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

    Neuronpedia

    INDEX
    Explanations

    words related to changes or adjustments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political party changes and policy adjustments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    putable
    -0.77
    cott
    -0.66
    audi
    -0.63
    uala
    -0.62
     Piercing
    -0.62
    llah
    -0.61
    ensual
    -0.60
    bos
    -0.60
    agree
    -0.59
    otal
    -0.59
    POSITIVE LOGITS
     accordingly
    1.07
     habits
    0.76
     fortunes
    0.76
     hinges
    0.72
     structure
    0.70
     layout
    0.68
     facade
    0.67
     dramatically
    0.67
     differently
    0.66
     workflow
    0.66
    Act Density 0.507%

    No Known Activations