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

    Neuronpedia

    INDEX
    Explanations

    direct speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -1.14
     ―――――
    -1.06
    ſelves
    -1.04
     $_"
    -1.02
    verwijspagina
    -1.02
     itſelf
    -1.01
     Efq
    -1.00
     Majefty
    -0.97
     ſind
    -0.96
    )";
    -0.94
    POSITIVE LOGITS
     "
    0.88
     “
    0.84
    “
    0.73
    <eos>
    0.72
     I
    0.69
    .
    0.68
    '
    0.67
     '
    0.66
    ,"
    0.65
    "
    0.65
    Act Density 0.048%

    No Known Activations