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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes happening over time

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.81
    kef
    -0.79
    minster
    -0.76
    awan
    -0.74
    emate
    -0.73
    erd
    -0.71
    uckland
    -0.68
    alach
    -0.67
    XT
    -0.67
     Ri
    -0.66
    POSITIVE LOGITS
     periods
    1.02
    frames
    0.98
     iterations
    0.87
     consuming
    0.80
     generations
    0.77
     millennia
    0.77
    trial
    0.74
     gestation
    0.73
     ago
    0.72
     cycles
    0.72
    Act Density 0.020%

    No Known Activations