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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to mathematical definitions and principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     d
    -1.09
    d
    -0.93
    ⅾ
    -0.75
    ԁ
    -0.74
     propOrder
    -0.72
    Ԁ
    -0.71
    ｄ
    -0.69
    ɗ
    -0.64
     da
    -0.63
     du
    -0.60
    POSITIVE LOGITS
     De
    0.86
     Dir
    0.81
     Ди
    0.79
     Де
    0.78
     Do
    0.77
     Dia
    0.77
     Di
    0.77
    Ｄ
    0.76
     До
    0.75
     Dy
    0.74
    Act Density 2.488%

    No Known Activations