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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing examples or illustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illa
    -0.18
    illas
    -0.17
    baugh
    -0.16
    ÃľRK
    -0.16
    UNET
    -0.15
    âĪı
    -0.15
    Mappings
    -0.14
    agon
    -0.14
    ÑīÑij
    -0.14
    .Ui
    -0.14
    POSITIVE LOGITS
    ores
    0.17
    eldo
    0.14
     Olympics
    0.14
    casting
    0.14
    cla
    0.13
     Olympic
    0.13
    erot
    0.13
    w
    0.13
     spoiler
    0.13
    λικ
    0.13
    Act Density 0.028%

    No Known Activations