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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal interpretations and political tensions involving nationality and citizenship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences starting with conjunctions

    np_acts-logits-general · gemini-2.0-flash

    but yet or since

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     showcasing
    -0.92
     showcased
    -0.84
     incentiv
    -0.84
    Mhm
    -0.80
     transitioning
    -0.79
     impactful
    -0.79
     aka
    -0.78
     Additionally
    -0.78
     leveraging
    -0.77
    abestanden
    -0.76
    POSITIVE LOGITS
     doubtless
    0.76
     muß
    0.60
     thereupon
    0.59
     such
    0.58
     forthwith
    0.58
     skall
    0.56
     freilich
    0.55
     Daß
    0.54
     ordinarily
    0.53
     daß
    0.51
    Act Density 0.682%

    No Known Activations