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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical entities or relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to the U.S. in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mermaid
    -0.69
     TAMADRA
    -0.67
     Feather
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.65
     Madden
    -0.65
     Vapor
    -0.64
    osaurs
    -0.64
     PRO
    -0.63
     McGr
    -0.63
     LOT
    -0.62
    POSITIVE LOGITS
    taboola
    1.18
    based
    1.07
    division
    1.04
    themed
    1.01
    dep
    0.96
    interstitial
    0.95
    facing
    0.92
    imposed
    0.91
    san
    0.91
    induced
    0.90
    Act Density 0.013%

    No Known Activations