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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.61
    isible
    -0.56
    ingo
    -0.55
    etti
    -0.55
    Ge
    -0.53
    cil
    -0.52
    equal
    -0.52
    ifferent
    -0.52
    rg
    -0.51
    bler
    -0.51
    POSITIVE LOGITS
     morning
    0.92
    ursday
    0.89
     afternoon
    0.82
    morning
    0.78
     Sept
    0.77
     evening
    0.77
     January
    0.76
     semester
    0.75
     week
    0.75
     July
    0.74
    Act Density 0.283%

    No Known Activations