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

    Neuronpedia

    INDEX
    Explanations

    phrases related to waking up from sleep

    oai_token-act-pair · gpt-3.5-turbo

    instances of waking or being awakened

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inates
    -0.80
    entric
    -0.67
    ately
    -0.66
     Rouge
    -0.66
    berus
    -0.65
    esan
    -0.63
     coord
    -0.62
    ahime
    -0.62
    ietal
    -0.61
     chloride
    -0.61
    POSITIVE LOGITS
    mares
    1.11
    wake
    1.09
    fulness
    0.93
    up
    0.85
    mare
    0.81
     refreshed
    0.81
    urst
    0.79
     Wake
    0.79
    Up
    0.77
     woke
    0.75
    Act Density 0.023%

    No Known Activations