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

    Neuronpedia

    INDEX
    Explanations

    French words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to dysregulation and accentuation in language or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.76
    ously
    -0.75
    osite
    -0.70
    aneously
    -0.68
    omaly
    -0.66
     Tong
    -0.63
    RAY
    -0.62
     Lime
    -0.60
    ocene
    -0.58
    eland
    -0.58
    POSITIVE LOGITS
    izoph
    1.02
    regulated
    0.84
    dain
    0.84
    irable
    0.83
    regulation
    0.78
    ivery
    0.76
    ept
    0.75
    ré
    0.73
    sum
    0.73
    rift
    0.71
    Act Density 0.048%

    No Known Activations