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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases, possibly involving reservations or schedules

    oai_token-act-pair · gpt-3.5-turbo

    references to statements, opinions, or allegations and their confirmations or denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indoor
    -0.77
     beaches
    -0.71
    chnology
    -0.71
    expensive
    -0.69
    Thousands
    -0.68
    Hundreds
    -0.68
     indoors
    -0.68
    roups
    -0.67
    iership
    -0.66
    usterity
    -0.65
    POSITIVE LOGITS
     he
    1.23
     âĢ
    1.19
    âĢ
    1.04
     commenter
    1.04
     his
    0.97
     commenters
    0.93
    his
    0.90
     Scalia
    0.87
     she
    0.87
     §
    0.85
    Act Density 0.613%

    No Known Activations