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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structure elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     =
    -0.18
     equals
    -0.17
     Pale
    -0.14
    altern
    -0.14
    ause
    -0.14
    aña
    -0.14
    ega
    -0.14
    :
    -0.14
    "go
    -0.13
    Lon
    -0.13
    POSITIVE LOGITS
    olan
    0.19
    ìĿ´ê³ł
    0.19
    /false
    0.16
    OrNil
    0.15
    ä¸Ķ
    0.15
    lander
    0.14
    URLException
    0.14
    abela
    0.13
    èĢĮ
    0.13
    лÑıв
    0.13
    Act Density 0.192%

    No Known Activations