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

    Neuronpedia

    INDEX
    Explanations

    references to a specific place or person named "Pers."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nz
    -0.76
    akespe
    -0.74
    llah
    -0.71
    BILL
    -0.70
    iannopoulos
    -0.68
    ctors
    -0.67
    Leod
    -0.67
    masters
    -0.66
    aneers
    -0.66
    yrinth
    -0.65
    POSITIVE LOGITS
    istence
    1.17
    istent
    1.09
    iments
    0.93
    pect
    0.91
    idence
    0.88
    erver
    0.88
     Pers
    0.87
    ipher
    0.84
    ervation
    0.84
    hing
    0.80
    Act Density 0.011%

    No Known Activations