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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or lack of guarantees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    guarantee or lack thereof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    berday
    -0.62
    DockStyle
    -0.59
     InputDecoration
    -0.58
     ligiloj
    -0.56
    SharedCtor
    -0.56
     initComponents
    -0.54
    ArrowToggle
    -0.53
    WithMany
    -0.52
     Wikimedijinoj
    -0.50
     informée
    -0.50
    POSITIVE LOGITS
     guarantee
    0.52
     promise
    0.40
    guarantee
    0.38
     outcome
    0.35
     success
    0.35
    gefahr
    0.34
    Outcome
    0.34
     Guarantee
    0.33
     retention
    0.33
     guaranty
    0.32
    Act Density 0.037%

    No Known Activations