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

    Neuronpedia

    INDEX
    Explanations

    references to the city of Tokyo in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the end of sequences or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.92
    edly
    -0.82
    theless
    -0.76
    stones
    -0.74
    icularly
    -0.71
     Lynd
    -0.71
    dule
    -0.71
    hetically
    -0.69
    guard
    -0.69
    drivers
    -0.67
    POSITIVE LOGITS
    ichi
    1.03
    jin
    1.00
    imura
    0.96
    ji
    0.88
    ya
    0.88
    pport
    0.87
     yen
    0.85
    amaru
    0.84
    etsu
    0.84
    pta
    0.84
    Act Density 0.062%

    No Known Activations