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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to financial figures or statistics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.87
    fire
    -0.75
    Fire
    -0.71
    BRE
    -0.71
     Leilan
    -0.67
    hedon
    -0.66
     Bene
    -0.65
    ensional
    -0.65
    ctrl
    -0.64
    Bee
    -0.64
    POSITIVE LOGITS
    %]
    1.02
    %-
    0.95
    %"
    0.93
    %;
    0.93
     percent
    0.93
    %)
    0.92
     yards
    0.91
    %:
    0.89
    percent
    0.88
    %
    0.86
    Act Density 5.981%

    No Known Activations