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

    Neuronpedia

    INDEX
    Explanations

    comment syntax and markup in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cordero
    -0.90
     FontWeight
    -0.82
    addGap
    -0.80
    serviceWorker
    -0.76
    PRNewswire
    -0.76
     Flu
    -0.74
    lossians
    -0.73
     Thornton
    -0.73
     Griffin
    -0.72
     дописавши
    -0.71
    POSITIVE LOGITS
     Theſe
    1.09
    )*/
    1.03
     themſelves
    0.96
    ');?>
    0.93
     myſelf
    0.92
    >-->
    0.92
     uſed
    0.89
     himſelf
    0.87
     Neymar
    0.86
     pleaſure
    0.86
    Act Density 0.018%

    No Known Activations