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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses and their contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -3.70
    ↵↵↵
    -3.70
    -3.70
    -3.70
    ↵
    -3.70
    ↵
    -3.70
    ↵
    -3.70
    ↵
    -3.70
    ↵  Âł
    -3.70
    <|outofrange|>
    -3.70
    POSITIVE LOGITS
    úblic
    1.44
    urban
    1.44
    aliana
    1.42
    reve
    1.42
    gmail
    1.41
    erald
    1.38
    oard
    1.36
    uten
    1.35
    acket
    1.34
    udes
    1.34
    Act Density 0.263%

    No Known Activations