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

    Neuronpedia

    INDEX
    Explanations

    non-English characters and potentially names or locations

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.71
     Heath
    -0.70
     Starr
    -0.69
    ORED
    -0.67
    liness
    -0.67
    SPONSORED
    -0.66
    20439
    -0.66
     Daly
    -0.65
    bury
    -0.65
     Hastings
    -0.65
    POSITIVE LOGITS
    Ŀ
    1.38
    Ð
    1.35
    ¹
    1.33
    ±
    1.32
    Ķ
    1.29
    ł
    1.27
    ³
    1.27
    ļ
    1.21
    ¡
    1.21
    Ĵ
    1.19
    Act Density 0.002%

    No Known Activations