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

    Neuronpedia

    INDEX
    Explanations

    cities and numbers related to various locations and values

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various U.S. cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.73
    yout
    -0.68
     artif
    -0.67
     dyed
    -0.65
     recre
    -0.62
     prote
    -0.61
    aws
    -0.60
    vernment
    -0.60
    lehem
    -0.60
     portrayed
    -0.59
    POSITIVE LOGITS
     +
    2.63
    +
    2.13
    +.
    1.66
     +#
    1.64
    +(
    1.59
     +=
    1.56
    -+
    1.54
    plus
    1.49
     ++
    1.47
     âĪĴ
    1.46
    Act Density 0.076%

    No Known Activations