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

    Neuronpedia

    INDEX
    Explanations

    references and citations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Хорошо
    -0.51
    ーション
    -0.50
    EndGlobalSection
    -0.50
    miste
    -0.50
    mantel
    -0.49
    ArgsConstructor
    -0.49
    istics
    -0.48
    gste
    -0.48
     Garn
    -0.47
    AppCompat
    -0.47
    POSITIVE LOGITS
     REF
    1.18
     refs
    1.10
     references
    1.06
    REF
    1.05
     Refs
    1.05
     Reference
    1.03
     reference
    1.02
    ref
    1.02
    Refer
    1.01
     References
    1.01
    Act Density 0.310%

    No Known Activations