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

    Neuronpedia

    INDEX
    Explanations

    references to key-value pairs and key management in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſeveral
    -1.13
     Theſe
    -1.08
     themſelves
    -1.08
     becauſe
    -0.98
     itſelf
    -0.97
     myſelf
    -0.96
     greateſt
    -0.96
     whoſe
    -0.94
     inſ
    -0.93
     ſuch
    -0.91
    POSITIVE LOGITS
     keys
    1.84
     Keys
    1.61
    keys
    1.58
    key
    1.50
    Keys
    1.40
    KEY
    1.39
     key
    1.38
     KEYS
    1.37
     KEY
    1.35
     Key
    1.33
    Act Density 0.051%

    No Known Activations