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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols in contextual discussions of equations and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.83
    MLLoader
    -0.83
    GIVEREF
    -0.82
     pylint
    -0.82
    
    -0.82
    ſelf
    -0.81
     ་་
    -0.78
    ^(@)
    -0.78
     unſ
    -0.76
     protoimpl
    -0.76
    POSITIVE LOGITS
    {
    0.90
     {
    0.76
     
    0.54
     R
    0.53
     A
    0.53
    }^
    0.52
    {
    0.52
     W
    0.52
    <eos>
    0.52
     B
    0.51
    Act Density 1.507%

    No Known Activations