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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, such as weeks and months

    oai_token-act-pair · gpt-3.5-turbo

    temporal references relating to the quality or condition of a period of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haar
    -0.77
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
     dams
    -0.70
    emort
    -0.69
    atem
    -0.69
    verified
    -0.63
     guiActiveUn
    -0.63
    Cmd
    -0.62
     balcon
    -0.62
     guiIcon
    -0.62
    POSITIVE LOGITS
    nings
    0.94
    dream
    0.78
    night
    0.77
    ../
    0.74
    bye
    0.67
     outing
    0.63
    buy
    0.62
     affair
    0.62
    ning
    0.61
     opener
    0.61
    Act Density 0.120%

    No Known Activations