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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the start of a new segment or topic

    oai_token-act-pair · gpt-3.5-turbo

    the word "Here" indicating a list or detailed explanation is forthcoming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.62
    )].
    -0.60
    mong
    -0.60
    Doctors
    -0.59
     absor
    -0.58
     Archdemon
    -0.56
    existent
    -0.56
     acupuncture
    -0.54
     vib
    -0.54
     Circle
    -0.53
    POSITIVE LOGITS
    tics
    1.29
    tical
    1.25
    abouts
    1.19
    tic
    1.12
    ford
    0.81
     Comes
    0.80
    after
    0.77
    here
    0.77
    yers
    0.76
    fore
    0.76
    Act Density 0.041%

    No Known Activations