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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to legal frameworks and administrative procedures

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

    Before certain nouns

    np_acts-logits-general · gemini-2.0-flash

    grammatical structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.63
     a
    -0.60
     for
    -0.59
     set
    -0.57
     in
    -0.57
     to
    -0.56
     si
    -0.55
     por
    -0.54
     l
    -0.53
     on
    -0.52
    POSITIVE LOGITS
     Majefty
    1.13
     greateſt
    1.09
     ſeveral
    1.07
     ſtate
    1.07
     Houſe
    1.06
     myſelf
    1.05
     iſt
    1.05
     Theſe
    1.04
     ſche
    1.02
     purpoſe
    1.01
    Act Density 1.204%

    No Known Activations