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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in month and day format

    oai_token-act-pair · gpt-3.5-turbo

    statements about uncertainty regarding events and predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dehuman
    -0.69
     misogyn
    -0.65
     witchcraft
    -0.65
     raping
    -0.64
     murderer
    -0.62
     stereotype
    -0.62
     pearl
    -0.61
     misogyny
    -0.61
     persecut
    -0.60
     anthrop
    -0.60
    POSITIVE LOGITS
     timetable
    0.99
     tentative
    0.95
     TBA
    0.87
     deadline
    0.85
     announcements
    0.80
     Deadline
    0.79
     contingency
    0.76
     2019
    0.75
     announcement
    0.74
     TBD
    0.74
    Act Density 1.200%

    No Known Activations