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

    Neuronpedia

    INDEX
    Explanations

    instances of decision-making or choices described in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.53
     وتسجيلات
    -0.47
     expectation
    -0.47
     assuring
    -0.43
     expect
    -0.42
    RenderAtEndOf
    -0.42
     понимаю
    -0.42
     expectancy
    -0.42
     noqa
    -0.42
    AppMethodBeat
    -0.41
    POSITIVE LOGITS
     unilaterally
    0.54
     venganza
    0.51
     upon
    0.49
    upon
    0.49
    要不要
    0.48
    LabelTagHelper
    0.47
     unanimously
    0.47
     instead
    0.47
     fate
    0.46
     asupra
    0.45
    Act Density 0.211%

    No Known Activations