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

    Neuronpedia

    INDEX
    Explanations

    the character '²'

    oai_token-act-pair · gpt-4-turbo

    number combinations and some special characters

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols potentially indicating encoding issues or non-standard text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.84
    isner
    -0.79
    NetMessage
    -0.79
    ynthesis
    -0.79
    sembly
    -0.78
    ebus
    -0.78
    pocket
    -0.78
    essing
    -0.76
    versions
    -0.74
    ession
    -0.73
    POSITIVE LOGITS
    ²
    1.04
    ³
    1.01
    ¡
    1.01
    ł
    0.97
    ãĥ¼ãĥ
    0.92
    ´
    0.91
    »
    0.85
    ãĤ§
    0.83
    ãĤ«
    0.83
    ¹
    0.82
    Act Density 0.006%

    No Known Activations