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

    Neuronpedia

    INDEX
    Explanations

    references to specific actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     שוליים
    -0.58
     stránka
    -0.55
    原始内容存档于
    -0.51
    SourceChecksum
    -0.49
    וויק
    -0.49
    Collegamenti
    -0.48
    ExtendWith
    -0.47
    Външни
    -0.46
    viewDidLoad
    -0.46
    WriteBarrier
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.82
    ագրություններ
    0.71
     nakalista
    0.65
    Демографія
    0.62
    RegressionTest
    0.60
    Lähteet
    0.60
    Geplaatst
    0.60
    áklad
    0.58
     Neolithic
    0.57
    ]++;
    0.56
    Act Density 0.725%

    No Known Activations