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

    Neuronpedia

    INDEX
    Explanations

    statements related to controversy or contentious situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palest
    -0.83
    Buyable
    -0.78
     guiActiveUnfocused
    -0.69
    è£ħ
    -0.69
    çīĪ
    -0.69
     RAD
    -0.67
    ãĤ¬
    -0.66
    Interstitial
    -0.65
    Desk
    -0.63
     Circus
    -0.63
    POSITIVE LOGITS
    £
    1.00
    ¼
    0.95
    º
    0.94
    ¿
    0.91
    Ń
    0.91
    ¢
    0.91
    ¤
    0.91
    Ķ
    0.89
    ĸ
    0.87
    ¬
    0.87
    Act Density 1.422%

    No Known Activations