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

    Neuronpedia

    INDEX
    Explanations

    references to conditional and comparative statements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jsonwebtoken
    -0.35
    ，
    -0.33
     L
    -0.30
     h
    -0.30
     Hein
    -0.28
    AnchorTagHelper
    -0.28
     ,
    -0.28
     Le
    -0.28
     Jr
    -0.27
     McL
    -0.27
    POSITIVE LOGITS
     للمعارف
    0.90
    fromnode
    0.78
     autorytatywna
    0.77
    hyrchwyd
    0.75
    Geplaatst
    0.70
     otomatig
    0.70
     beſch
    0.70
     deſſen
    0.69
    <unused23>
    0.69
    <unused80>
    0.69
    Act Density 0.817%

    No Known Activations