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

    Neuronpedia

    INDEX
    Explanations

    phrases related to free speech and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wap
    -0.15
    erland
    -0.14
    utral
    -0.14
    iator
    -0.14
    ill
    -0.14
    -scalable
    -0.14
    ledo
    -0.13
     Hao
    -0.13
    umi
    -0.13
    ynn
    -0.13
    POSITIVE LOGITS
    esin
    0.16
    ãĢģ“
    0.14
    ÙĪرÙĨ
    0.14
    ТÐŀ
    0.14
    .Unicode
    0.14
    .lazy
    0.14
    chl
    0.14
    oret
    0.14
    egis
    0.13
     ФоÑĢ
    0.13
    Act Density 0.360%

    No Known Activations