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

    Neuronpedia

    INDEX
    Explanations

    references to slavery and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [to
    -0.15
    istory
    -0.15
    erif
    -0.15
     crow
    -0.14
    ismus
    -0.14
    esser
    -0.14
    tick
    -0.14
    ÏĥÏĦε
    -0.14
    tega
    -0.13
    اÙĦÙĤ
    -0.13
    POSITIVE LOGITS
    enko
    0.17
    owl
    0.16
    ãĥĥãĤ·ãĥ¥
    0.15
    acia
    0.15
     Shack
    0.15
    geber
    0.15
    rypt
    0.14
    orum
    0.14
    utor
    0.14
     ******************************************************************************↵
    0.14
    Act Density 0.010%

    No Known Activations