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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political conflict and activism

    oai_token-act-pair · gpt-3.5-turbo

    themes related to political conflict and disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urai
    -0.59
     (@
    -0.57
     TODAY
    -0.57
     Wow
    -0.55
     congratulations
    -0.54
     Explain
    -0.53
     THANK
    -0.53
    combe
    -0.53
    adena
    -0.53
    antage
    -0.52
    POSITIVE LOGITS
     bureaucracy
    0.73
     unfairly
    0.68
     unchecked
    0.68
     adversaries
    0.66
     encro
    0.66
     entrenched
    0.65
     tactics
    0.65
     unfavorable
    0.65
     perceived
    0.65
     ideologies
    0.64
    Act Density 1.435%

    No Known Activations