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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aston
    -0.16
    æŁı
    -0.15
    enburg
    -0.15
    ÛĮدا
    -0.13
     BaÄŁ
    -0.13
    essim
    -0.13
    Nuevo
    -0.13
    .Spring
    -0.13
    asics
    -0.13
    IXEL
    -0.13
    POSITIVE LOGITS
     Ok
    0.36
     Ry
    0.28
    æ²ĸ
    0.26
     ok
    0.25
    Ok
    0.24
    .ok
    0.23
    -ok
    0.21
     OK
    0.21
     çIJ
    0.21
     island
    0.21
    Act Density 0.006%

    No Known Activations