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

    Neuronpedia

    INDEX
    Explanations

    adverbs that modify actions or states, particularly those indicating manner or degree

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

    ending in "-ly" (adverbs)

    np_acts-logits-general · gemini-2.0-flash

    adverbs ending in -ally/-ically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.71
    CompilerServices
    -0.69
    MigrationBuilder
    -0.68
    fillType
    -0.68
     Roskov
    -0.66
     spécialement
    -0.66
     oficialmente
    -0.66
     officiellement
    -0.65
     soigneusement
    -0.63
    finally
    -0.63
    POSITIVE LOGITS
     speaking
    1.17
     hablando
    0.97
     parlant
    0.96
    speaking
    0.87
     Speaking
    0.85
     Yours
    0.83
     falando
    0.81
     worded
    0.79
     priced
    0.77
     parlando
    0.77
    Act Density 0.507%

    No Known Activations