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

    Neuronpedia

    INDEX
    Explanations

    references to daily activities or routines

    oai_token-act-pair · gpt-3.5-turbo

    references to daily activities and schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hett
    -0.78
    ngth
    -0.77
    emort
    -0.75
    ACTED
    -0.70
    obal
    -0.68
     Eag
    -0.67
    æ©
    -0.67
    ashtra
    -0.66
    oice
    -0.66
    icultural
    -0.66
    POSITIVE LOGITS
    dream
    1.79
    care
    1.19
    lights
    1.10
    break
    1.07
    light
    1.01
    nings
    0.97
    trip
    0.94
    long
    0.90
    BOOK
    0.88
    glass
    0.87
    Act Density 0.084%

    No Known Activations