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

    Neuronpedia

    INDEX
    Explanations

    words related to importance or priority

    oai_token-act-pair · gpt-3.5-turbo

    words related to primary or principal concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erved
    -0.88
    paio
    -0.83
    apons
    -0.80
    azel
    -0.79
    agra
    -0.79
    erves
    -0.77
    attery
    -0.77
    fy
    -0.77
    ossession
    -0.77
    utics
    -0.75
    POSITIVE LOGITS
     culprit
    1.06
     theme
    0.96
     reason
    0.94
     proponent
    0.91
     difference
    0.87
     objective
    0.86
     exception
    0.85
     source
    0.84
     thing
    0.83
     question
    0.83
    Act Density 0.126%

    No Known Activations