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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to mathematical modeling and derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    b
    -0.49
     הב
    -0.44
    ƅ
    -0.43
    bat
    -0.41
    ble
    -0.41
    bre
    -0.41
    Ƅ
    -0.40
    ｂ
    -0.40
    bur
    -0.40
    bla
    -0.40
    POSITIVE LOGITS
     Bu
    0.85
     Bi
    0.83
     Be
    0.83
     Bio
    0.81
     BB
    0.81
     Բ
    0.81
     Bo
    0.79
     BI
    0.79
     Bin
    0.79
     Бу
    0.79
    Act Density 0.905%

    No Known Activations