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

    Neuronpedia

    INDEX
    Explanations

    keys and key-related terms in code contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſeveral
    -1.34
     Theſe
    -1.32
     themſelves
    -1.32
     itſelf
    -1.27
     myſelf
    -1.26
     whoſe
    -1.26
     ―――――
    -1.22
     Anſ
    -1.18
     becauſe
    -1.18
     greateſt
    -1.17
    POSITIVE LOGITS
     keys
    1.90
    key
    1.70
     key
    1.68
     Keys
    1.66
    keys
    1.61
     KEY
    1.58
    KEY
    1.58
     Key
    1.57
    Keys
    1.43
     KEYS
    1.43
    Act Density 0.036%

    No Known Activations