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

    Neuronpedia

    INDEX
    Explanations

    concepts related to governance and authority

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

    Prepositions followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    language context or archaic English

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     impactful
    -0.95
    Referencie
    -0.81
     Additionally
    -0.81
     incentiv
    -0.79
     alfo
    -0.78
     itſelf
    -0.78
     ucapnya
    -0.78
    Additionally
    -0.78
     Jefus
    -0.77
    ביוגרפיה
    -0.76
    POSITIVE LOGITS
     daß
    0.84
     muß
    0.75
     läßt
    0.71
     skall
    0.58
     such
    0.57
     commonest
    0.56
     thence
    0.55
    faßt
    0.54
     müßte
    0.54
     eût
    0.53
    Act Density 1.040%

    No Known Activations