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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the presence of substantial updates or events

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

    the word "with"

    np_acts-logits-general · gemini-2.0-flash

    With

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CompleteListener
    -0.75
    MLLoader
    -0.75
    WriteTagHelper
    -0.67
    WebServlet
    -0.67
    IContainer
    -0.67
     FetchType
    -0.64
     onCancelled
    -0.63
    TemporalType
    -0.63
    DoubleQuotes
    -0.63
    Personensuche
    -0.62
    POSITIVE LOGITS
    With
    0.95
     With
    0.93
     WITH
    0.63
    with
    0.62
    WITH
    0.61
     Avec
    0.58
    Without
    0.55
     hindsight
    0.55
    stood
    0.55
     Without
    0.55
    Act Density 0.090%

    No Known Activations