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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data and analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Room
    -0.65
    issner
    -0.64
     Borden
    -0.61
    மைய
    -0.60
    Room
    -0.58
    hbox
    -0.58
     hotell
    -0.58
     برانيه
    -0.57
     mest
    -0.57
     aukš
    -0.57
    POSITIVE LOGITS
     statistics
    1.34
     stats
    1.30
     stat
    1.17
     statistic
    1.17
     Stats
    1.13
     STATS
    1.11
    stats
    1.11
    Statistics
    1.11
     Statistics
    1.11
    STATS
    1.10
    Act Density 0.159%

    No Known Activations