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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "OK" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.94
     neceff
    -0.91
     reaſon
    -0.90
     ſtate
    -0.87
     myſelf
    -0.86
     juſ
    -0.85
     poffible
    -0.85
     Monfieur
    -0.83
     pleaſure
    -0.83
     fubject
    -0.82
    POSITIVE LOGITS
     shorter
    1.05
     smaller
    1.01
     lesser
    0.81
    smaller
    0.72
     Smaller
    0.70
     lower
    0.66
     bag
    0.65
    Smaller
    0.64
     pat
    0.61
     Shorter
    0.58
    Act Density 0.149%

    No Known Activations