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

    Neuronpedia

    INDEX
    Explanations

    references to judgment or legal decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gem
    -0.16
    yne
    -0.15
    alion
    -0.15
    ei
    -0.14
    alo
    -0.14
    lg
    -0.14
    ugo
    -0.14
    cho
    -0.13
     fus
    -0.13
    alim
    -0.13
    POSITIVE LOGITS
     certain
    0.15
    æŁIJ
    0.14
     Certain
    0.14
    otti
    0.13
    vida
    0.13
    Ñīин
    0.13
    rics
    0.13
     brass
    0.12
    ysi
    0.12
     мÑıÑģ
    0.12
    Act Density 2.765%

    No Known Activations