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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time or duration of past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æľ«
    -0.15
    ogan
    -0.15
    ãĥ£
    -0.15
    ernes
    -0.15
    ÄŁan
    -0.15
    arts
    -0.15
    ungi
    -0.14
    rone
    -0.14
     Packs
    -0.14
    erner
    -0.14
    POSITIVE LOGITS
     few
    0.23
    /current
    0.17
     decade
    0.17
     several
    0.16
    åĩł
    0.16
     неÑģколÑĮко
    0.15
    OnInit
    0.15
     three
    0.15
    Few
    0.15
     two
    0.15
    Act Density 0.041%

    No Known Activations