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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NUMX
    -0.58
    NewUrlParser
    -0.57
    Personensuche
    -0.54
    parsedMessage
    -0.54
    Билгалдахарш
    -0.53
     استنادى
    -0.52
     محفوظة
    -0.49
    LayoutStyle
    -0.49
    ofire
    -0.48
    ########.
    -0.47
    POSITIVE LOGITS
     DD
    0.53
     HH
    0.47
     EE
    0.45
     Hallen
    0.44
     TT
    0.44
     GG
    0.43
    MessageTagHelper
    0.43
     dd
    0.43
     FF
    0.42
     Dodd
    0.42
    Act Density 0.205%

    No Known Activations