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

    Neuronpedia

    INDEX
    Explanations

    date and time related terms

    oai_token-act-pair · gpt-3.5-turbo

    dates and timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    finder
    -0.60
    Interested
    -0.59
    vice
    -0.57
    orically
    -0.57
    andise
    -0.57
    ilitary
    -0.57
    ongo
    -0.56
    tube
    -0.54
    anca
    -0.54
    allo
    -0.54
    POSITIVE LOGITS
     07
    0.97
     09
    0.93
     08
    0.93
     06
    0.90
     05
    0.88
     02
    0.83
     03
    0.82
     04
    0.82
    Tue
    0.81
     Jul
    0.76
    Act Density 0.084%

    No Known Activations