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

    Neuronpedia

    INDEX
    Explanations

    specific names related to health conditions or medications

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to people or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Katy
    -0.72
     caller
    -0.70
    UME
    -0.70
    ãģĦ
    -0.69
     PLAN
    -0.69
     Quit
    -0.69
     GOODMAN
    -0.67
     balloons
    -0.65
     Kessler
    -0.64
     Gallup
    -0.63
    POSITIVE LOGITS
     Duc
    1.44
    aido
    0.92
    rative
    0.92
    otom
    0.88
    ione
    0.85
    hene
    0.81
    ros
    0.81
    fen
    0.80
    aux
    0.80
    roman
    0.79
    Act Density 0.007%

    No Known Activations