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

    Neuronpedia

    INDEX
    Explanations

    updates or new information in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to updates or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cad
    -0.67
     pride
    -0.67
     youth
    -0.65
     quarter
    -0.64
     sat
    -0.63
     fal
    -0.63
     mon
    -0.62
     pupil
    -0.62
     lust
    -0.62
     ser
    -0.61
    POSITIVE LOGITS
    UPDATE
    3.74
     UPDATE
    2.61
    Update
    2.41
    EDIT
    1.79
    update
    1.74
    PDATED
    1.66
    Updated
    1.63
    PDATE
    1.53
    updated
    1.48
    Edit
    1.42
    Act Density 0.027%

    No Known Activations