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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses and quotations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ož
    -0.17
    however
    -0.15
     Fulton
    -0.15
    ÄĽn
    -0.15
    ighth
    -0.15
    enas
    -0.14
    erece
    -0.14
    ALLERY
    -0.14
    IGHL
    -0.14
    ucas
    -0.14
    POSITIVE LOGITS
    oret
    0.20
    ÑĢави
    0.15
     Nationals
    0.14
    oley
    0.13
    etat
    0.13
     reason
    0.13
     ?><?
    0.13
     wards
    0.13
     lack
    0.13
     flesh
    0.13
    Act Density 0.118%

    No Known Activations