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

    Neuronpedia

    INDEX
    Explanations

    personal messages and expressions for sharing thoughts or experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement or enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Laden
    -0.69
     automobile
    -0.69
     ÂŃ
    -0.66
     Saddam
    -0.63
     Rodham
    -0.62
    ASHINGTON
    -0.62
    utterstock
    -0.61
     automobiles
    -0.61
     Communists
    -0.60
    quet
    -0.60
    POSITIVE LOGITS
     haha
    1.15
     alot
    1.05
     ;)
    1.04
     :)
    1.03
     XD
    0.98
     english
    0.94
     lol
    0.92
     kinda
    0.91
     devs
    0.91
     youtube
    0.91
    Act Density 1.993%

    No Known Activations