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

    Neuronpedia

    INDEX
    Explanations

    dates, quantities, and estimations

    oai_token-act-pair · gpt-3.5-turbo

    words related to reporting, estimating, and revealing information or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ROM
    -0.78
    picture
    -0.74
    avorite
    -0.74
    isode
    -0.73
    uga
    -0.72
    apes
    -0.67
    otype
    -0.66
    pak
    -0.65
    orio
    -0.65
    Exit
    -0.65
    POSITIVE LOGITS
     arg
    0.69
     Eth
    0.66
     unanimously
    0.65
     electr
    0.64
     Engels
    0.63
     ¶
    0.63
     contention
    0.62
     ICO
    0.61
     contended
    0.60
     orally
    0.59
    Act Density 0.096%

    No Known Activations