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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions that reflect a strong opinion or sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĶåĽŀ
    -0.15
    nder
    -0.14
    ½æķ°
    -0.14
    ród
    -0.14
    ULD
    -0.13
    719
    -0.13
    247
    -0.13
    ernals
    -0.13
    581
    -0.13
    беÑĢ
    -0.13
    POSITIVE LOGITS
    ÙĦت
    0.15
    caled
    0.15
    itzer
    0.15
    bn
    0.14
    dong
    0.14
    каз
    0.14
    hong
    0.14
    ekk
    0.13
    onsense
    0.13
    -cent
    0.13
    Act Density 0.068%

    No Known Activations