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

    Neuronpedia

    INDEX
    Explanations

    references to falling asleep

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "asleep."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Char
    -0.75
    venants
    -0.70
     risks
    -0.69
    eq
    -0.66
    auntlets
    -0.65
    Hyper
    -0.65
    uber
    -0.63
    INC
    -0.62
    issue
    -0.62
     RIS
    -0.62
    POSITIVE LOGITS
     asleep
    1.39
     seiz
    0.85
    leep
    0.84
     slept
    0.83
    urnal
    0.82
     awake
    0.78
     dreaming
    0.78
     sleeps
    0.74
     sleep
    0.72
     sleepy
    0.71
    Act Density 0.005%

    No Known Activations