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

    Neuronpedia

    INDEX
    Explanations

    references to mirrors and reflective concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.09
    Демографія
    -1.07
     utafitiHapana
    -1.05
     itſelf
    -1.03
     Theſe
    -1.01
     springfox
    -1.01
    ReusableCell
    -1.01
    IntoConstraints
    -0.99
     Efq
    -0.98
     InputDecoration
    -0.95
    POSITIVE LOGITS
     '"
    1.51
     "'
    1.33
    ='"
    1.17
    '"
    1.16
    "'
    1.00
    ('"
    0.98
    ="'
    0.88
    ("'
    0.83
     "'"
    0.79
     '"'
    0.77
    Act Density 0.128%

    No Known Activations