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

    Neuronpedia

    INDEX
    Explanations

    discourse markers indicating suggestions or recommendations

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

    needs suggestions and improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.65
     faſt
    -0.62
     kasarigan
    -0.62
    WebVitals
    -0.62
     Meksiku
    -0.61
    ReusableCell
    -0.60
     Houſe
    -0.60
     ModelExpression
    -0.59
     deſt
    -0.59
    ruik
    -0.59
    POSITIVE LOGITS
    suggestions
    0.34
     urging
    0.34
     Needs
    0.33
     Suggestions
    0.32
     betterment
    0.32
     идеи
    0.31
     suggestions
    0.31
     Mon
    0.31
     діа
    0.30
     reivindic
    0.30
    Act Density 0.221%

    No Known Activations