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

    Neuronpedia

    INDEX
    Explanations

    numerical values formatted as dates or list items

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or references related to dates and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atis
    -0.78
    asca
    -0.69
    umin
    -0.68
    itsch
    -0.68
    ascus
    -0.67
    atem
    -0.67
    nih
    -0.66
     tremend
    -0.65
    edia
    -0.64
    itzer
    -0.64
    POSITIVE LOGITS
    th
    1.00
     Minutes
    0.85
     minutes
    0.83
    arters
    0.81
    mins
    0.81
    55
    0.77
    yrs
    0.77
    %:
    0.76
     mins
    0.76
    36
    0.76
    Act Density 0.046%

    No Known Activations