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

    Neuronpedia

    INDEX
    Explanations

    punctuations and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.80
    zzlies
    -0.78
     تضيفلها
    -0.77
     Stapleton
    -0.76
     Werth
    -0.74
     ostavi
    -0.71
    Grimm
    -0.71
     ComVisible
    -0.70
     Grä
    -0.69
    Holt
    -0.68
    POSITIVE LOGITS
    2
    0.99
    nd
    0.90
     twos
    0.85
     thirds
    0.84
    thirds
    0.83
    ₂
    0.79
    braio
    0.73
     sẻ
    0.71
     Tw
    0.69
    २
    0.66
    Act Density 0.289%

    No Known Activations