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

    Neuronpedia

    INDEX
    Explanations

    phrases communicating uncertainty or hearsay related to events or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftware
    -0.16
    æ§
    -0.15
    ãĤ«ãĥ¼
    -0.14
    å¸Ń
    -0.14
     postage
    -0.14
    fra
    -0.14
    æŃ
    -0.14
    ayar
    -0.13
    inho
    -0.13
    IRA
    -0.13
    POSITIVE LOGITS
    amat
    0.17
    afort
    0.15
    .sec
    0.15
    reek
    0.14
    ãĥĥãĥī
    0.14
     lum
    0.14
     leaked
    0.14
    лÑĥÑĩ
    0.14
    umat
    0.13
    ">ÃĹ</
    0.13
    Act Density 0.019%

    No Known Activations