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

    Neuronpedia

    INDEX
    Explanations

    numerical values representing monetary amounts

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dos
    -0.87
     Hoff
    -0.69
    assetsadobe
    -0.67
     observ
    -0.66
     punishable
    -0.63
     recorder
    -0.63
     Nib
    -0.61
     nonviolent
    -0.61
     resur
    -0.61
     recomp
    -0.61
    POSITIVE LOGITS
    %
    2.25
    %,
    2.05
    %"
    1.98
    %.
    1.96
    %;
    1.95
    %-
    1.94
    %:
    1.87
    %)
    1.85
    %).
    1.84
    %),
    1.74
    Act Density 0.085%

    No Known Activations