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

    Neuronpedia

    INDEX
    Explanations

    characters with special characters and emojis

    oai_token-act-pair · gpt-3.5-turbo

    unusual or potentially coded sequences of characters, likely indicating a specific encoding or format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arton
    -0.89
    cius
    -0.78
    leground
    -0.74
    achy
    -0.73
    etsk
    -0.73
    orsche
    -0.72
     bonded
    -0.71
    iche
    -0.71
    olithic
    -0.71
    lycer
    -0.70
    POSITIVE LOGITS
    ãĤ
    1.65
    ãģ
    1.65
    ãģª
    1.50
    ãģĭ
    1.49
    ãĤī
    1.49
    ãģŁ
    1.46
    ãģĦ
    1.45
    ãĤĭ
    1.45
    ãģ¾
    1.43
    ãģ¦
    1.41
    Act Density 0.010%

    No Known Activations