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

    Neuronpedia

    INDEX
    Explanations

    names of specific geographical locations and political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations or regional identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    notation
    -0.84
    naissance
    -0.82
    ©¶æ
    -0.82
    vernment
    -0.79
    phrine
    -0.74
    gee
    -0.69
    claimed
    -0.68
    ERC
    -0.68
    ZA
    -0.68
    notations
    -0.67
    POSITIVE LOGITS
    sburgh
    1.06
    inx
    0.98
    onia
    0.93
    sburg
    0.85
    ydia
    0.82
    aji
    0.81
    enger
    0.78
    downs
    0.78
    antine
    0.76
    uci
    0.74
    Act Density 0.053%

    No Known Activations