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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating statistical evaluation or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    is
    -0.17
     wherever
    -0.14
    if
    -0.14
     Downing
    -0.14
    ro
    -0.14
     ro
    -0.14
    jobs
    -0.14
    rite
    -0.13
    at
    -0.13
     strip
    -0.13
    POSITIVE LOGITS
    enderit
    0.16
    BoxLayout
    0.16
    ëĵľë¦¬
    0.16
    aska
    0.15
    ÃŃž
    0.14
    LOB
    0.14
    ÅĻeb
    0.14
    avl
    0.14
    оÑĩка
    0.14
    å¥Ķ
    0.14
    Act Density 0.074%

    No Known Activations