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

    Neuronpedia

    INDEX
    Explanations

    concessive clauses or transitions in text

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

    although, while, though

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?
    -0.64
     Administrativna
    -0.62
    SourceChecksum
    -0.59
    queryInterface
    -0.56
    ագրություններ
    -0.52
     rhestr
    -0.49
    ⓧ
    -0.48
     propOrder
    -0.45
    Ӕ
    -0.43
    حياتها
    -0.42
    POSITIVE LOGITS
     Tweede
    0.43
    Despite
    0.41
     Innen
    0.39
     &___
    0.39
     ancianos
    0.38
     CreateTagHelper
    0.38
     contrast
    0.37
    slidesToShow
    0.36
    inken
    0.36
     emploi
    0.36
    Act Density 0.091%

    No Known Activations