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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns, particularly names of people, organizations, and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UDA
    -0.15
    _intf
    -0.14
     PATCH
    -0.13
    éĢIJ
    -0.13
     vill
    -0.13
    pets
    -0.13
    lein
    -0.13
    EDURE
    -0.13
    ãĥĻãĥ«
    -0.13
    beat
    -0.12
    POSITIVE LOGITS
     family
    0.15
    acco
    0.14
    360
    0.14
    akens
    0.14
    YE
    0.14
    anean
    0.13
     ITE
    0.13
     Fol
    0.13
    787
    0.13
     DropIndex
    0.13
    Act Density 0.355%

    No Known Activations