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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the utility or helpfulness of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.88
    dymyr
    -0.81
    OGND
    -0.79
     AspNetCore
    -0.72
    nestjs
    -0.69
    JspWriter
    -0.66
    RunWith
    -0.65
    UpInside
    -0.64
     HasFactory
    -0.63
    queryInterface
    -0.62
    POSITIVE LOGITS
     useful
    1.78
    useful
    1.63
     Useful
    1.58
    Useful
    1.50
     helpful
    1.36
     utile
    1.34
     útil
    1.31
     usefulness
    1.29
     berguna
    1.27
     utiles
    1.26
    Act Density 0.129%

    No Known Activations