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

    Neuronpedia

    INDEX
    Explanations

    city names in the format of "City, State."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ovic
    -0.71
    DragonMagazine
    -0.70
    erity
    -0.66
    ebook
    -0.66
    staking
    -0.66
    metadata
    -0.61
    expensive
    -0.61
     stewards
    -0.59
    isine
    -0.58
    ahime
    -0.58
    POSITIVE LOGITS
    Y
    0.93
    C
    0.84
     Korea
    0.82
    J
    0.78
    D
    0.76
    Ireland
    0.74
    Ire
    0.73
    S
    0.73
    K
    0.72
    M
    0.71
    Act Density 0.017%

    No Known Activations