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

    Neuronpedia

    INDEX
    Explanations

    time-related information, such as hours and prices

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mash
    -0.73
     Jem
    -0.68
     RT
    -0.68
     ha
    -0.66
     Soldiers
    -0.64
     diverse
    -0.64
     veh
    -0.63
     tolerant
    -0.63
     mixed
    -0.62
     CT
    -0.62
    POSITIVE LOGITS
    5
    1.07
    25
    1.07
    3
    1.06
    8
    1.03
    4
    1.02
    26
    1.01
    6
    0.99
    35
    0.99
    16
    0.99
    15
    0.98
    Act Density 0.033%

    No Known Activations