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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters that likely belong to a specific language or encoding format

    oai_token-act-pair · gpt-3.5-turbo

    visual symbols or characters in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.84
    matically
    -0.81
     Skydragon
    -0.76
    haps
    -0.76
    ippi
    -0.75
    puter
    -0.74
     myster
    -0.73
    Else
    -0.73
     philos
    -0.73
    uyomi
    -0.72
    POSITIVE LOGITS
    ب
    0.87
    ERN
    0.84
    ãĥ¼
    0.83
    ׾
    0.83
    ÙĬ
    0.83
    į
    0.81
    Ø
    0.80
    ±
    0.80
    ãĥ¼ãĥ
    0.79
    Ù
    0.78
    Act Density 0.002%

    No Known Activations