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
     varandra
    -0.86
     normaux
    -0.83
     réaliste
    -0.83
     flesta
    -0.82
     rendus
    -0.81
     Bevan
    -0.81
    Portale
    -0.81
    windigkeit
    -0.79
     tilbage
    -0.79
     esempi
    -0.79
    POSITIVE LOGITS
     lock
    1.54
     LOCK
    1.52
     locks
    1.51
     Lock
    1.51
     Locks
    1.48
    Locks
    1.48
    locks
    1.33
    lock
    1.32
     Lockwood
    1.31
    LOCK
    1.30
    Act Density 0.073%

    No Known Activations