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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to empowerment and support for individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wyn
    -0.16
    Sharper
    -0.16
    esar
    -0.15
    ÌĨ
    -0.15
    ạch
    -0.14
    icias
    -0.14
    utable
    -0.14
     ÙĩÛĮ
    -0.14
    icult
    -0.13
    chers
    -0.13
    POSITIVE LOGITS
    /power
    0.18
    atti
    0.15
    atz
    0.15
    /disable
    0.15
    standing
    0.14
    iferay
    0.14
    -play
    0.14
    fully
    0.13
    flu
    0.13
    ızı
    0.13
    Act Density 0.012%

    No Known Activations