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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political conflict and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTS
    -0.44
     Streets
    -0.41
     learnings
    -0.40
     scenarios
    -0.39
     forums
    -0.38
     hallways
    -0.38
     Horizons
    -0.37
     horizons
    -0.36
    works
    -0.36
     voren
    -0.35
    POSITIVE LOGITS
    RegressionTest
    0.63
    :✨
    0.52
     CreateTagHelper
    0.51
     ModelExpression
    0.50
     most
    0.49
    SharedDtor
    0.47
    InjectAttribute
    0.46
     Савезне
    0.46
     douceur
    0.46
     trifle
    0.43
    Act Density 0.881%

    No Known Activations