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

    Neuronpedia

    INDEX
    Explanations

    contextual numbers and city names

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸
    -0.82
    SPONSORED
    -0.58
    heit
    -0.57
    ecause
    -0.56
     CARE
    -0.55
    ','
    -0.55
     apologizing
    -0.55
    */(
    -0.54
    oÄŁ
    -0.54
    minster
    -0.54
    POSITIVE LOGITS
    etta
    0.70
    criptions
    0.67
    uncle
    0.66
    ams
    0.64
    inent
    0.63
     Avg
    0.62
    adin
    0.60
     avg
    0.59
    aints
    0.57
    ocalypse
    0.57
    Act Density 0.173%

    No Known Activations