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

    Neuronpedia

    INDEX
    Explanations

    references to stone and its various uses or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.08
     himſelf
    -0.95
     themſelves
    -0.94
     myſelf
    -0.92
     Majefty
    -0.89
     unſ
    -0.88
     Cæsar
    -0.88
     bershka
    -0.84
     ſever
    -0.84
     fevere
    -0.84
    POSITIVE LOGITS
     Stone
    1.92
     stone
    1.86
    Stone
    1.83
    stone
    1.79
     STONE
    1.77
     stones
    1.72
     Stones
    1.64
    Stones
    1.60
    STONE
    1.53
    stones
    1.44
    Act Density 0.035%

    No Known Activations