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

    Neuronpedia

    INDEX
    Explanations

    instances of numbers, particularly those representing years or significant data points related to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (es
    -0.16
    oc
    -0.15
    ic
    -0.15
    zcze
    -0.14
     Times
    -0.14
     sooner
    -0.14
    gua
    -0.14
    gba
    -0.14
    ghi
    -0.13
     Downs
    -0.13
    POSITIVE LOGITS
    年代
    0.30
    ties
    0.25
    ies
    0.24
    IES
    0.20
    elper
    0.19
    something
    0.19
    ÈĻ
    0.18
    Something
    0.17
    s
    0.17
     decade
    0.17
    Act Density 0.015%

    No Known Activations