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

    Neuronpedia

    INDEX
    Explanations

    variations of verb endings, specifically focusing on participles and related morphological forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -1.38
     ſche
    -1.33
     raiſ
    -1.26
     anſ
    -1.22
     Eſ
    -1.21
     pleaſure
    -1.19
     Reſ
    -1.18
     iſt
    -1.16
     deſt
    -1.16
     ſhould
    -1.16
    POSITIVE LOGITS
    OGND
    0.65
    󠁿
    0.65
    ец
    0.63
     genomen
    0.62
    ¿½
    0.62
    ampingi
    0.61
    MLLoader
    0.61
     a
    0.61
    剂
    0.59
    帖最后由
    0.58
    Act Density 0.213%

    No Known Activations