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

    Neuronpedia

    INDEX
    Explanations

    instances of XML or HTML document declarations along with preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dari
    -0.58
     getPath
    -0.55
    iler
    -0.53
    рк
    -0.53
     arth
    -0.50
     soap
    -0.50
    ActionResult
    -0.49
    ্য
    -0.48
    뀔
    -0.48
    Thriller
    -0.48
    POSITIVE LOGITS
    PerformLayout
    1.36
    Preferences
    1.24
    Preference
    1.18
    preference
    1.17
    preferences
    1.15
     FontWeight
    1.14
     Preference
    1.13
     Preferences
    1.12
    ruptedException
    1.10
     preferences
    1.08
    Act Density 0.042%

    No Known Activations