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

    Neuronpedia

    INDEX
    Explanations

    names of political figures and organizations

    oai_token-act-pair · gpt-3.5-turbo

    significant mentions of names, organizations, or entities related to political and economic topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.74
    catentry
    -0.71
    \",
    -0.64
    Reviewer
    -0.63
    itionally
    -0.62
    unless
    -0.61
    ittle
    -0.57
    udeb
    -0.57
    cffff
    -0.57
    probably
    -0.57
    POSITIVE LOGITS
     succeeds
    1.28
     hadn
    1.27
     weren
    1.27
     were
    1.18
     fails
    1.10
     survives
    1.08
    were
    1.02
     decides
    1.01
     pans
    1.00
     persists
    0.97
    Act Density 0.258%

    No Known Activations