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

    Neuronpedia

    INDEX
    Explanations

    words related to computer science and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    advertising and promotional language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oft
    -0.92
    Aren
    -0.88
    Extra
    -0.87
    Reloaded
    -0.85
    recomm
    -0.84
    DragonMagazine
    -0.81
    Adds
    -0.81
    Gene
    -0.80
    Org
    -0.79
    CVE
    -0.79
    POSITIVE LOGITS
     e
    0.87
     ¯
    0.84
     SECTION
    0.80
     {\
    0.74
     ,
    0.72
     SPACE
    0.71
     PAY
    0.70
     ]
    0.69
     )))
    0.69
     !
    0.68
    Act Density 0.083%

    No Known Activations