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

    Neuronpedia

    INDEX
    Explanations

    references to events or occurrences happening over the past year

    oai_token-act-pair · gpt-3.5-turbo

    references to duration, particularly the phrase "over the past year."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Facilities
    -0.70
     monop
    -0.64
     breaching
    -0.63
     instr
    -0.62
    inki
    -0.62
     Fram
    -0.61
     viol
    -0.61
    igham
    -0.60
     wills
    -0.60
     wand
    -0.60
    POSITIVE LOGITS
    orate
    0.99
    eteenth
    0.79
    days
    0.78
    iannopoulos
    0.77
    nings
    0.74
     semester
    0.70
    ruary
    0.70
    long
    0.68
    oton
    0.68
    frames
    0.67
    Act Density 0.087%

    No Known Activations