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

    Neuronpedia

    INDEX
    Explanations

    terms related to locking mechanisms and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.97
     fantasmas
    -0.69
    thâu
    -0.66
     betweenstory
    -0.65
    berikut
    -0.63
     ujednoznacz
    -0.60
    hibli
    -0.60
    isateur
    -0.60
    äler
    -0.60
     parlant
    -0.59
    POSITIVE LOGITS
     Locks
    1.38
     locks
    1.31
    Locks
    1.31
     LOCK
    1.23
     Lock
    1.23
     lock
    1.19
    LOCK
    1.12
    lock
    1.11
    locks
    1.09
    Lock
    1.05
    Act Density 0.088%

    No Known Activations