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

    Neuronpedia

    INDEX
    Explanations

    references to locks and locking mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bevan
    -0.80
    Portale
    -0.78
     normaux
    -0.73
    windigkeit
    -0.72
    twimg
    -0.72
     delà
    -0.72
     esempi
    -0.71
    isiaj
    -0.71
    BGP
    -0.70
    itant
    -0.69
    POSITIVE LOGITS
     LOCK
    1.54
     locks
    1.53
     lock
    1.52
    Locks
    1.50
     Lock
    1.48
     Locks
    1.48
    locks
    1.37
    lock
    1.36
    LOCK
    1.34
     locked
    1.32
    Act Density 0.086%

    No Known Activations