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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orama
    -0.21
    opi
    -0.17
    itsu
    -0.15
    fram
    -0.15
    fst
    -0.15
    emax
    -0.15
    illum
    -0.15
    vanished
    -0.15
    opak
    -0.15
    enerator
    -0.15
    POSITIVE LOGITS
    gard
    0.15
     indeed
    0.15
    ãĥĥãĤ«ãĥ¼
    0.15
     Tent
    0.15
     Couch
    0.14
    ÑĦиÑĨи
    0.14
    -fi
    0.14
    931
    0.14
    ault
    0.14
     respectively
    0.14
    Act Density 0.080%

    No Known Activations