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

    Neuronpedia

    INDEX
    Explanations

    phrases that express public opinion or sentiment towards various topics

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

    Comes after "some people" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    people express opinions or understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setupUi
    -0.42
     intStringLen
    -0.40
     surla
    -0.36
    σθαι
    -0.36
     propOrder
    -0.35
    Попис
    -0.35
    CardModule
    -0.34
    sizeCache
    -0.31
    BuildContext
    -0.30
     salvo
    -0.30
    POSITIVE LOGITS
    很多人
    0.53
    cloudflare
    0.52
    pecies
    0.48
    ſt
    0.48
     préfère
    0.47
    有些人
    0.47
    parseFrom
    0.46
    RTLE
    0.46
     préf
    0.46
     prefer
    0.45
    Act Density 0.595%

    No Known Activations