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

    Neuronpedia

    INDEX
    Explanations

    words related to tracking and monitoring activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "tr" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELS
    -0.81
    manship
    -0.70
     Mechdragon
    -0.68
     Aman
    -0.66
    ãģ®éŃĶ
    -0.65
     Pigs
    -0.63
     arts
    -0.62
     Cheong
    -0.61
    cook
    -0.61
     Grande
    -0.61
    POSITIVE LOGITS
    ainer
    1.25
    ains
    1.08
    ained
    1.07
    unks
    1.02
    acker
    1.02
    icker
    1.02
    ayer
    1.00
    unk
    0.99
    udeau
    0.98
    acement
    0.97
    Act Density 0.014%

    No Known Activations