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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate emphasis or focus on specific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hood
    -0.16
    ãĥ¼ãĥ©
    -0.15
    åł
    -0.15
    ÙĪÛĮزÛĮ
    -0.15
    HEMA
    -0.15
    yb
    -0.15
    quate
    -0.15
    nal
    -0.15
    arella
    -0.14
    PT
    -0.14
    POSITIVE LOGITS
     Tow
    0.16
    lix
    0.16
    .tex
    0.16
     Bene
    0.16
    306
    0.14
     Burnett
    0.14
    iza
    0.14
    naÄį
    0.14
    lu
    0.14
    adera
    0.14
    Act Density 0.032%

    No Known Activations