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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the act of observing

    oai_token-act-pair · gpt-3.5-turbo

    references to visual perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manag
    -0.73
     Adin
    -0.72
     disarm
    -0.69
     careful
    -0.68
     treasurer
    -0.68
     reset
    -0.65
     recons
    -0.63
     contention
    -0.62
     reconnect
    -0.62
     reass
    -0.62
    POSITIVE LOGITS
    DragonMagazine
    0.97
    Downloadha
    0.95
    SI
    0.87
    wcsstore
    0.77
    áµ
    0.74
    Ô
    0.72
    PsyNetMessage
    0.70
    YING
    0.69
    IU
    0.69
    çīĪ
    0.68
    Act Density 0.099%

    No Known Activations