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

    Neuronpedia

    INDEX
    Explanations

    phrases that express anticipation or expectation

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

    Follows conjunctions or sentence breaks

    np_acts-logits-general · gemini-2.0-flash

    getting to the point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.37
     fal
    -0.35
    proofing
    -0.34
     Bruch
    -0.34
     remembers
    -0.34
     Inns
    -0.32
    ViewFeatures
    -0.32
     Marta
    -0.32
    few
    -0.31
     cytochrome
    -0.31
    POSITIVE LOGITS
    setVerticalGroup
    0.64
     OMITBAD
    0.58
    parsedMessage
    0.55
    enterOuterAlt
    0.54
    astify
    0.54
     suspense
    0.51
    UserScript
    0.50
    WebVitals
    0.50
    PostInfinity
    0.48
     miniaturka
    0.47
    Act Density 0.375%

    No Known Activations