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

    Neuronpedia

    INDEX
    Explanations

    names of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly the name "Ahmad."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropri
    -0.73
    Frame
    -0.70
    Corp
    -0.67
     se
    -0.66
     frame
    -0.66
     Frame
    -0.62
    Seg
    -0.61
     conj
    -0.60
     po
    -0.60
     meta
    -0.59
    POSITIVE LOGITS
     Ahmad
    3.88
     Ahmed
    1.98
     Mahmoud
    1.71
     Mohammad
    1.67
     Mahm
    1.54
     Abbas
    1.52
     Muhammad
    1.52
     Mohamed
    1.49
     Imam
    1.48
     Malik
    1.47
    Act Density 0.014%

    No Known Activations