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

    Neuronpedia

    INDEX
    Explanations

    specific years within a chronological range

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orgot
    -0.15
    usi
    -0.14
    argin
    -0.13
     Garten
    -0.13
     choisir
    -0.12
    λοι
    -0.12
    abad
    -0.12
     worn
    -0.12
     fibre
    -0.12
    nave
    -0.12
    POSITIVE LOGITS
     tr
    0.15
    ves
    0.14
     Stevens
    0.14
    ãĤĵãģ¨
    0.14
    ulant
    0.13
    .extension
    0.13
    athan
    0.13
    elf
    0.13
    utherford
    0.13
    .override
    0.13
    Act Density 0.005%

    No Known Activations