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

    Neuronpedia

    INDEX
    Explanations

    references to citations and academic formatting in a research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oru
    -0.07
    orum
    -0.07
    TRL
    -0.07
     lô
    -0.06
    etest
    -0.06
    upo
    -0.06
     CÆ¡
    -0.06
     Lust
    -0.06
     æ¼
    -0.06
    lap
    -0.06
    POSITIVE LOGITS
    ceph
    0.07
    alf
    0.06
    ills
    0.06
    aina
    0.06
    .blogspot
    0.06
    iew
    0.06
    ews
    0.06
    ÙģاÙĤ
    0.06
    lector
    0.06
    946
    0.06
    Act Density 0.027%

    No Known Activations