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

    Neuronpedia

    INDEX
    Explanations

    recurrent phrases indicating repetition or continuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kano
    -0.93
     Hale
    -0.67
    \_\_
    -0.67
    tisseur
    -0.65
    vfs
    -0.65
     Koc
    -0.64
    ymal
    -0.63
     Lodi
    -0.62
     Purdy
    -0.62
     Hernando
    -0.61
    POSITIVE LOGITS
    TestingModule
    1.05
    AGAIN
    1.03
     Again
    1.00
    Again
    1.00
     AGAIN
    0.99
     again
    0.96
    jsdelivr
    0.90
    again
    0.89
     numberWith
    0.85
     Audiodateien
    0.84
    Act Density 0.058%

    No Known Activations