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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time, particularly those suggesting past occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nestjs
    -0.82
     ​​
    -0.71
     Bul
    -0.67
    исленность
    -0.65
     wake
    -0.64
     Wal
    -0.63
    burgs
    -0.62
     Injectable
    -0.60
    unile
    -0.59
     Un
    -0.58
    POSITIVE LOGITS
     earlier
    2.08
    earlier
    2.07
     Earlier
    2.02
    Earlier
    1.91
    later
    1.34
     EARL
    1.33
     LATER
    1.27
    Later
    1.24
     later
    1.20
     leſs
    1.19
    Act Density 0.050%

    No Known Activations