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

    Neuronpedia

    INDEX
    Explanations

    words related to locations, especially with the letter 'q'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'q'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.71
     Oblivion
    -0.66
     ESA
    -0.64
     Eclipse
    -0.64
    ographically
    -0.62
     lav
    -0.62
     savior
    -0.61
     readable
    -0.60
     chronological
    -0.60
     Turing
    -0.60
    POSITIVE LOGITS
    aeda
    1.02
    eus
    0.97
    iao
    0.94
    iu
    0.92
    edo
    0.90
    lling
    0.89
    dn
    0.89
    rt
    0.87
    akening
    0.86
    arth
    0.86
    Act Density 0.021%

    No Known Activations