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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the timing of events, specifically the word "Last" followed by a time reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ular
    -0.18
    erv
    -0.17
    _EV
    -0.16
    ogan
    -0.15
    uch
    -0.15
    idel
    -0.14
     Breed
    -0.14
     Easter
    -0.14
    u
    -0.14
     Most
    -0.14
    POSITIVE LOGITS
    ing
    0.26
     chance
    0.18
    edis
    0.17
    Chance
    0.17
     Chance
    0.17
     year
    0.17
    ingly
    0.16
    sik
    0.16
     last
    0.16
    imir
    0.16
    Act Density 0.018%

    No Known Activations