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

    Neuronpedia

    INDEX
    Explanations

    numerical values and variables, especially in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.82
    ſelves
    -0.69
     Romains
    -0.65
    ifrance
    -0.63
    HasForeignKey
    -0.62
     renovables
    -0.61
    tonode
    -0.61
    couvrez
    -0.60
     Jefus
    -0.60
    ſelf
    -0.59
    POSITIVE LOGITS
     intptr
    0.56
    alain
    0.51
    ingin
    0.51
    陣
    0.51
     ber
    0.51
    fett
    0.50
     bask
    0.50
     bas
    0.50
    CUR
    0.50
    ью
    0.50
    Act Density 1.698%

    No Known Activations