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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events happening before a certain point in time

    oai_token-act-pair · gpt-3.5-turbo

    the word "Prior" and its variants, indicating temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.84
    è¦ļéĨĴ
    -0.79
    aden
    -0.72
    ÙĴ
    -0.65
     darts
    -0.65
     ILCS
    -0.62
    immer
    -0.62
    chrom
    -0.60
     scalp
    -0.59
    ources
    -0.59
    POSITIVE LOGITS
    ities
    1.19
    itized
    0.98
    ity
    0.89
    itor
    0.79
    IOR
    0.79
    icip
    0.79
    profits
    0.75
    alities
    0.75
    ality
    0.74
    requisite
    0.74
    Act Density 0.010%

    No Known Activations