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

    Neuronpedia

    INDEX
    Explanations

    technical terms and units related to measurements in physics or engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.77
     Sass
    -0.77
    flink
    -0.75
     Dede
    -0.73
     Weid
    -0.72
     Jefus
    -0.70
     BST
    -0.68
    ilaian
    -0.68
    انجليز
    -0.67
     Obre
    -0.67
    POSITIVE LOGITS
    mu
    2.22
     Mu
    1.98
     mu
    1.86
    Mu
    1.86
     μ
    1.86
    μ
    1.72
     µ
    1.39
    MU
    1.34
     mutagen
    1.30
     MU
    1.28
    Act Density 0.170%

    No Known Activations