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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to color theory and representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oux
    -0.18
    uko
    -0.17
    isko
    -0.16
     Clearance
    -0.15
    iphers
    -0.14
    ç©¿
    -0.14
    -BEGIN
    -0.14
    HH
    -0.14
    Ïģιο
    -0.14
    .TextAlignment
    -0.14
    POSITIVE LOGITS
     gam
    0.31
     Gam
    0.27
    gam
    0.25
     color
    0.24
     Color
    0.24
     primaries
    0.23
    709
    0.23
    Gam
    0.22
     chrom
    0.21
     ÎĶE
    0.21
    Act Density 0.027%

    No Known Activations