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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific periods of time

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardo
    -0.73
    andro
    -0.68
    artisan
    -0.66
     Tro
    -0.66
    illard
    -0.65
    Tro
    -0.64
    bold
    -0.63
    alg
    -0.62
    fol
    -0.60
    uno
    -0.59
    POSITIVE LOGITS
     duration
    1.02
     periods
    0.94
    duration
    0.92
     intervals
    0.80
    Duration
    0.79
     interval
    0.78
     period
    0.78
     consecut
    0.76
     thereafter
    0.75
     longer
    0.74
    Act Density 0.062%

    No Known Activations