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

    Neuronpedia

    INDEX
    Explanations

    words indicating strong emphasis or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uz
    -0.20
     Alone
    -0.15
    ĥ
    -0.15
     alone
    -0.15
     emb
    -0.15
     forth
    -0.14
     Tie
    -0.14
     sleep
    -0.14
    ãĤ¦ãĥĪ
    -0.14
    ole
    -0.13
    POSITIVE LOGITS
    ést
    0.15
    .gdx
    0.15
    ynos
    0.14
    олом
    0.14
     ngữ
    0.14
    esco
    0.14
    ừng
    0.14
    dain
    0.14
    521
    0.14
     eventdata
    0.14
    Act Density 0.008%

    No Known Activations