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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "last" followed by a number indicating time or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ):?>↵
    -0.16
     Easter
    -0.15
    uch
    -0.15
    creasing
    -0.15
    iete
    -0.14
    åĵ¡
    -0.13
    mare
    -0.13
    ah
    -0.13
     Drum
    -0.13
    fait
    -0.13
    POSITIVE LOGITS
     chance
    0.23
    ing
    0.23
     Chance
    0.22
    Chance
    0.22
     week
    0.21
    ingly
    0.20
     year
    0.20
    edis
    0.19
     month
    0.18
     modified
    0.17
    Act Density 0.018%

    No Known Activations