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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     print
    -0.17
     Slater
    -0.16
     '\"
    -0.16
    antz
    -0.16
    ognito
    -0.16
    .await
    -0.15
    uble
    -0.15
    aniel
    -0.15
    ->{'
    -0.15
    _regularizer
    -0.14
    POSITIVE LOGITS
    _exc
    0.18
    cls
    0.16
     exc
    0.16
    _cls
    0.16
    (exc
    0.16
    _compat
    0.16
    (compact
    0.15
    aler
    0.15
    exc
    0.15
     Wich
    0.15
    Act Density 0.067%

    No Known Activations