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

    Neuronpedia

    INDEX
    Explanations

    key phrases associated with final conclusions or summarizations in discussions

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

    Comes before a comma or conjunction

    np_acts-logits-general · gemini-2.0-flash

    concluding or final point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    migo
    -0.61
     propOrder
    -0.59
    WebVitals
    -0.58
    parsedMessage
    -0.57
     Offisielt
    -0.55
    '>{
    -0.55
     priori
    -0.53
    SharedCtor
    -0.53
    めました
    -0.53
    ')}}">
    -0.52
    POSITIVE LOGITS
     another
    1.54
    another
    1.50
    Another
    1.48
     Another
    1.37
     also
    1.15
     ANOTHER
    1.13
    另一个
    1.06
    also
    1.06
    另一個
    1.05
    Otra
    1.02
    Act Density 0.443%

    No Known Activations