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

    Neuronpedia

    INDEX
    Explanations

    phrases describing comparisons and contrasts within contexts

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

    "in" followed by a pronoun or determiner

    np_acts-logits-general · gemini-2.0-flash

    in its / in that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تفصیلات
    -0.68
    PARATUS
    -0.64
    insics
    -0.64
    eseorang
    -0.61
    ьаж
    -0.61
    scriptcase
    -0.60
    ellón
    -0.60
     Roskov
    -0.60
     Савезне
    -0.59
     DBNull
    -0.58
    POSITIVE LOGITS
     regards
    1.30
     regard
    1.15
     terms
    1.07
    regards
    0.96
    regard
    0.94
     Hinsicht
    0.92
     respects
    0.88
     cuanto
    0.86
    terms
    0.80
     respect
    0.80
    Act Density 0.373%

    No Known Activations