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

    Neuronpedia

    INDEX
    Explanations

    word forms related to the act of sleeping

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of sleeping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inez
    -0.83
    enez
    -0.73
    vernment
    -0.73
    ific
    -0.72
    £ı
    -0.69
    cture
    -0.68
    ctions
    -0.67
    ================================
    -0.66
    ISO
    -0.66
    Ĭ±
    -0.63
    POSITIVE LOGITS
     slept
    0.83
     sleeps
    0.82
    walker
    0.82
     pill
    0.79
    eper
    0.79
     arrang
    0.77
    walking
    0.76
    pill
    0.76
     sleeping
    0.76
     sleeper
    0.75
    Act Density 0.022%

    No Known Activations