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

    Neuronpedia

    INDEX
    Explanations

    assertions about visual appeal and imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ìĹŃìĭľ
    -0.15
    ãģļ
    -0.15
    cket
    -0.15
     Yorker
    -0.15
     yine
    -0.14
     toujours
    -0.14
     Obviously
    -0.14
    esign
    -0.14
     siempre
    -0.14
     surtout
    -0.14
    POSITIVE LOGITS
     border
    0.30
     practically
    0.29
     almost
    0.29
     rival
    0.28
     literally
    0.27
     borders
    0.27
     nearly
    0.27
    border
    0.27
    almost
    0.25
     borderline
    0.25
    Act Density 0.246%

    No Known Activations