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

    Neuronpedia

    INDEX
    Explanations

    differences or contrasts between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of phrases that contrast different subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ragon
    -0.67
    é¾įå¥ij士
    -0.67
    amaz
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
    è¦ļéĨĴ
    -0.64
    cloneembedreportprint
    -0.61
    ãĤ´ãĥ³
    -0.61
     exting
    -0.60
    Associated
    -0.60
     redes
    -0.60
    POSITIVE LOGITS
     however
    1.00
     which
    0.96
     whose
    0.89
     wherein
    0.83
     ours
    0.81
     whom
    0.81
     though
    0.79
     there
    0.78
     where
    0.73
     whereby
    0.71
    Act Density 0.118%

    No Known Activations