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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce a topic or discussion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize significant or noteworthy aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.76
    $$$$
    -0.67
    igation
    -0.64
     ..............
    -0.63
    Filename
    -0.63
    missions
    -0.63
    robe
    -0.62
    Cas
    -0.61
    ivery
    -0.61
     Rooms
    -0.61
    POSITIVE LOGITS
     struck
    0.99
     bothered
    0.98
     noticeably
    0.97
     conspic
    0.95
     intrigued
    0.93
     stood
    0.93
     overlooked
    0.92
     impressed
    0.91
     reson
    0.90
     bothers
    0.90
    Act Density 0.239%

    No Known Activations