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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political debates and statements

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express opinions or remarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     undet
    -0.81
     unlocks
    -0.74
     reversible
    -0.74
    iencies
    -0.72
    versible
    -0.71
     handy
    -0.71
     dips
    -0.71
     unpredict
    -0.69
     fucked
    -0.68
    bolt
    -0.68
    POSITIVE LOGITS
     Others
    1.17
     They
    1.16
     Their
    1.08
     Critics
    1.05
     Specifically
    1.00
     Speaking
    1.00
     Some
    0.99
     Officials
    0.98
     Advoc
    0.98
     Supporters
    0.98
    Act Density 0.490%

    No Known Activations