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

    Neuronpedia

    INDEX
    Explanations

    references to community engagement and promotional efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hat
    -0.16
    Hat
    -0.15
     Hat
    -0.15
     Tar
    -0.14
     presentation
    -0.14
    iae
    -0.14
    iagnostics
    -0.14
    woke
    -0.14
     Presentation
    -0.14
    Presentation
    -0.14
    POSITIVE LOGITS
     addCriterion
    0.17
    ajo
    0.17
    ensi
    0.15
     Dish
    0.15
    (éĩij
    0.14
    entes
    0.14
    uilt
    0.14
    231
    0.14
    ugar
    0.14
    auss
    0.14
    Act Density 0.022%

    No Known Activations