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

    Neuronpedia

    INDEX
    Explanations

    legal or official notices

    oai_token-act-pair · gpt-3.5-turbo

    references to formal notifications or alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UES
    -0.75
    ECD
    -0.72
    rina
    -0.72
    Export
    -0.70
    EVA
    -0.68
    UFF
    -0.66
    âĹ¼
    -0.64
     recess
    -0.64
    UE
    -0.63
    Unity
    -0.63
    POSITIVE LOGITS
     notices
    0.89
    andum
    0.89
    isance
    0.88
    orial
    0.87
     notice
    0.85
    lessly
    0.85
    lessness
    0.80
    eming
    0.80
    abl
    0.79
    taker
    0.77
    Act Density 0.016%

    No Known Activations