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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.83
    #+#
    -0.83
     Italijanski
    -0.82
     "..\..\
    -0.81
    Jeografia
    -0.79
     Biôgrafia
    -0.75
    EndGlobalSection
    -0.75
     "..\..\..\
    -0.74
    Diweddarwch
    -0.74
    QMetaType
    -0.74
    POSITIVE LOGITS
    arky
    0.42
     haw
    0.42
    ToolStripButton
    0.41
     reformers
    0.40
     añ
    0.39
     Ank
    0.39
    しく
    0.39
    んだり
    0.38
     understood
    0.38
     justifiable
    0.38
    Act Density 0.251%

    No Known Activations