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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating temporal sequence or order

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time or sequential events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Policy
    -0.74
    bill
    -0.73
    alth
    -0.72
    opian
    -0.71
    Federal
    -0.70
    payer
    -0.70
    onym
    -0.70
    insula
    -0.70
    ument
    -0.68
    olitical
    -0.67
    POSITIVE LOGITS
     teammate
    1.14
     halftime
    1.07
     averaging
    1.00
    juries
    1.00
     teammates
    0.97
     Jere
    0.95
     rookies
    0.93
     Reggie
    0.92
     Kyle
    0.92
     finishing
    0.90
    Act Density 0.223%

    No Known Activations