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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical values or currency

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating high importance or critical statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yar
    -1.21
    YA
    -1.00
     Bubble
    -0.98
    ¥µ
    -0.97
    ya
    -0.97
    xb
    -0.92
    yx
    -0.89
    Yan
    -0.89
    yan
    -0.88
     Wak
    -0.85
    POSITIVE LOGITS
    ipp
    0.98
    ass
    0.94
    oss
    0.93
    131
    0.92
    select
    0.90
    iss
    0.86
    IPP
    0.85
    lect
    0.84
    ress
    0.83
    asses
    0.81
    Act Density 0.383%

    No Known Activations