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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate commonality or general observations about experiences or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    firm
    -0.16
    öh
    -0.16
     alike
    -0.15
    輪
    -0.15
    bert
    -0.15
    aliz
    -0.14
    ầm
    -0.14
    fetch
    -0.14
    ibre
    -0.13
    BERT
    -0.13
    POSITIVE LOGITS
    uida
    0.16
    igkeit
    0.15
    ÐĺТ
    0.15
     gsi
    0.14
    etooth
    0.14
    enties
    0.14
    icket
    0.14
    illisecond
    0.14
    pig
    0.13
    gang
    0.13
    Act Density 0.094%

    No Known Activations