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

    Neuronpedia

    INDEX
    Explanations

    headings or sections labeled "About" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     final
    -0.15
     (
    -0.15
    precated
    -0.15
    -0.14
     all
    -0.13
     [
    -0.13
    atti
    -0.13
     wand
    -0.13
     untranslated
    -0.13
    utter
    -0.13
    POSITIVE LOGITS
     Us
    0.43
    Us
    0.35
    -us
    0.27
     Yourself
    0.22
     us
    0.21
    _us
    0.20
    us
    0.19
     Me
    0.17
    WebHost
    0.17
    	us
    0.16
    Act Density 0.034%

    No Known Activations