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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions such as specific hours or timeframes

    oai_token-act-pair · gpt-3.5-turbo

    numerical sequences and values related to dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emouth
    -0.74
    efer
    -0.66
    ulk
    -0.63
    ucci
    -0.62
    iating
    -0.59
    ieri
    -0.58
    stead
    -0.58
     vested
    -0.58
     illusion
    -0.57
     blot
    -0.55
    POSITIVE LOGITS
    11
    1.44
    12
    1.35
     11
    1.35
     12
    1.24
    13
    1.21
    10
    1.10
     13
    1.09
    14
    1.05
     ele
    1.03
    15
    1.01
    Act Density 0.128%

    No Known Activations