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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in the day-month format

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and numerical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tut
    -0.56
     hobbies
    -0.56
     explan
    -0.55
     lawy
    -0.55
     habitual
    -0.54
     Genie
    -0.54
     DI
    -0.54
     sys
    -0.54
     streng
    -0.53
     distance
    -0.53
    POSITIVE LOGITS
    th
    1.59
    rd
    1.18
    ths
    1.09
    TH
    1.01
    teenth
    0.99
    nd
    0.93
    tha
    0.89
    eteenth
    0.88
    thus
    0.87
    ember
    0.87
    Act Density 0.101%

    No Known Activations