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

    Neuronpedia

    INDEX
    Explanations

    Twitter usernames and handles

    oai_token-act-pair · gpt-3.5-turbo

    words and symbols related to sports events and performance statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FG
    -0.86
    aki
    -0.84
     CSI
    -0.81
     Nicholas
    -0.81
    icator
    -0.80
     KN
    -0.80
    slice
    -0.79
     Cra
    -0.78
     empt
    -0.77
     Chaser
    -0.76
    POSITIVE LOGITS
    MET
    0.99
     Metro
    0.89
    Metro
    0.88
    ord
    0.87
    roy
    0.87
    har
    0.87
    imore
    0.86
     Palestin
    0.86
    MAR
    0.84
    android
    0.84
    Act Density 0.406%

    No Known Activations