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

    Neuronpedia

    INDEX
    Explanations

    phrases questioning the definition of terms or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.78
    RegressionTest
    -0.76
     ExecuteAsync
    -0.71
     <<<<<<<<<<<<<<
    -0.70
     cherchés
    -0.70
     Tasse
    -0.69
     Chaco
    -0.69
    UnusedPrivate
    -0.69
    ThroughAttribute
    -0.67
    +#+#
    -0.66
    POSITIVE LOGITS
    Whats
    0.65
    whats
    0.60
     what
    0.60
     the
    0.57
     Whats
    0.57
    什么是
    0.55
     why
    0.54
    bukkit
    0.52
     vad
    0.51
    rieks
    0.51
    Act Density 0.116%

    No Known Activations