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

    Neuronpedia

    INDEX
    Explanations

    keywords and function definitions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -1.25
     “
    -1.10
    ["
    -0.95
     „
    -0.93
     ["
    -0.90
    ，“
    -0.87
     «
    -0.84
     ".
    -0.84
    。「
    -0.84
    「
    -0.84
    POSITIVE LOGITS
    ()
    1.28
    (){
    1.26
    (){
    1.15
    (){}
    1.07
     (){
    1.05
     ()
    0.97
    ():
    0.97
    _()
    0.96
    ()
    0.94
    }()
    0.89
    Act Density 0.212%

    No Known Activations