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

    Neuronpedia

    INDEX
    Explanations

    structural elements of programming syntax, such as parentheses and specific symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Keys
    -0.74
    transQ
    -0.68
    Keys
    -0.66
     Kicks
    -0.62
     Clues
    -0.59
    KEYS
    -0.59
     KEYS
    -0.58
     Nuc
    -0.57
     referrerpolicy
    -0.57
     Mains
    -0.56
    POSITIVE LOGITS
     key
    1.46
    key
    1.23
     ke
    0.74
    Key
    0.63
     Ke
    0.61
     Keith
    0.61
     king
    0.58
     Kevin
    0.58
     Key
    0.57
     rey
    0.55
    Act Density 0.190%

    No Known Activations