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

    Neuronpedia

    INDEX
    Explanations

    elements related to power dynamics and control within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    веÑĢ
    -0.17
    alez
    -0.16
    ahl
    -0.16
    ãĥ¼ãĥ«
    -0.15
    .BLL
    -0.15
    á»±c
    -0.15
    Ỽ
    -0.14
    æ³£
    -0.14
    ÑĢеменно
    -0.14
    pler
    -0.14
    POSITIVE LOGITS
     upon
    0.17
    ="__
    0.15
     Thornton
    0.15
    à¤Ĺल
    0.15
     Messenger
    0.14
    Upon
    0.14
    宫
    0.14
     Upon
    0.14
     ÙħÙĨÙĩ
    0.14
    Bi
    0.14
    Act Density 0.110%

    No Known Activations