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

    Neuronpedia

    INDEX
    Explanations

    locations or proper nouns containing the letters "Ki"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names associated with individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.86
    worthiness
    -0.78
    theless
    -0.75
    bread
    -0.73
    nikov
    -0.71
    spread
    -0.70
    side
    -0.69
    lain
    -0.69
    tons
    -0.67
    ski
    -0.66
    POSITIVE LOGITS
    ñ
    1.06
    pling
    1.06
    plom
    1.05
    ÃŁ
    1.04
    ordan
    1.02
    plin
    1.00
    qq
    0.96
    abetes
    0.95
    ña
    0.94
    pper
    0.94
    Act Density 0.098%

    No Known Activations