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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.72
    Before
    -0.67
     Monfieur
    -0.66
    Espèce
    -0.63
     Before
    -0.63
     ſtate
    -0.61
     فريبيس
    -0.59
     diſt
    -0.57
     Diſ
    -0.56
     ſeveral
    -0.56
    POSITIVE LOGITS
     time
    1.85
     Time
    1.33
    time
    1.32
    Time
    1.21
     TIME
    1.20
    TIME
    1.03
     tijd
    1.02
    TimeTo
    0.93
     hora
    0.92
    时间
    0.92
    Act Density 0.124%

    No Known Activations