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

    Neuronpedia

    INDEX
    Explanations

    statements made by political figures

    oai_token-act-pair · gpt-3.5-turbo

    quotes from notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mination
    -0.80
    otin
    -0.79
    vier
    -0.74
    Quality
    -0.73
    fet
    -0.69
    notations
    -0.69
    UTH
    -0.69
    uploads
    -0.67
    kn
    -0.67
    fur
    -0.67
    POSITIVE LOGITS
     sarcast
    1.03
     rhet
    0.95
     quoted
    0.85
     excerpts
    0.83
     passionately
    0.83
     referring
    0.82
     quoting
    0.82
     bluntly
    0.79
     scathing
    0.78
     addressing
    0.76
    Act Density 0.223%

    No Known Activations