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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change or event happening after a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    the word "since" indicating the passage of time or events related to a prior occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abus
    -0.77
    amina
    -0.71
    hack
    -0.67
    Ruby
    -0.66
    NRS
    -0.66
    amount
    -0.66
    gravity
    -0.64
    iHUD
    -0.64
    Fight
    -0.64
    bart
    -0.63
    POSITIVE LOGITS
    ĸļ
    1.19
    rely
    1.03
     1955
    0.78
     1979
    0.76
     1961
    0.75
    since
    0.74
     1946
    0.74
     1945
    0.73
     installing
    0.72
     1951
    0.72
    Act Density 0.052%

    No Known Activations