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

    Neuronpedia

    INDEX
    Explanations

    contexts related to independence and personal agency in historical and social settings

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

    Tokens preceding a preposition

    np_acts-logits-general · gemini-2.0-flash

    specialized nouns and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (!)
    -0.66
    <s>
    -0.62
    (!)
    -0.60
    !</
    -0.60
    !),
    -0.58
    </em>
    -0.57
    !—
    -0.57
     én
    -0.56
    ?!?
    -0.56
    ...</
    -0.55
    POSITIVE LOGITS
    antaranya
    1.05
     didalam
    0.85
     jepang
    0.81
     equipments
    0.77
     parís
    0.77
     daß
    0.75
     ainfi
    0.74
     diantaranya
    0.73
     diatas
    0.73
     purpoſe
    0.73
    Act Density 0.855%

    No Known Activations