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

    Neuronpedia

    INDEX
    Explanations

    references to bars or similar establishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ese
    -0.25
    y
    -0.20
    naire
    -0.20
    ene
    -0.20
    esse
    -0.18
    ester
    -0.18
    aires
    -0.18
    estar
    -0.18
    end
    -0.18
    edb
    -0.17
    POSITIVE LOGITS
    riers
    0.24
    oque
    0.20
    mony
    0.19
    rows
    0.19
    celona
    0.18
    becue
    0.18
    asaki
    0.17
    rier
    0.16
    tered
    0.16
    rell
    0.16
    Act Density 0.027%

    No Known Activations