftian
    0.67
     becauſe
    0.67
     neceſſ
    0.67
     Efq
    0.65
    Act Density 0.544%

    No Known Activations