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

    Neuronpedia

    INDEX
    Explanations

    statements about awareness and perception regarding experiences and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prt
    -0.15
    hcp
    -0.14
    817
    -0.14
    iloc
    -0.14
     misunderstanding
    -0.14
    avery
    -0.13
    iten
    -0.13
     Understanding
    -0.13
    isman
    -0.13
     Ratings
    -0.13
    POSITIVE LOGITS
     notice
    0.56
     noticed
    0.50
     notices
    0.50
    notice
    0.47
     Notice
    0.47
    Notice
    0.46
     noticing
    0.44
    noticed
    0.42
     NOTICE
    0.38
     Noticed
    0.37
    Act Density 0.151%

    No Known Activations