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

    Neuronpedia

    INDEX
    Explanations

    references to cats or cat-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orer
    -0.19
    steen
    -0.18
    ourt
    -0.17
    gaard
    -0.17
     Atmos
    -0.17
    ureka
    -0.16
     Citadel
    -0.16
    hl
    -0.16
    icana
    -0.15
    iola
    -0.15
    POSITIVE LOGITS
    apult
    0.33
    égorie
    0.29
    nip
    0.28
    fish
    0.23
    elog
    0.21
    amar
    0.20
    enary
    0.20
    amount
    0.20
    ting
    0.20
    walk
    0.20
    Act Density 0.014%

    No Known Activations