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

    Neuronpedia

    INDEX
    Explanations

    comparisons or similes using the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erte
    -0.14
     Pey
    -0.14
    elper
    -0.14
    ube
    -0.14
    .configure
    -0.14
    å¥
    -0.14
    ĸ
    -0.14
     Existing
    -0.14
     yerde
    -0.14
    fg
    -0.13
    POSITIVE LOGITS
     Energ
    0.20
     champ
    0.20
     champs
    0.18
     bans
    0.17
    presso
    0.17
     proverb
    0.17
     freight
    0.17
     champion
    0.16
     clock
    0.15
     absolute
    0.15
    Act Density 0.057%

    No Known Activations