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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases related to structured systems, treatments, or specific measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.77
     surla
    -0.75
    -0.74
    DeleteBehavior
    -0.71
     Numerade
    -0.71
     Normdatei
    -0.68
     pinulongan
    -0.66
     '\\;'
    -0.65
    OGND
    -0.65
    XmlAccessorType
    -0.61
    POSITIVE LOGITS
     gober
    0.35
     gobier
    0.35
     igualdad
    0.33
     confronti
    0.32
     مشين
    0.32
    .
    0.31
     Vernunft
    0.30
     fédé
    0.30
     dieux
    0.30
     aço
    0.29
    Act Density 1.746%

    No Known Activations