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

    Neuronpedia

    INDEX
    Explanations

    syntactic patterns ending in a semicolon

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withd
    -0.71
    senal
    -0.71
     Moroc
    -0.70
    enegger
    -0.69
     encount
    -0.68
     Vaugh
    -0.68
     advoc
    -0.67
     Seym
    -0.64
     redes
    -0.62
     Azerb
    -0.61
    POSITIVE LOGITS
    inventoryQuantity
    0.68
    println
    0.68
    else
    0.64
    minecraft
    0.64
     noun
    0.64
    cloud
    0.64
    ËĪ
    0.63
    soType
    0.62
     wanna
    0.61
     ye
    0.61
    Act Density 0.332%

    No Known Activations