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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to locks and locking mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bakgrund
    -0.66
     varandra
    -0.66
     själva
    -0.64
     razonable
    -0.63
     gră
    -0.63
     esportivo
    -0.63
     készült
    -0.62
     móg
    -0.60
     căr
    -0.60
     gammal
    -0.60
    POSITIVE LOGITS
     lock
    3.79
     Lock
    3.60
    lock
    3.54
     LOCK
    3.35
    Lock
    3.33
     locks
    3.31
    LOCK
    3.13
    locks
    2.94
     Locks
    2.90
     locking
    2.84
    Act Density 0.023%

    No Known Activations