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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain Latin terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quette
    -0.17
    morgan
    -0.16
     Fine
    -0.14
    uez
    -0.14
    /weather
    -0.14
    stown
    -0.14
    deniz
    -0.14
    esser
    -0.14
    rimon
    -0.14
    amespace
    -0.13
    POSITIVE LOGITS
    ks
    0.15
    sky
    0.15
    olk
    0.15
     cater
    0.15
    zen
    0.15
    esco
    0.14
    à¹īà¸Ńà¸Ļ
    0.14
    ác
    0.13
    380
    0.13
    ges
    0.13
    Act Density 0.003%

    No Known Activations