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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to policies and regulatory matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lé
    -0.17
    æ´¥
    -0.16
    icom
    -0.15
    lings
    -0.15
    atab
    -0.14
    å
    -0.14
    stad
    -0.14
    ienne
    -0.14
    sted
    -0.14
    ming
    -0.14
    POSITIVE LOGITS
    /legal
    0.20
    holders
    0.18
    heiro
    0.17
    ofile
    0.15
    Cookies
    0.15
    -makers
    0.15
    fully
    0.15
    ichick
    0.14
    rons
    0.14
    holder
    0.14
    Act Density 0.035%

    No Known Activations