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

    Neuronpedia

    INDEX
    Explanations

    single words with a special character associated with them

    oai_token-act-pair · gpt-3.5-turbo

    unique identifiers or symbols associated with specific topics or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     blacks
    -0.82
     Blacks
    -0.71
     creditors
    -0.67
     retirees
    -0.66
     miscar
    -0.65
     UD
    -0.64
     Arabs
    -0.64
     lots
    -0.64
     partners
    -0.64
     peanuts
    -0.63
    POSITIVE LOGITS
    framework
    1.02
    thing
    1.01
    formation
    1.00
    entity
    0.99
    issance
    0.98
    ï¸ı
    0.97
    expression
    0.97
    factor
    0.97
    ship
    0.96
    cation
    0.94
    Act Density 0.233%

    No Known Activations