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

    Neuronpedia

    INDEX
    Explanations

    references to "rock" and "lock" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indd
    -0.54
     Wege
    -0.48
     inhoud
    -0.48
     alimentaire
    -0.47
     bı
    -0.47
    PathVariable
    -0.45
    inary
    -0.45
     carrying
    -0.45
    Blah
    -0.44
     Sonntag
    -0.44
    POSITIVE LOGITS
    Locks
    0.98
     Locks
    0.93
     locks
    0.92
     Lock
    0.85
     LOCK
    0.79
     lock
    0.77
     propOrder
    0.75
    LOCK
    0.75
    Personendaten
    0.74
     nahilalakip
    0.74
    Act Density 0.123%

    No Known Activations