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

    Neuronpedia

    INDEX
    Explanations

    references to temperature values

    oai_token-act-pair · gpt-3.5-turbo

    references to temperature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.78
    lihood
    -0.76
     Scotia
    -0.76
     Barkley
    -0.70
    ãģį
    -0.67
    Magikarp
    -0.65
    ION
    -0.63
     Newfoundland
    -0.61
     Tav
    -0.61
     Explorer
    -0.60
    POSITIVE LOGITS
    porary
    1.48
    poral
    1.28
    pered
    1.22
    perate
    1.21
    perature
    1.15
    plates
    1.14
    ples
    1.13
    pering
    1.11
    ension
    1.08
    erity
    1.04
    Act Density 0.015%

    No Known Activations