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

    Neuronpedia

    INDEX
    Explanations

    instances of time-related events

    oai_token-act-pair · gpt-3.5-turbo

    the repeated reference to "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sers
    -0.76
    vu
    -0.69
    76561
    -0.66
    rawdownloadcloneembedreportprint
    -0.61
     Franch
    -0.61
    Downloadha
    -0.60
    osaurus
    -0.59
    =-=-=-=-=-=-=-=-
    -0.59
    916
    -0.58
    bred
    -0.58
    POSITIVE LOGITS
     month
    1.52
     week
    1.47
     year
    1.36
     afternoon
    1.20
     decade
    1.16
     semester
    1.13
     morning
    1.12
     evening
    1.11
     summer
    1.09
     weekend
    1.08
    Act Density 0.040%

    No Known Activations