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

    Neuronpedia

    INDEX
    Explanations

    concepts related to linearity and linear models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فرو
    -0.35
     pihak
    -0.34
     tiết
    -0.34
    uti
    -0.34
    обще
    -0.33
    Ủ
    -0.33
    aa
    -0.33
    haal
    -0.32
    lott
    -0.32
    mart
    -0.32
    POSITIVE LOGITS
     linear
    0.91
     Linear
    0.85
    linear
    0.84
     LINEAR
    0.83
    Linear
    0.81
     liné
    0.79
    LINEAR
    0.68
     فريبيس
    0.64
    线性
    0.64
     linearity
    0.59
    Act Density 0.247%

    No Known Activations