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

    Neuronpedia

    INDEX
    Explanations

    references to names or naming conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cuenca
    -0.66
    )");
    -0.63
    例句
    -0.62
    "]);
    -0.62
    {}/
    -0.59
    Corollary
    -0.58
     للغاية
    -0.57
    ientôt
    -0.57
     \%)
    -0.57
    Při
    -0.56
    POSITIVE LOGITS
     names
    1.86
     name
    1.75
     Names
    1.62
     NAME
    1.52
     Name
    1.47
    names
    1.43
     NAMES
    1.38
    name
    1.33
    Names
    1.32
    NAME
    1.31
    Act Density 0.115%

    No Known Activations