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

    Neuronpedia

    INDEX
    Explanations

    mentions of large quantities or volumes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating large quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doodle
    -0.72
     Frontier
    -0.72
    inav
    -0.67
    inates
    -0.66
     Commissioners
    -0.65
    ©¶æ
    -0.63
     Till
    -0.60
    iners
    -0.60
     Carnival
    -0.59
    inelli
    -0.59
    POSITIVE LOGITS
     of
    0.92
     (>
    0.88
     amount
    0.88
     amounts
    0.87
    pour
    0.83
     (~
    0.78
    ngth
    0.78
     quantities
    0.76
    UID
    0.68
     quantity
    0.68
    Act Density 0.026%

    No Known Activations