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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a repeated action or comparison with previous instances

    oai_token-act-pair · gpt-3.5-turbo

    references to the phrase "this time around."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haar
    -0.78
    Room
    -0.77
    Lenin
    -0.69
    verified
    -0.68
    rw
    -0.66
    pload
    -0.65
    Cho
    -0.64
    Shares
    -0.64
    ynt
    -0.63
    pee
    -0.63
    POSITIVE LOGITS
    iatus
    0.73
     ignition
    0.71
    otiation
    0.69
     Nieto
    0.69
     ..........
    0.68
     Seym
    0.66
    quickShipAvailable
    0.65
     solicitation
    0.61
     revocation
    0.61
     festivities
    0.61
    Act Density 0.048%

    No Known Activations