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

    Neuronpedia

    INDEX
    Explanations

    references to causality and the interconnectedness of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynchronously
    -0.17
     Bowman
    -0.16
    966
    -0.15
     Robertson
    -0.15
     Drinking
    -0.14
    leen
    -0.14
    baz
    -0.14
    iá»ģn
    -0.14
    icamente
    -0.14
     Wir
    -0.14
    POSITIVE LOGITS
    amb
    0.15
    uis
    0.15
     å¾ĴæŃ©
    0.15
    iture
    0.14
    ulo
    0.14
    uppies
    0.14
    anvas
    0.14
     Remaining
    0.14
    igate
    0.14
    kara
    0.14
    Act Density 0.285%

    No Known Activations