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

    Neuronpedia

    INDEX
    Explanations

    time-related terms and forecasting phrases, such as "three years", "four months", and "in two weeks."

    oai_token-act-pair · gpt-3.5-turbo

    time-related expressions indicating the passage of days, weeks, months, and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inse
    -0.72
     inclusion
    -0.67
    reon
    -0.63
    irsch
    -0.61
    utsche
    -0.61
     subp
    -0.60
     incent
    -0.60
     facade
    -0.60
     fault
    -0.60
     compuls
    -0.60
    POSITIVE LOGITS
     span
    0.99
     increments
    0.98
    hops
    0.74
     ago
    0.72
     intervals
    0.68
     fashion
    0.66
    soDeliveryDate
    0.65
    VERT
    0.65
    opian
    0.64
     PLoS
    0.64
    Act Density 0.097%

    No Known Activations