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

    Neuronpedia

    INDEX
    Explanations

    past and hypothetical verb constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     is
    -0.59
     wish
    -0.38
     would
    -0.33
     wished
    -0.32
     I
    -0.32
     was
    -0.31
     don
    -0.31
    者は
    -0.31
     had
    -0.31
    was
    -0.31
    POSITIVE LOGITS
     للاسماء
    0.78
     ब्रेकडाउन
    0.74
     <>",
    0.72
    LookAnd
    0.70
    yntaxException
    0.66
    StoryboardSegue
    0.63
    хьтан
    0.62
     AssemblyVersion
    0.61
    interopRequire
    0.60
     ModelExpression
    0.60
    Act Density 0.421%

    No Known Activations