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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to statistical modeling and inference in complex data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sianic
    -0.39
     final
    -0.38
     Repe
    -0.38
    repe
    -0.38
     bare
    -0.37
     repe
    -0.37
     desped
    -0.37
    spaghetti
    -0.36
     Bare
    -0.35
    AddHtmlAttribute
    -0.35
    POSITIVE LOGITS
    criminator
    0.58
     Autorisations
    0.57
    UpdateCommand
    0.52
    DeleteCommand
    0.50
    Personendaten
    0.49
    ReLU
    0.48
    IsContent
    0.47
    passphrase
    0.46
    RegressionTest
    0.46
     caufe
    0.45
    Act Density 0.679%

    No Known Activations