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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related words and phrases, particularly those that indicate specific days or months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ystem
    -0.66
    imon
    -0.57
    iov
    -0.56
     Shutterstock
    -0.54
    Contents
    -0.54
    ources
    -0.54
    yles
    -0.54
    robe
    -0.54
    onne
    -0.53
    inyl
    -0.52
    POSITIVE LOGITS
    's
    1.56
    âĢ²
    1.07
    ÃŃs
    1.07
    ´
    1.01
    \'
    0.98
    �
    0.90
    `
    0.89
    Ê
    0.86
     prayers
    0.70
     marks
    0.64
    Act Density 0.134%

    No Known Activations