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

    Neuronpedia

    INDEX
    Explanations

    statements asserting the existence or presence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĤ£äºĽ
    -0.17
     few
    -0.16
     všechny
    -0.15
    λικά
    -0.14
     chúng
    -0.14
    ucc
    -0.14
     two
    -0.14
    itol
    -0.14
     ÑįÑĤи
    -0.14
     headaches
    -0.13
    POSITIVE LOGITS
     room
    0.23
     evidence
    0.20
     spou
    0.20
     talk
    0.20
     footage
    0.16
     ROOM
    0.16
     variability
    0.15
     mention
    0.15
     Room
    0.15
     plenty
    0.15
    Act Density 0.107%

    No Known Activations