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

    Neuronpedia

    INDEX
    Explanations

    code references and method signatures in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    дам
    -0.15
    زÙĪ
    -0.14
    krv
    -0.14
    .Qual
    -0.14
    utto
    -0.14
    Ñĩим
    -0.14
    verture
    -0.14
     ...č↵
    -0.13
    aight
    -0.13
    ToBounds
    -0.13
    POSITIVE LOGITS
    aye
    0.16
    infeld
    0.16
    enthal
    0.15
    ules
    0.15
    unte
    0.14
     Expanded
    0.14
    alue
    0.14
    283
    0.14
    zeigen
    0.14
    uggy
    0.14
    Act Density 0.027%

    No Known Activations