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

    Neuronpedia

    INDEX
    Explanations

    the word "lock" or its variations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     virtuel
    -0.55
     radikal
    -0.55
     karton
    -0.52
    comfor
    -0.51
    diyah
    -0.50
     vorrei
    -0.50
     bisogna
    -0.49
     vogliamo
    -0.48
     Heeren
    -0.48
     koz
    -0.48
    POSITIVE LOGITS
     lock
    1.35
     locks
    1.29
     Lock
    1.22
     locking
    1.20
    lock
    1.19
     locked
    1.18
    Lock
    1.09
    locks
    1.09
    locked
    1.08
     LOCK
    1.05
    Act Density 0.062%

    No Known Activations