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

    Neuronpedia

    INDEX
    Explanations

    phrases related to routine actions or habits

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of daily occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itars
    -0.86
    emort
    -0.85
    itsch
    -0.75
    aeus
    -0.74
    atis
    -0.72
    emet
    -0.70
    DragonMagazine
    -0.70
    dinand
    -0.69
    tymology
    -0.69
    ounded
    -0.69
    POSITIVE LOGITS
     thereafter
    0.92
    motion
    0.91
     mornings
    0.84
    dream
    0.82
    days
    0.81
     waking
    0.77
    night
    0.77
    noon
    0.74
    theless
    0.70
     commute
    0.69
    Act Density 0.033%

    No Known Activations