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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aloud
    -0.81
     whenever
    -0.78
     accordingly
    -0.71
     periodically
    -0.67
    opa
    -0.67
    ISTER
    -0.65
     thereafter
    -0.65
     irrespective
    -0.65
    LEASE
    -0.64
    udo
    -0.64
    POSITIVE LOGITS
     slightest
    1.43
     requisite
    1.08
     opportunity
    1.04
     ability
    1.00
     luxury
    0.99
     guts
    0.98
     sophistication
    0.98
     capability
    0.98
     same
    0.97
     expertise
    0.94
    Act Density 0.054%

    No Known Activations