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

    Neuronpedia

    INDEX
    Explanations

    references to specific concepts or items within a theoretical or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.85
     Houſe
    -0.80
     pleaſure
    -0.79
     Majefty
    -0.78
     Monfieur
    -0.73
     reaſon
    -0.73
     Efq
    -0.72
     Anſ
    -0.72
     Etr
    -0.69
     Garibaldi
    -0.69
    POSITIVE LOGITS
     mêmes
    0.52
    例句
    0.52
     •
    0.48
     relation
    0.47
     demás
    0.47
     betreffenden
    0.47
     lazos
    0.47
    elfth
    0.47
    vanju
    0.47
     précédentes
    0.46
    Act Density 1.378%

    No Known Activations