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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ongoing or continuous action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rumania
    -0.74
    ndham
    -0.74
     XCTest
    -0.73
     Cavendish
    -0.69
     HSC
    -0.69
     SSI
    -0.68
     DbSet
    -0.68
    UTERS
    -0.66
     Pepsi
    -0.65
     Witnesses
    -0.65
    POSITIVE LOGITS
     Along
    1.74
     ALONG
    1.69
    Along
    1.67
     along
    1.61
    along
    1.52
     langs
    1.10
     entlang
    1.08
     lungo
    1.03
    沿
    0.96
     вдоль
    0.89
    Act Density 0.048%

    No Known Activations