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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مُعرِّف
    -0.75
     nahilalakip
    -0.72
     arşivlendi
    -0.63
    ScopeManager
    -0.58
    subsubsection
    -0.57
    velt
    -0.56
    izadores
    -0.55
     transfieras
    -0.54
    nicze
    -0.54
    ]]:
    -0.54
    POSITIVE LOGITS
    0
    1.10
     Commandments
    0.83
     Downing
    0.80
    AndEndTag
    0.78
    AddTagHelper
    0.75
     invokingState
    0.74
     Tors
    0.72
     commandments
    0.70
    8
    0.65
    يته
    0.63
    Act Density 0.308%

    No Known Activations