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

    Neuronpedia

    INDEX
    Explanations

    references to singular and plural nouns related to unity or collective concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onor
    -0.61
    AddTagHelper
    -0.56
    (['/
    -0.53
    Boas
    -0.52
     كومونز
    -0.51
     barrier
    -0.51
    olusi
    -0.51
    ficulty
    -0.51
    regi
    -0.51
    dziel
    -0.50
    POSITIVE LOGITS
     виправивши
    0.82
    aarrggbb
    0.70
    峙
    0.68
     ours
    0.68
    Ours
    0.67
     ones
    0.66
    OwnProperty
    0.66
     منها
    0.65
     légale
    0.64
     فريبيس
    0.63
    Act Density 0.243%

    No Known Activations