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

    Neuronpedia

    INDEX
    Explanations

    mentions of trademarked or brand names

    oai_token-act-pair · gpt-3.5-turbo

    a specific type of character or symbol that appears frequently in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deepening
    -0.79
     mutually
    -0.77
     logger
    -0.72
     yield
    -0.71
     mathemat
    -0.71
     prominently
    -0.69
     accumulating
    -0.68
     advis
    -0.68
     fortun
    -0.67
     nurturing
    -0.66
    POSITIVE LOGITS
    ï¸ı
    1.32
    ski
    1.21
    tsy
    1.04
    ship
    1.00
    s
    0.98
    iversary
    0.95
    ufact
    0.93
    kay
    0.90
    sky
    0.90
    tal
    0.89
    Act Density 0.179%

    No Known Activations