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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by verbs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    istant
    -0.80
    igi
    -0.79
    Reilly
    -0.74
    kson
    -0.71
    pect
    -0.71
    era
    -0.69
     Scand
    -0.69
     largeDownload
    -0.68
    bard
    -0.67
    stadt
    -0.67
    POSITIVE LOGITS
     virtue
    1.44
     fiat
    1.07
    products
    1.05
     decree
    0.96
     default
    0.95
     sheer
    0.94
    catch
    0.94
     means
    0.94
    laws
    0.92
     leaps
    0.88
    Act Density 0.111%

    No Known Activations