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

    Neuronpedia

    INDEX
    Explanations

    references to educational institutions and related structures or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Francois
    -0.17
     before
    -0.16
     Rene
    -0.15
     Orleans
    -0.15
     monet
    -0.15
     Napoleon
    -0.14
     rather
    -0.14
    iere
    -0.14
     adulti
    -0.14
    jerne
    -0.14
    POSITIVE LOGITS
     pour
    0.30
     et
    0.24
     sur
    0.24
     dans
    0.24
     le
    0.24
     qui
    0.23
     dont
    0.23
     ou
    0.23
     «
    0.22
     avec
    0.22
    Act Density 0.568%

    No Known Activations