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

    Neuronpedia

    INDEX
    Explanations

    instances of the past tense of "wake," specifically the word "woke"

    oai_token-act-pair · gpt-4-turbo

    references to waking up or awakening

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "woke" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inates
    -0.82
    onne
    -0.78
    orde
    -0.70
     Hezbollah
    -0.70
    iyah
    -0.66
     collateral
    -0.65
    ateral
    -0.64
    ately
    -0.64
    asse
    -0.64
    osa
    -0.63
    POSITIVE LOGITS
    mares
    1.21
    wake
    1.12
     woke
    0.90
     awake
    0.85
    dream
    0.83
     wakes
    0.79
     wake
    0.77
    Dream
    0.76
    leep
    0.76
    achine
    0.75
    Act Density 0.015%

    No Known Activations