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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a political slogan

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making America great again and expressing positive changes or improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldo
    -0.64
    staking
    -0.61
     doct
    -0.61
     Mub
    -0.60
    secret
    -0.58
     smuggled
    -0.56
     excerpt
    -0.55
     buildup
    -0.55
     Guid
    -0.55
     genesis
    -0.53
    POSITIVE LOGITS
     again
    1.08
     Again
    1.03
    ible
    0.86
    lier
    0.83
    atable
    0.82
    Again
    0.82
    able
    0.81
    terday
    0.80
    again
    0.80
    ABLE
    0.76
    Act Density 0.202%

    No Known Activations