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

    Neuronpedia

    INDEX
    Explanations

    temporal phrases indicating periods of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.57
     itſelf
    -0.57
     houſe
    -0.57
     ſtand
    -0.56
     Majefty
    -0.55
     ſta
    -0.54
     ſtate
    -0.54
     raiſ
    -0.53
     leſs
    -0.52
     anſ
    -0.51
    POSITIVE LOGITS
     during
    1.26
    during
    1.21
     DURING
    1.18
     During
    1.13
    During
    1.07
    durante
    0.97
     Durante
    0.93
    Durante
    0.89
     durante
    0.88
     tijdens
    0.83
    Act Density 0.115%

    No Known Activations