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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or official documents and procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal issues and legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lu
    -0.92
     Patton
    -0.91
     Mos
    -0.90
     Zucker
    -0.86
     Buck
    -0.86
    âĺ
    -0.82
     Lep
    -0.82
    Lu
    -0.81
     Anton
    -0.79
     Cous
    -0.79
    POSITIVE LOGITS
    untu
    0.99
    escription
    0.90
    icals
    0.85
    ern
    0.85
    ARY
    0.85
    iam
    0.84
    itional
    0.83
    ãĤ³
    0.83
    ubuntu
    0.82
    ailability
    0.80
    Act Density 0.491%

    No Known Activations