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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or characters, often in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mv
    -0.18
    ley
    -0.17
     addCriterion
    -0.17
    studio
    -0.17
    na
    -0.17
    à¥Ģय
    -0.16
    st
    -0.16
    mr
    -0.16
    sters
    -0.16
    mis
    -0.16
    POSITIVE LOGITS
    kins
    0.30
    lic
    0.27
    -boy
    0.23
     Mae
    0.23
    boy
    0.22
    thon
    0.21
     boy
    0.21
    bear
    0.20
    grams
    0.20
    gram
    0.19
    Act Density 0.096%

    No Known Activations