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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures or events related to a specific region

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific term or name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wi
    -0.70
     predetermined
    -0.70
     cloud
    -0.69
     spectrum
    -0.68
     STD
    -0.68
     microw
    -0.65
     field
    -0.64
     Thu
    -0.63
     bytes
    -0.63
     scratch
    -0.62
    POSITIVE LOGITS
    ador
    4.78
    ados
    1.21
    ado
    1.15
    ad
    1.05
    ada
    1.05
    atorial
    1.03
    uno
    1.02
    amura
    1.02
    istar
    1.00
    ando
    0.98
    Act Density 0.015%

    No Known Activations