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

    Neuronpedia

    INDEX
    Explanations

    references to academic presentations and conferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tard
    -0.17
    coop
    -0.16
    ijken
    -0.16
    lez
    -0.16
    utters
    -0.15
    ECT
    -0.15
    elman
    -0.15
    aggio
    -0.15
    isper
    -0.15
    åĭ
    -0.14
    POSITIVE LOGITS
    Datum
    0.14
    anol
    0.14
    ESIS
    0.14
    amp
    0.14
    ãĥĥãĤ·ãĥ¥
    0.14
    CHO
    0.14
     ade
    0.13
     Dah
    0.13
    titles
    0.13
    EZ
    0.13
    Act Density 0.027%

    No Known Activations