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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "lock" and its associated meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.56
     ModelExpression
    -0.56
    Personensuche
    -0.50
     צילום
    -0.49
    setVerticalGroup
    -0.48
     Gerald
    -0.47
    +};
    -0.47
    .*")]
    -0.47
    istoitu
    -0.46
     spared
    -0.44
    POSITIVE LOGITS
     Lock
    0.89
     lock
    0.87
    Lock
    0.84
     LOCK
    0.84
     locks
    0.79
     locked
    0.75
     Locked
    0.75
    lock
    0.75
     Locks
    0.74
     locking
    0.73
    Act Density 0.129%

    No Known Activations