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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight distinctions or preferences among items or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ello
    -0.19
     æĸ¹
    -0.15
     odst
    -0.14
    hatt
    -0.14
    RelativeTo
    -0.14
    alic
    -0.14
    Forge
    -0.14
    clusion
    -0.14
    .renderer
    -0.13
    usi
    -0.13
    POSITIVE LOGITS
     Cummings
    0.15
    ioni
    0.14
     Owen
    0.14
    İ·
    0.13
    osa
    0.13
    ستÛĮ
    0.13
    acea
    0.13
     Cutter
    0.13
     Winn
    0.13
    AUSE
    0.13
    Act Density 0.024%

    No Known Activations