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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -1.08
    OGND
    -0.90
    uxxxx
    -0.82
    MessageTagHelper
    -0.82
    Ꞓ
    -0.79
    WebElementEntity
    -0.79
    Autoritní
    -0.79
     estekak
    -0.78
    CloseOperation
    -0.77
    ⒝
    -0.77
    POSITIVE LOGITS
     Bewußt
    0.45
    ⅗
    0.42
     Wikiseite
    0.40
     beliau
    0.31
     Einfluß
    0.30
     Gnade
    0.30
     siebie
    0.29
    berdayakan
    0.28
     solches
    0.28
     boneka
    0.28
    Act Density 0.993%

    No Known Activations