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

    Neuronpedia

    INDEX
    Explanations

    text related to diverse languages, possibly focusing on specific characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.87
     guiActiveUnfocused
    -0.83
    terday
    -0.75
    creen
    -0.64
     TPP
    -0.64
    ified
    -0.64
     decomp
    -0.63
    ORED
    -0.63
    flash
    -0.62
    hower
    -0.61
    POSITIVE LOGITS
    ģ
    1.35
    ¬
    1.29
    ¼
    1.28
    ¸
    1.21
    Ģ
    1.19
    ´
    1.19
    ½
    1.18
    ĺ
    1.16
    »
    1.15
    ĭ
    1.15
    Act Density 0.006%

    No Known Activations