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

    Neuronpedia

    INDEX
    Explanations

    questions and statements related to truth and factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.83
     vœux
    -0.68
    ]")]
    -0.68
    NOPQRST
    -0.68
     مشين
    -0.64
     Offisielt
    -0.61
    restling
    -0.61
    riwal
    -0.61
    __':
    -0.60
    TemporalType
    -0.59
    POSITIVE LOGITS
     FetchType
    0.63
      
    0.57
    何を
    0.52
    NameInMap
    0.50
     benne
    0.48
    autoconfigure
    0.48
    Население
    0.46
     performance
    0.46
     everything
    0.45
    diğini
    0.45
    Act Density 0.303%

    No Known Activations