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

    Neuronpedia

    INDEX
    Explanations

    legal and political terms and information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pty
    -0.72
    tnc
    -0.71
    vier
    -0.68
     Chaser
    -0.66
     Canaver
    -0.65
    ¾
    -0.65
    arium
    -0.63
    ious
    -0.62
     Machina
    -0.62
    okemon
    -0.59
    POSITIVE LOGITS
     levels
    1.05
     altitude
    1.03
     stakes
    1.00
     priced
    0.96
     earners
    0.92
     concentrations
    0.92
    lighting
    0.91
     ceilings
    0.90
     level
    0.89
     pitched
    0.89
    Act Density 2.990%

    No Known Activations