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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions indicating relationships or connections

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

    Prepositions followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    for\/of followed by the/this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.44
    !*\
    -0.42
    SuspendLayout
    -0.41
     rather
    -0.41
     protoimpl
    -0.40
    +#+
    -0.38
    BeNil
    -0.38
    pgterms
    -0.38
     Dietz
    -0.38
     happy
    -0.38
    POSITIVE LOGITS
     Chwiliwch
    0.47
    جوايز
    0.44
    ſelf
    0.43
    stateProvider
    0.43
     kağıdı
    0.43
    </thead>
    0.40
     Kini
    0.40
    новништво
    0.40
     szóci
    0.40
     theſe
    0.39
    Act Density 0.842%

    No Known Activations