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

    Neuronpedia

    INDEX
    Explanations

    lines ending with unusual characters (such as Ċ followed by a number)

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to news and reporting structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brandon
    -0.65
     Double
    -0.63
     Cho
    -0.62
     Deity
    -0.61
     Wrong
    -0.61
     Bowman
    -0.60
     Reincarnated
    -0.59
     Vaughn
    -0.59
     Badge
    -0.58
     rave
    -0.58
    POSITIVE LOGITS
    ccording
    0.88
    ERROR
    0.75
    WAR
    0.75
    Britain
    0.74
    Econom
    0.73
    Iraq
    0.72
    BBC
    0.72
    Prime
    0.71
     Sabha
    0.70
    Pakistan
    0.70
    Act Density 0.097%

    No Known Activations