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

    Neuronpedia

    INDEX
    Explanations

    references to menus in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.11
     becauſe
    -0.98
    CloseOperation
    -0.95
     raiſ
    -0.94
     auffi
    -0.94
     enfans
    -0.92
    __':
    -0.91
     Monfieur
    -0.91
     myſelf
    -0.91
     grève
    -0.91
    POSITIVE LOGITS
     menu
    0.66
     
    0.63
     por
    0.62
     able
    0.59
     “
    0.57
     al
    0.53
     ter
    0.53
     inclusive
    0.53
     (
    0.53
    getAll
    0.52
    Act Density 0.094%

    No Known Activations