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

    Neuronpedia

    INDEX
    Explanations

    languages

    oai_token-act-pair · gpt-3.5-turbo

    references to various nationalities and foods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.48
    irements
    -0.47
    cca
    -0.47
    abis
    -0.46
    ËĪ
    -0.45
    æ©Ł
    -0.45
    vt
    -0.44
    alse
    -0.44
    gru
    -0.43
    çīĪ
    -0.42
    POSITIVE LOGITS
    ))))
    0.66
    '."
    0.64
    .''.
    0.61
    ]."
    0.61
    .'"
    0.60
     guiName
    0.60
    )).
    0.57
     respectively
    0.56
     etc
    0.56
     };
    0.55
    Act Density 1.848%

    No Known Activations