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

    Neuronpedia

    INDEX
    Explanations

    features related to software functionality and user interface design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Middleton
    -0.15
    æ¢
    -0.14
    423
    -0.14
    ãĥ¼ãĥ³
    -0.14
    kaar
    -0.14
    623
    -0.14
    685
    -0.13
     informat
    -0.13
     pob
    -0.13
    523
    -0.13
    POSITIVE LOGITS
     built
    0.24
     ability
    0.24
    built
    0.23
     facility
    0.21
     builtin
    0.21
     automatic
    0.20
     capability
    0.20
     Undo
    0.19
     support
    0.18
    facility
    0.18
    Act Density 0.180%

    No Known Activations