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

    Neuronpedia

    INDEX
    Explanations

    mentions of old or aged items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "old" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.89
    rawdownloadcloneembedreportprint
    -0.78
    Ĥİ
    -0.77
    illation
    -0.77
    rer
    -0.76
    vous
    -0.76
    amera
    -0.75
    rencies
    -0.74
    atography
    -0.72
    ILA
    -0.72
    POSITIVE LOGITS
     fashioned
    1.55
    school
    1.02
    fashioned
    0.97
     timers
    0.96
     standby
    0.94
    est
    0.91
    timer
    0.86
    rums
    0.85
     school
    0.83
    tim
    0.80
    Act Density 0.040%

    No Known Activations